JP2001050713A - Image processing method and apparatus - Google Patents

Abstract

(57) [Problem] To provide an image processing method and apparatus capable of performing high-speed operation with a small restriction on the installation position of the apparatus and measuring the speed and length of a moving object with high accuracy. SOLUTION: A plurality of line sensor cameras whose imaging axes are parallel are used. The time-series image data A captured by the line sensor camera is divided into strip images (step 401),
The travel time is obtained by associating the strip image with the time-series image data B of the line sensor camera B (step 40).
2), a moving time is obtained by obtaining a moving time of each strip image and a moving distance corresponding thereto (step 403), and the time-series image data and a template of a specific pattern such as wheels are corrected using the moving speed to scale. In addition, a similarity is obtained (step 404), and a threshold value process is performed on the similarity to recognize a specific shape pattern and recognize that the vehicle is a moving vehicle (step 406).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing method and apparatus, and more particularly, to a relative moving speed of an observation point and an object from time-series image data photographed using a line sensor camera or the like. The present invention relates to a method for measuring the length of an object, a pattern recognition method using the same, and an apparatus for them.

[0002]

2. Description of the Related Art As a method for measuring the speed of a moving object using a plurality of sensors, there is a method using two photoelectric tubes. In this method, two phototubes are installed in parallel at a distance from each other, and a speed is obtained from a time difference in which a moving object crosses in front of the phototube. The method is widely used, for example, for measuring the speed of an automobile.

On the other hand, the following methods exist for measuring the speed and length of a moving object from an image. "Traffic flow measurement using double slit image" (Reference (1), IEICE Road Traffic Research Group document RTA94-5, 1994) and "Traffic measurement using double slit camera" (Reference (2), image Journal of the Institute of Electronics, 26-3, 1997). With these methods,
A slit is artificially provided in a video taken by a general video camera, and a spatiotemporal image obtained by connecting images on the slit is used. By providing these slits at two locations and determining the time required for the object to pass between the slits, the passing speed and the length of the object are measured.

[0004]

However, the above prior art has the following problems. When the observation side or the target object moves relatively on a predetermined trajectory and the problem of measuring the relative movement speed, measuring the length of the target object, and recognizing the pattern of the target object is considered, the conventional photoelectric tube is used. In the measurement, the measuring device must be installed so as to sandwich the target object. Further, since an image cannot be acquired by this method, it is unknown what target object has passed in front of the sensor. Therefore, the target object must be confirmed visually by hand.

On the other hand, in the conventional video image, since the two slits are not parallel, the depth must be fixed in advance and the actual moving distance between the slits must be separately obtained. In addition, a general video camera can shoot only 30 frames / second, and when the target object moves at a high speed, it is impossible to obtain speed measurement accuracy. Further, there is no method for measuring a relative moving speed with respect to a target object from an image using a camera installed on the moving object.

SUMMARY OF THE INVENTION Accordingly, an object of the present invention is to solve the problems of the prior art and propose a new method of measuring speed and length, a method of recognizing a pattern, and an apparatus therefor. , Measurement of the relative movement speed when the observation point and the target object move relatively, measurement of the movement speed and length of the target object when the observation point is fixed, and measurement of the target object in those cases An object of the present invention is to provide a technology that can easily perform a pattern recognition process.

[0007]

According to a first aspect of the present invention, there is provided an image processing apparatus, comprising: a moving object which moves on a predetermined trajectory relative to an observation point; An image processing method for measuring a moving speed, comprising: synchronizing a plurality of line image acquiring units installed so that line axes are parallel and traverse a trajectory of a relatively moving target object at a fixed line photographing cycle time. Obtaining each time-series image data taken in time series, and calculating the similarity to associate the image of the target object between the respective time-series image data, Obtaining the moving time of the target object between each line image acquiring means from the deviation amount of the target object and the line photographing cycle time, the moving time, and the image acquisition of each line image acquiring means on the trajectory. And gist image processing method characterized by comprising the steps of: obtaining a relative moving speed between the distance 置間 of the target object and the observation point.

According to a second aspect of the present invention, there is provided an image processing method for measuring a moving speed of a target object moving on a predetermined trajectory, wherein the line axis is parallel and the target object moves. A step of synchronizing a plurality of line image acquisition devices installed so as to cross the orbit and acquiring each time-series image data photographed in a time-series at a constant line photographing cycle time, and Based on the time axis, by associating the target object between the respective time-series image data, a shift amount between image acquisition positions of the line image acquisition device of the target object is calculated, and the shift amount and the shift amount are calculated. Calculating a moving time from a line photographing cycle time; and calculating a moving speed of the target object from the moving time and a distance between image acquisition positions of the line image acquiring devices on the trajectory. The image processing method characterized by having a flop and gist.

According to a third aspect of the present invention, the similarity between the respective time-series image data is calculated so that the target object is associated with each of the time-series image data, and the moving time is reduced. It is a feature that is required.

According to a fourth aspect of the present invention, an image change point at which a difference between each of the time-series image data and a previously acquired background image is equal to or larger than a threshold value is detected, and the image change point in each of the time-series image data is detected. The method is characterized in that the moving object is associated with the target object on the basis of a change point and a moving time is obtained.

Further, according to the present invention, an image change point where a difference between each line image in the time-series image data and the line image one cycle before is equal to or more than a threshold value is detected, The moving object is associated with the target object based on the image change point in the time-series image data.

According to a sixth aspect of the present invention, when a target object having a specific shape pattern recognizable as an image moves on a predetermined trajectory relative to an observation point, the target object is moved. An image processing method for recognizing, wherein a step of obtaining a relative moving speed between an observation point and a target object by using the image processing method according to claim 1, and a scale in a time axis direction based on the relative moving speed. By performing the correction, the step of matching the scale between the time-series image data and the template of the specific shape pattern prepared in advance, and the step between the time-series image data and the template of the specific shape pattern whose scales match. Recognizing the specific shape pattern in the time-series image data by calculating a degree of similarity. The law and the spirit.

According to a seventh aspect of the present invention, there is provided an image processing method for recognizing a target object having a specific shape pattern recognizable as an image when the target object moves on a predetermined trajectory. Obtaining a moving speed of the target object using the image processing method according to claim 2; and correcting a scale in a time axis direction based on the moving speed, thereby preparing time-series image data and time-series image data in advance. The step of matching the scale with the template of the specific shape pattern, and calculating the similarity between the time-series image data and the template of the specific shape pattern with the matched scale, the time-series image data in the time-series image data Recognizing the specific shape pattern.

The invention according to claim 8 is an image processing method for measuring the length of a target object from each time-series image data of the target object moving on a predetermined trajectory, Obtaining the moving speed of the target object using the image processing method according to claim 2, and determining whether a difference between the background image and the background image acquired in advance is equal to or greater than a threshold value, thereby obtaining the time-series image data. Detecting the start point and the end point of the target object from; and obtaining the shooting time from the start point to the end point of the target object based on the line shooting cycle time, and determining the target time from the shooting time and the moving speed of the target object. Calculating the length of the object.

According to a ninth aspect of the present invention, there is provided an image processing method for measuring the length of a target object from each time-series image data of the target object moving on a predetermined trajectory, Obtaining a moving speed of the target object by using the speed measuring method according to claim 2, and determining whether a difference between each line image and each line image one cycle before is equal to or more than a threshold value. By detecting the start point and the end point of the target object from each of the time-series image data, obtaining a shooting time from the start point to the end point based on the line shooting cycle time, from the moving speed and the shooting time Calculating the length of the target object.

According to a tenth aspect of the present invention, there is provided an image processing apparatus for measuring a relative moving speed when an object moves on a predetermined trajectory relative to an observation point, A plurality of line image acquisition units installed so that their axes are parallel and traverse the trajectory of a relatively moving target object acquire each time-series image data imaged in a time-series manner at a fixed line imaging cycle time while synchronizing. And calculating the similarity to associate the image of the target object between each of the time-series image data, to thereby determine the shift amount of the target object between the associated images and the line shooting cycle time. And a time calculating means for calculating the moving time of the target object between each line image acquiring means, and the moving time and the target object from the distance between the image acquiring positions of the line image acquiring means on the trajectory. And gist image processing apparatus characterized by comprising a speed calculation means for calculating a relative speed between the measuring points.

The invention according to claim 11 is an image processing apparatus for measuring the moving speed of a target object moving on a predetermined trajectory, wherein the line axis is parallel and the target object moves. A plurality of line image acquisition units installed so as to cross the orbit; an image acquisition unit for acquiring each time-series image data taken in a time-series manner at a constant line imaging cycle time while synchronizing; and each of the time-series image data. Based on
By associating the target object between the respective time-series image data on the time axis, a shift amount between the image acquisition positions of the line image acquisition means of the target object is calculated, and the shift amount and the line shooting cycle are calculated. Time calculating means for calculating a moving time from time, and speed calculating means for calculating a moving speed of the target object from the moving time and a distance between image acquisition positions of the line image acquiring means on the trajectory. The gist is an image processing apparatus that is a feature.

According to a twelfth aspect of the present invention, the time calculating means associates the target object between the time-series image data by calculating the similarity between the time-series image data. It is characterized by the following.

In the invention according to claim 13, the time calculating means detects an image change point at which a difference between each of the time-series image data and a previously acquired background image is equal to or larger than a threshold value, and The method is characterized in that the target object is associated based on the image change point in the series image data.

In a preferred embodiment of the present invention, the time calculating means includes an image changing point at which a difference between each line image in the time series image data and the line image one cycle before is equal to or more than a threshold value. Is detected, and the target object is associated based on the image change point in each of the time-series image data.

According to a fifteenth aspect of the present invention, when a target object including a specific shape pattern recognizable as an image moves on a predetermined trajectory relatively to an observation point, the target object is moved. An image processing apparatus for recognizing, comprising: a speed measuring unit including the image processing device according to claim 10; and correcting a scale in a time axis direction based on a relative moving speed obtained by the speed measuring unit. By doing so, scale correction means for matching the scale of the time-series image data obtained by the speed measurement means with the template of the specific shape pattern prepared in advance, and the time-series image data and the specific shape pattern with matching scales Pattern detection means for detecting and recognizing the specific shape pattern by calculating a similarity between the template and the template. And gist image processing apparatus according to claim Rukoto.

According to the present invention, when an object including a specific shape pattern recognizable as an image moves on a predetermined trajectory, the object is recognized at a stationary observation point. An apparatus, comprising:
Speed measuring means provided with an image processing apparatus according to the, and by correcting the scale in the time axis direction based on the moving speed obtained by the speed measuring means, time-series image data acquired by the speed measuring means Scale correction means for matching the scale with the template of the specific shape pattern prepared in advance, and by calculating the similarity between the time-series image data and the template with the specific shape pattern whose scale matches, A gist of the present invention is an image processing apparatus including pattern detection means for detecting and recognizing the specific shape pattern.

According to a seventeenth aspect of the present invention, there is provided an image processing apparatus for measuring the length of a target object moving on a predetermined trajectory, wherein the speed is provided with the image processing apparatus according to the eleventh aspect. Measuring means, image change point detecting means for detecting a starting point and an ending point of the target object from each of the time-series image data by determining whether a difference between the previously acquired background image is equal to or greater than a threshold value, and Length calculation means for obtaining a shooting time from the start point to the end point of the target object based on a line shooting cycle time of the measurement means, and calculating a length of the target object from the shooting time and a moving speed of the target object. The gist of the present invention is an image processing apparatus including:

[0024] According to an eighteenth aspect of the present invention, there is provided an image processing apparatus for measuring the length of a target object moving on a predetermined trajectory, the speed comprising the image processing apparatus according to the eleventh aspect. An image for detecting a start point and an end point of a target object from each of the time-series image data by determining whether or not a difference between each of the line images and the line image one cycle before the line image is equal to or greater than a threshold value. Change point detection means, and length calculation means for obtaining a shooting time from the start point to the end point based on the line shooting cycle time, and calculating the length of the target object from the moving speed and the shooting time. The gist of the present invention is an image processing apparatus provided with the above.

Further, the invention according to claim 19 is provided with recording means for recording the image data acquired by the line image acquiring means together with the measured moving speed of the target object and the pattern recognition result. The means is characterized in that a polarizing filter is mounted.

According to a twentieth aspect of the present invention, there is provided a recording device for recording the image data acquired by the line image acquiring device together with the measured moving speed of the target object and the pattern recognition result. The means is provided with a visible light cut filter that cuts visible light and transmits infrared light.

[0027]

Embodiments of the present invention will be described below in detail with reference to the drawings.

<Embodiment 1> An embodiment of a speed measurement and pattern recognition method and a device thereof according to a first embodiment of the present invention will be described. In the present embodiment, as an example of image processing using a plurality of line sensor cameras, a measurement system in which two line sensor cameras are installed is mounted on the moving vehicle, and the moving speed of the moving vehicle moving on a predetermined track is measured. The stationary vehicle is recognized as the stationary vehicle as the stationary vehicle. Here, the predetermined track is, for example, a lane on a road. At this time, the moving vehicle and the stationary object relatively move, and the stationary object moving on a predetermined trajectory in a system based on the moving vehicle is observed by the line sensor camera. The relative movement speed is measured.

FIG. 1 shows an apparatus for carrying out the speed measurement and pattern recognition method according to the first embodiment of the present invention. The information processing apparatus 101 shown in FIG.
02, a storage device 103, a display device 104 such as a display, and a measurement device 105 are connected. However, in the storage device 103, a measured value accumulating unit 106 and an image accumulating unit 107 are provided. Further, a line sensor camera A 108, a line sensor camera B 109, and a synchronizer 110 are provided in the measuring device 105. Here, the synchronizer 110 is, for example, a pulse generator. The time-series image data from the line sensor camera is synchronized with the two cameras using the synchronization device 110, and is imaged at a constant line imaging cycle time.

The line sensor camera used in the present embodiment is a monochrome line sensor camera. Each pixel has 256 gradations of 8 bits, the number of pixels of each line is 2048, and the photographing time interval for each line, that is, the line photographing cycle time is 10 minutes.
0 μs.

FIG. 2 is a diagram showing an example of a speed measuring method, a pattern recognizing method and a measuring system in the apparatus according to the present embodiment, wherein 201 is a stopped vehicle 1, 202 is a stopped vehicle 2, 203 is a moving vehicle, and 204 is a moving vehicle. Is the moving direction, 205 is the line sensor camera A, 20 installed on the moving vehicle 203.
Reference numeral 6 denotes a line sensor camera B installed on the moving vehicle 203.

FIG. 3 is a view of the measuring system of FIG. 2 as viewed from above, where 301 is a moving vehicle, 302 is a moving direction, 303 is a line sensor camera A, 304 is a line sensor camera B,
305 is an angle θ, 306 is a distance L between line axes, 307 is a moving distance Lr, 308 is a stopped vehicle 1, and 309 is a stopped vehicle 2. The direction in which the moving vehicle 301 moves is the moving direction 3
02 and the line sensor camera A with respect to the moving direction 302.
303 and the line sensor camera B 304 have an angle θ 305
Let's say it's leaning. At this time, the actual moving distance Lr307 when the stopped vehicle relatively moves between the line axes is obtained as Lr = L / sin (θ).

FIG. 4 is a flowchart of the speed measurement and pattern recognition method according to the present embodiment.
The processes from 01 to 406 are processes executed by the information processing apparatus 101 such as a CPU of a personal computer.
Hereinafter, the speed measurement and pattern recognition method of the present embodiment will be described with reference to the flowchart of FIG.

First, the traveling speed of the relative moving vehicle is measured. First, the time-series image data A411 captured by the line sensor camera A303 is divided into strip images (step 401). FIG. 5 shows an example of the time-series image data of the line sensor camera and the divided strip image,
Represents time-series image data A of the line sensor camera A, 502
Represents time-series image data B of the line sensor camera B, 503
Is a strip image, 504 is a matched area, 505 is a strip width W, and 506 is a moving time Tv. The number of lines in the time axis direction of the strip image is preferably about 10 to 20, and the number of pixels in one line is 2,048. In this case, the number of pixels in one strip image is about 20,480 to 40,960.

Next, the strip image and the line sensor camera B3
04 and the time lag amount are calculated (step 402). As shown in FIG. 5, the line sensor camera B3 comes before the line sensor camera A303.
Since the stopped vehicle crosses in front of 04, the area 504 that matches on the time-series image data B corresponding to the strip image 503 exists on the time axis 507. Therefore, the similarity is calculated using the difference calculation and the correlation coefficient calculation (see “Image Processing Handbook” (Ref. (3), Shokodo, 1987)) only in the negative direction of the time axis. Region 50 matched using values
4 is detected, and the time lag amount is calculated.

Here, a strip image 503 divided on the basis of the time-series image data A501 and the time-series image data B502
A method of associating with. For association, a cross-correlation value between both images is calculated, and a point having the highest correlation value within a predetermined range and having the highest correlation is detected. When the number of pixels in one line of a strip image is m and the number of lines is n, the brightness (gradation) of each point in the strip image is Ia
(i, j). Further, the brightness of each point of the partial area for n lines starting from time t in the time-series image data B 412 is represented by I
Let b (t, i, j). Assuming that the average and variance of the brightness in each region are μa, μb (t), σa ² , σb (t) ² , the cross-correlation value c (t) between these regions is given by the following equation.

[0037]

(Equation 1)

This c (t) takes a value in the range of -1 to 1, and becomes closer to 1 as the similarity between the two partial regions increases. Therefore, t is used as a variable, that is, the strip image 503 is shifted in the time axis direction on the time-series image data B502, and t at which the value of c (t) is closest to 1 is detected, and the time-series image data B5
The matched area 504 in 02 is determined.

Note that instead of calculating the cross-correlation value, a difference value d (t) according to the following equation may be used.

[0040]

(Equation 2)

The closer the d (t) is to 0, the higher the similarity between the two images.

If the number of lines in a strip image is too small, there is a high possibility that an error will occur in associating the images, while if the number of lines is too large, the calculation time for calculating the similarity will be too long. In addition, the change of the correlation value or the difference value becomes too gradual, and the accuracy of the association decreases. Accordingly, when the number of pixels in one line is about 2048 as in the present embodiment, the number of lines in the strip image is set to one.
It is desirable to set it to about 0 to 20.

Next, a moving speed using the time shift amount of each strip image and the corresponding moving distance is obtained (step 403). Specifically, the time shift amount, that is, the moving time Tv, is obtained as follows using the number of moving pixels P of the strip image and the photographing time interval Tc of the line sensor camera: Tv = P × Tc. Therefore, the moving speed Vm of the moving object is obtained as follows: Vm = Lr / Tv

It should be noted that if the above-described speed measurement processing is performed on all of the plurality of strip images and the obtained plurality of measurement results are averaged or a representative value is obtained by majority decision, etc.,
Measurement accuracy can be improved. That is, each strip image included in the time-series image data A captured by the line sensor camera A is associated with the time-series image data B captured by the line sensor camera B to determine the time lag amount, and to determine the speed. calculate. Then, based on the speed measurement result values corresponding to the number of strip images thus obtained, an average value is calculated, or a representative value is determined by majority decision or the like.

As described above, it is possible to measure the moving speed of a moving object using two line sensor cameras.

Next, pattern recognition of a specific geometric pattern of the moving object is performed from the time-series image data.
Processing for recognizing a moving object will be described.

First, the time-series image data and the template of the specific pattern prepared in advance in a database or the like are taken out using the moving speed, and the scale in the time axis direction is corrected using the already calculated moving speed. Then, the similarity is calculated (step 405). Here, a wheel is used as a specific pattern to be detected.

FIG. 6 shows an example of a template of a specific pattern.
2 is the length Xt in the time axis direction, 603 is the length Yt in the line axis direction, 604 is the template of the corrected specific pattern, 605 is the length X in the time axis direction, and 606 is the length Y in the line axis direction. is there. Specific pattern template 601
Is time-series image data captured at the time interval Ttc, X = Xt × Ttc / Tc, and the scales in the time axis direction can be matched. On the other hand, the scale in the line axis direction changes depending on the depth distance from the line sensor camera at the time of shooting. Therefore, the template of the specific pattern is scaled up and down in the direction of the line axis to match the scale. Thereafter, the similarity is obtained by the above-described difference calculation or cross-correlation value calculation (see Document (3)), and when a similarity higher than a predetermined similarity is obtained, it is determined that the pattern has matched. Here, the template of the specific pattern is corrected to match the scale, but the time-series image data or both may be corrected.

Next, the pattern is recognized using the similarity,
The stopped vehicle is recognized (step 406). By performing threshold processing, that is, processing based on whether or not the degree of similarity calculated in step 405 is equal to or greater than a predetermined threshold, wheels having a specific pattern are recognized. Therefore, if a wheel is detected in the time-series image data, it means that the stationary object is a stopped vehicle. As described above, a stationary object can be recognized from time-series image data using two line sensor cameras.

In this embodiment, the observation point is moved and the target object is stationary. However, even if both are moved, the relative movement speed can be measured by the same method. In the above, an example in which wheels are used as a specific pattern has been described.However, after performing scale correction in the time axis direction according to the moving speed, it is also possible to perform pattern recognition on a license plate attached to the front and rear surfaces of the vehicle. It is possible.

<Embodiment 2> An embodiment of a speed and length measurement and pattern recognition method and a device thereof according to a second embodiment of the present invention will be described below. In the present embodiment, an observation point on which two line sensor cameras are installed as a plurality of examples is fixed, and velocity measurement, length measurement, and pattern recognition of a moving object moving on a predetermined trajectory are performed. Here, the predetermined trajectory is, for example, a lane when the moving object is a vehicle, or a sidewalk when the moving object is a pedestrian. The same measuring device as that of the first embodiment is used as the measuring device of the present embodiment (see FIG. 1).

FIG. 7 is a diagram showing an example of a speed and length measurement and pattern recognition method and a measurement system in the apparatus according to the present embodiment, in which 701 is a moving vehicle, 702 is a line sensor camera A, 703 is a line sensor camera. B and 704 are measurement devices.

FIG. 8 is a view of the measuring system of FIG. 7 as viewed from above, where 801 is a moving vehicle, 802 is a moving direction, 803 is a line sensor camera A, 804 is a line sensor camera B,
805 is an angle θ, 806 is a distance L between line axes, and 807 is a movement distance Lr. The direction in which the moving vehicle 801 moves is defined as a moving direction 802, and the line sensor camera A 803 and the line sensor camera B 804 are inclined at an angle θ805 with respect to the moving direction 802. At this time, the actual moving distance Lr807 when the moving vehicle passes between the line axes is obtained as Lr = L / sin (θ).

FIG. 9 is a flowchart of the speed measurement, length measurement, and pattern recognition method according to the present embodiment. The processing of steps 901 to 906 shown in FIG. 9 is executed by the information processing apparatus 101 such as a CPU of a personal computer. This is the process to be performed. Hereinafter, the speed measurement, the length measurement, and the pattern recognition method according to the present embodiment will be described with reference to the flowchart in FIG.

First, the moving speed of the moving vehicle is determined. First, the line sensor camera A 803 and the line sensor camera B 804 extract an image pattern including the moving vehicle 801 from each of the time-series images 911 and 913 that are synchronously photographed in a time-series at a constant line photographing cycle time (step). 901). Images captured in advance by the line sensor camera A 803 and the line sensor camera B 804 when there is no moving vehicle are converted into background images A 912 and B 91.
4 is stored in the image storage unit 107.

FIG. 10 is a diagram showing an example of a time-series image of the line sensor camera, wherein 1001 is time-series image data A of the line sensor camera A, 1002 is time-series image data B of the line sensor camera B, and 1003 is Background images A and 1004 for the line sensor camera A are background images B and 1005 for the line sensor camera B are time axes. The background image A1003 and the background image B1004 are images having a width of one line or several lines. In this embodiment, since the observation point is fixed, the time-series image data A
An image in which the moving vehicle 801 exists on a continuous background image, such as 1001 and time-series image data B1002, is obtained. Therefore, the difference calculation and the correlation coefficient calculation with respect to the background image are performed for each line or every several lines (refer to Reference (3)), and the threshold value processing and the labeling processing (refer to Reference (3)) are performed based on the obtained values. This makes it possible to extract an image pattern including a region different from the background image, that is, a moving object. However, since the background image changes depending on the lighting conditions, the background image may be updated at any time. In addition,
The cross-correlation value c
(t) or the definition formula of the difference value d (t) can be used.

Next, the extracted image patterns are associated with each other in the time-series images, and the time shift amount of the image patterns is obtained (step 902).

FIG. 11 is a diagram showing an example of an image pattern extracted from each time-series image data. 1101 is an image pattern A in the time-series image data A, and 1102 is an image pattern in the time-series image data B. B, 1103 denotes a moving time Tv, 1104 denotes a photographing time Tm, and 1105 denotes a time axis. First, each image pattern is associated. Specifically, the correspondence is established based on the difference calculation and the correlation coefficient calculation between the image patterns (see Document (3)). After the association, the time shift amount of the corresponding image pattern, that is, the moving distance Lr807
Is determined for the moving time Tv1103.

Next, a moving speed using the time shift amount of the image pattern and the corresponding moving distance is obtained (step 903). Specifically, the time shift amount, that is, the movement time Tv is
Using the number P of moving pixels of the image pattern in the time-series image data and the shooting interval Tc of the line sensor camera, Tv = P × Tc is obtained. Therefore, the moving speed Vm of the moving object is obtained as follows: Vm = Lr / Tv As described above, it is possible to measure the moving speed of a moving object using two line sensor cameras.

Next, the length of the moving object is obtained using the photographing time and moving time of each image pattern (step 90).
4). The imaging time Tm1104 of the image pattern is a time between the start point and the end point of the image pattern on the time axis. Therefore,
The length Lm of the moving object is obtained by Lm = Vm × Tm. In general, when the angle θ 805 with respect to the moving direction 802 is other than 0, not only the side surface but also the front surface is photographed as shown in FIG. 10, so that an accurate object length in the moving direction cannot be obtained. However, as shown in FIG. 12, even when the angle θ is other than 0, when only the side surface is reflected in the time-series image data and the side surface is parallel to the moving direction, an accurate object length for the moving direction can be obtained. . Therefore, when measuring the length of the moving object, the angle θ80
A time-series image when 5 is set to 0 is used (see FIGS. 13 and 1).
4).

Next, pattern recognition of a specific geometric pattern of the moving object is performed from the time-series image data.
Recognize moving objects.

First, using the moving speed, the time-series image data and the template of the specific pattern prepared in advance in a database or the like are taken out, corrected, scaled, and the similarity is calculated (step 905). Here, wheels are used as the specific patterns to be detected as in the first embodiment. Similar to step 405 shown in the first embodiment,
Also in the present embodiment, the similarity can be obtained.

Next, the pattern is recognized using the similarity,
The moving vehicle is recognized (step 906). Step 90
By performing a threshold process on the similarity of No. 5, the wheels that are the specific patterns are recognized. Therefore, the shooting time of the moving object 11
If a wheel is detected in the time-series image data in 04, it means that the moving object is a moving vehicle. As described above, a moving object can be recognized from time-series image data using two line sensor cameras.

<Embodiment 3> An embodiment of a speed measuring method, a pattern recognition method, and a device thereof according to a third embodiment of the present invention will be described below. In the present embodiment, an observation point where two line sensor cameras are installed as a plurality of examples is fixed, and velocity measurement and pattern recognition of a moving object are performed. The measurement system of the present embodiment uses the same measurement system as that of the second embodiment (see FIGS. 7 and 8).

FIG. 15 is a flowchart of the speed measurement method and the pattern recognition method according to the present embodiment. Steps 1501 to 1505 shown in FIG. 15 are processing executed by the information processing apparatus 101 such as a CPU of a personal computer. Hereinafter, the speed measurement and pattern recognition method according to the present embodiment will be described with reference to the flowchart in FIG.

First, the moving speed of the moving object is obtained. First, an image change point on the time axis is detected from each of the time-series image data 1511 and 1512 (step 1501). However, the time-series image data is acquired in the same manner as in the second embodiment. FIG. 16 is an example of a diagram showing a temporal change in the image of the time-series image data. In FIG. 16, reference numeral 1601 denotes time-series image data A of the line sensor camera A, 1602 denotes one line image and one line image immediately before the line image. Change in the amount of change in time, 16
03 is an image change point, 1604 is a threshold value for the change amount, 1
605 is a time axis. In this embodiment, since the observation point is fixed, there is almost no temporal change in the image when there is no moving object. On the other hand, the change of the image at the moment when the moving object starts to pass is large. Therefore, a temporal change 1602 of the image change amount is obtained by a difference calculation or a correlation coefficient calculation (see Document (3)). Assuming that the number of pixels per line is m, the brightness (gradation) at time t of the i-th (1 ≦ i ≦ m) pixel in the line is I (t, i), and the line scanning time interval is t0, The above temporal change 1602 is given as e (t) defined by the following equation.

[0067]

(Equation 3)

An image change point 1603 is obtained by a process (threshold process) based on whether the amount of change is equal to or greater than a threshold 1604.
Can be requested. A similar process is performed on the time-series image data B1512 of the line sensor camera B to determine an image change point.

Next, the correspondence between each image change point and the time shift amount are calculated. As in the present embodiment, when the moving direction of the moving vehicle is determined, the vehicle crosses the line sensor camera B after crossing the line sensor camera A. Therefore, it is detected as an image change point from the time-series image data A, and the image change point of the time-series image data B immediately after that is associated with the start point of the image pattern of the moving vehicle. Even when the moving direction of the vehicle is unknown, the nearby image change point is associated with the start point or the end point of the image pattern of the moving vehicle. When the association is completed, the speed of the moving object can be calculated from the moving time and the actual moving distance as in the second embodiment.

The pattern recognition processing in steps 1504 to 1505 is obtained in the same manner as in the second embodiment.

<Embodiment 4> Hereinafter, an embodiment of a speed measurement and length measurement method according to a fourth embodiment of the present invention and an apparatus thereof will be described. In the present embodiment, an observation point on which two line sensors are installed as a plurality of examples is fixed, and velocity measurement and length measurement of a moving object are performed. The same measurement system as that of the second and third embodiments is used for the measurement system of the present embodiment (see FIGS. 7 and 8).

FIG. 17 is a flowchart of the speed measurement and length measurement method according to the present embodiment. Steps 1701 to 1704 shown in FIG. 17 are processes executed by the information processing apparatus 101 such as a CPU of a personal computer. Hereinafter, the speed measurement and the length measurement method of the present embodiment will be described with reference to the flowchart of FIG. First, the moving speed of the moving object is obtained. First, the start point and the end point of the image change area with the background image are detected on the time axis from the time-series image data 1711 and 1713 as in the second embodiment (step 1).
701).

FIG. 18 is an example of a diagram showing the temporal change in the amount of change between the time-series image data and the background image.
Represents time-series image data A of the line sensor camera A, 180
2 is a background image A, 1803 is a temporal change of the amount of change from the background image, 1804 is an image change point (start point), 1805 is an image change point (end point), 1806 is a threshold for the amount of change, 1
807 is a time axis. In this embodiment, since the observation point is fixed, when there is no moving object, there is almost no temporal change between the time-series image data and the background image. On the other hand, the change of the image when the moving object passes is large.
Accordingly, a temporal change 1803 in the amount of change from the background image is obtained by difference calculation or correlation coefficient calculation (see Document (3)). An image change point (start point) 1804 and an image change point (end point) are obtained by performing threshold processing with a threshold 1806 on the amount of change.
1805 can be obtained. Line sensor camera B
A similar process is performed on the time-series image data B1713 to obtain the start point and the end point of the image change point.

Next, the correspondence between each image change point and the time shift amount are calculated. Here, the start point and the end point of the image change point are considered as an image change point set. As in the present embodiment, when the moving direction of the moving vehicle is determined, the vehicle crosses the line sensor camera B after crossing the line sensor camera A. Therefore,
The set of image change points is detected from the time-series image data A, and the set of image change points of the time-series image data B immediately after that is associated with the start point and the end point of the image pattern of the moving vehicle. Even when the moving direction of the vehicle is unknown, a set of nearby image change points is associated as a set of a start point and an end point of an image pattern of the moving vehicle. When the association is completed, the speed of the moving object can be calculated from the moving time and the actual moving distance as in the first embodiment.

In the length measuring process of step 1704, the time between the start point and the end point is equivalent to the photographing time of the moving object.
This can be performed in the same manner as in the second embodiment.

In the second, third, and fourth embodiments, the image of the side surface is targeted. However, as shown in FIGS. 19 and 20, a line sensor camera A1902, 2003 having a moving vehicle 1901, 2001 installed on the top is connected to a line. Sensor camera B19
Also, the present invention can be applied to an image captured from 03,2004. As shown in FIGS. 21 and 22, the line sensor cameras A2102 and 2202 are used to accumulate the processing results.
In addition, the result of pattern recognition may be displayed or recorded on a still image or a video image of a moving object (moving vehicle 2101 or 2011) in synchronization with the line sensor cameras B2103 and 2203 and the area sensors 2104 and 2204. . Although two line sensor cameras are used, two or more line sensor cameras may be installed.

<Embodiment 5> Next, an embodiment of a speeding vehicle control system using the speed measuring method of the present invention will be described. In the present embodiment, the observation point where the two line sensor cameras are installed is fixed, and the speed measurement of the moving vehicle and the license plate recognition are performed.

FIG. 23 is a view showing an example of a speeding vehicle control system according to this embodiment. The line sensor camera A 3102, the line sensor camera B 3103, and the infrared light 3104 are installed on a gantry so that the moving vehicle 3101 can be photographed from above. The line axis of the line sensor camera A3102 and the line axis of the line sensor camera B3103 are set in parallel, and the image is taken synchronously at a constant line image taking cycle time. Also, a line sensor camera A310
2 and the line sensor camera B3103 are equipped with a polarizing filter for suppressing irregular reflection of the windshield and photographing the driver, and a visible light cut filter (infrared transmitting filter) for obtaining a stable image regardless of day and night. .

FIG. 24 is a side view of the system of FIG. 23. The line sensor camera A3203, the line sensor camera B3204, and the infrared light 3208 are installed at an angle θ downward with respect to the ground. At this time, the moving distance Lr of the moving vehicle between the line sensor camera A and the line sensor camera B is Lr = L / sin (θ).

FIG. 25 shows an example of time-series images obtained from the line sensor cameras A and B. Thus, by installing the line sensor camera downward from above, it becomes possible to photograph the license plate and the driver.

FIG. 26 is a flow chart showing the processing of the speeding vehicle control system using the speed measurement method of the present invention, and the outline along this flow chart will be described below. First, the time-series image data A of the line sensor camera A and the time-series image data B of the line sensor camera B are acquired, and an image change point on the time axis is detected from each of the time-series image data (step 3401).

FIG. 27 shows an example of a temporal change in the amount of change between the one-line image and the immediately preceding one-line image.
An image change point can be detected by a threshold value for the change amount.

Next, the correspondence between the image change points between the time-series image data A and B and the movement time are calculated (step 3402). When the moving direction of the moving vehicle is predetermined as shown in FIG. 24, the vehicle crosses the line sensor camera A and the line sensor camera B in this order. Therefore, an image change point is detected from the time-series image data A, and the image change point of the time-series image data B immediately after that is associated with the start point of the image pattern of the moving vehicle. Therefore, the moving time Tv with respect to the moving distance Lr between the two line sensor cameras of the moving vehicle
Is as shown in FIG. Next, the moving speed Vm of the moving vehicle is calculated using the moving distance Lr and the moving time Tv (step 3403). The moving speed Vm is obtained from the following equation. Vm = Lr / Tv

Next, the time-series image data and the previously stored character pattern template are corrected using the moving speed, and the similarity is calculated (step 3404). And
Characters are recognized based on the similarity and a license plate recognition result is output (step 3405).

FIG. 29 shows an example of time-series image data of the license plate portion when the speed of the moving vehicle is low and high. As shown in FIG. 29, the characters on the license plate are elongated when they are slow, and are crushed when they are fast. Therefore, the height of the characters on the license plate can be normalized by dividing the time axis of each time-series image data in FIG. 25 by the moving speed. If it can be normalized, regardless of the moving speed,
Conventional license plate recognition technology based on similarity ("Ch
aracter Recognition in Scene Images ”(Reference (4), So
ciety of Manufacturing Engineers, 1989)). Here, since there are two types of image data to be recognized, that of the line sensor camera A and that of the line sensor camera B, it is possible to increase the recognition accuracy by performing license plate recognition on each image. I can do it.

When the license plate becomes recognizable, a portion where the two images of the time-series image data A and B completely match can be known, so that the moving time of the plate position is recalculated to improve the accuracy of the moving speed. Can be enhanced.

As described above, the speed of a moving vehicle that is higher than the legal speed can be measured, characters on the license plate of the vehicle can be recognized, and an image of the driver can be stored.

In the above description, reference numerals 108, 205, 303, 702, 803, 120
2,1303,1902,2003,2102,220
2 and 3102 represent the same line sensor camera A. Similarly, reference numerals 109, 206, 304, 70
3,804,1203,1304,1903,200
4, 2103, 2203, 3103, and 3204 represent the same line sensor camera B. Similarly, reference numerals 701, 801, 1201, 1301, 1901, and 902
001, 2101, and 201 each represent a moving vehicle to be measured.

Similarly, reference numerals 306, 806, 130
5, 2005, 3205 represent the distance L between the line axes of the line sensor camera. Similarly, reference numeral 30
7, 807, 2007, and 3207 represent the moving distance Lr of the measurement target. Similarly, reference numerals 506 and 11
Reference numerals 03, 1403, and 3604 each denote a moving time Tv required to move the moving distance Lr. Similarly, reference numeral 1
Each of 104 and 1404 represents a photographing time Tm from the start point to the end point.

A program for realizing the functions of the above-described processes is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system and executed to execute speed measurement, Pattern recognition or length measurement may be performed.
Here, the “computer system” is an OS
And peripheral devices.

The “computer-readable recording medium” is a portable medium such as a floppy (registered trademark) disk, a magneto-optical disk, a ROM, a CD-ROM, or a storage device such as a hard disk built in a computer system. That means. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) inside a computer system that becomes a server or a client when a program is transmitted through a network such as the Internet or a communication line such as a telephone line. And those holding programs for a certain period of time.

The above program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting a program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.

The above program may be a program for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

Although the embodiments of the present invention have been described in detail with reference to the drawings, the specific configuration is not limited to these embodiments, and the design and the like may be made without departing from the gist of the present invention. included.

[0095]

According to the present invention, there is provided a method for measuring a relative moving speed when a target object moves on a predetermined trajectory relative to an observation point, the method comprising: Synchronizes a plurality of line image acquisition devices installed so as to be parallel and traverse the trajectory of a relatively moving target object to acquire each time-series image data captured in a time-series at a fixed line imaging cycle time And calculating the degree of similarity, by associating the image of the target object between the respective time-series image data, from the shift amount of the target object between the associated images and the line shooting cycle time. Calculating the moving time of the target object between the line image acquiring devices; and the relative time between the target object and the observation point based on the moving time and the distance between the image acquiring positions of the line image acquiring devices on the trajectory. Achieved by an image processing method having a step of obtaining the dynamic speed. With this method, the line image acquisition device acquires a clear image at high speed,
The calculation based on the image makes it possible to measure the relative moving speed of the target object with respect to the observation point.

Another object of the present invention is to provide a method of recognizing a target object having a specific shape pattern recognizable as an image when the target object moves on a predetermined trajectory relative to an observation point. Calculating the relative moving speed between the observation point and the target object using the speed measuring method, and correcting the scale in the time axis direction based on the relative moving speed, thereby obtaining time-series image data. And matching the scale with the template of the specific shape pattern prepared in advance, and calculating the similarity between the time-series image data with the matched scale and the template of the specific shape pattern. Detecting and recognizing the specific shape pattern in the sequence image data. With this method, it is possible to easily recognize the pattern of the moving target object.

Further, according to the present invention, there is provided a method for measuring the length of a target object from each time-series image data obtained by photographing the target object moving on a predetermined orbit while fixing an observation point. Determining the moving speed of the target object using a speed measurement method, and determining whether or not the difference between the previously acquired background image is equal to or greater than a threshold value, the starting point of the target object from each of the time-series image data and Detecting an end point; obtaining a shooting time from the start point to the end point of the target object based on the line shooting cycle time; calculating a length of the target object from the shooting time and a moving speed of the target object And measuring the length of the target object.

In the present invention, when the observation point is fixed and the target object moves on a predetermined trajectory, the moving speed measurement, the target object length measurement, and the target object pattern recognition processing can be performed. become able to.

Further, in the present invention, when a line image acquisition device (such as a line sensor camera) is used, it is not necessary to install the target object so as to sandwich the object, so that the installation is easier than the photoelectric tube. Unlike the case of the photoelectric tube, since the target object can be stored as image data, the target object can be specified after the measurement.

Further, since the use of the line image acquisition device enables a high-speed photographing of about 1000 times as compared with a video camera, the speed can be measured with higher precision than a conventionally used video camera, and an object which moves at a high speed Speed measurement is also possible. Also, unlike when using a video camera,
By installing a plurality of line image acquisition devices in parallel, it is possible to measure the speed independently of the distance from the camera.

Further, in the present invention, by increasing the number of line image acquisition devices to be used, speed measurement and length measurement can be performed by the number of combinations of line image acquisition devices, so that measurement accuracy can be improved. . Further, even if the target object cannot be recognized from one image due to the influence of noise or the like, the recognition processing is applied to another image, so that the accuracy of pattern recognition can be improved.

Further, since the apparatus of the present invention can photograph only with visible light, it is possible to measure the speed and length and recognize the pattern without being noticed by the measurement object.

[Brief description of the drawings]

FIG. 1 shows an example of a measuring apparatus according to a first embodiment of the present invention.

FIG. 2 shows an example of a measurement system for recognizing a stopped vehicle according to the first embodiment.

FIG. 3 is a view of the measurement system of FIG. 2 as viewed from above.

FIG. 4 is a flowchart of a speed measurement method and a pattern recognition method according to the first embodiment.

FIG. 5 shows an example of an output from the line sensor camera in the first embodiment.

FIG. 6 is a diagram illustrating an example of a template of a specific pattern according to the first embodiment.

FIG. 7 shows an example of a measurement system for measuring a moving vehicle according to the second embodiment of the present invention.

8 is a view of the measurement system of FIG. 7 as viewed from above.

FIG. 9 is a flowchart of a speed measurement method, a length measurement method, and a pattern recognition method according to the second embodiment.

FIG. 10 illustrates an example of an output from a line sensor camera according to the second embodiment.

FIG. 11 shows an example of an image pattern extraction result according to the second embodiment.

FIG. 12 is a diagram illustrating an example of a measurement system when measuring a moving vehicle according to the second embodiment as viewed from above.

FIG. 13 is a diagram illustrating an example of a measurement system when measuring a moving vehicle according to the second embodiment as viewed from above.

FIG. 14 illustrates an example of an output from a line sensor camera according to the second embodiment.

FIG. 15 is a flowchart of a speed measurement and pattern recognition method according to the third embodiment of the present invention.

FIG. 16 illustrates an example of a graph of an output from a line sensor camera and an image change amount according to the third embodiment.

FIG. 17 is a flowchart of a velocity measurement and length measurement method according to the fourth embodiment of the present invention.

FIG. 18 illustrates an example of a graph of an output from a line sensor camera and an image change amount with respect to a background image according to the fourth embodiment.

FIG. 19 shows an example of another measurement system when measuring the moving vehicles according to the second, third, and fourth embodiments of the present invention.

20 is a diagram of the measurement system of FIG. 18 as viewed from a side.

FIG. 21 illustrates an example of a measurement system in a case where the moving vehicles according to the second, third, and fourth embodiments of the present invention are measured and a measurement result is recorded in synchronization with an output of an area sensor.

FIG. 22 shows an example of a measurement system in a case where the moving vehicles according to the second, third, and fourth embodiments of the present invention are measured and the measurement result is recorded in synchronization with the output of the area sensor.

FIG. 23 shows an installation state of a moving vehicle speed measurement and license plate recognition device according to a fifth embodiment of the present invention.

FIG. 24 is a side view illustrating an example of the measurement of the speed of the moving vehicle according to the fifth embodiment of the present invention.

FIG. 25 shows an example of an output from a line sensor camera according to Embodiment 5 of the present invention.

FIG. 26 is a flowchart of a method for measuring a speed of a moving vehicle and recognizing a license plate according to Embodiment 5 of the present invention;

FIG. 27 illustrates an example of a graph of an output from a line sensor camera and an image change amount according to the fifth embodiment.

FIG. 28 illustrates an example of an image pattern extraction result according to the fifth embodiment.

FIG. 29 is a diagram illustrating speed correction of a license plate image according to the fifth embodiment.

[Explanation of symbols]

Reference Signs List 101 information processing device 102 bus line 103 storage device 104 display device 105 measuring device 106 measured value accumulating unit 107 image accumulating unit 108 line sensor camera A 109 line sensor camera B 110 synchronizing device 201, 202 stopped vehicle 203 moving vehicle 204 moving direction 205 Line sensor camera A 206 Line sensor camera B 301 Moving vehicle 302 Moving direction 303 Line sensor camera A 304 Line sensor camera B 305 Angle θ 306 Distance between line axes L 307 Moving distance Lr 308,309 Stopped vehicle 501 For line sensor camera A Sequence image data A 502 Time-series image data B 503 of the line sensor camera B Strip image 504 Matched area 505 Strip width W 506 Moving time Tv 507 Time axis 601 Temp of specific pattern 604 Line sensor camera A 703 Line sensor camera B 704 Measuring device 801 Moving vehicle 802 Moving direction 803 Line sensor camera A 804 Line sensor camera B 805 Angle θ 806 Distance between line axes L 807 Moving distance Lr 1001 Time-series image data A 1002 of the line sensor camera A Time-series image data B 1003 of the line sensor camera B 1003 Background image A 1004 Background image B 1005 Time axis 1101 Image pattern A 1102 Image pattern B 1103 Moving time Tv 1104 Shooting time Tm 1105 Time axis 1201 Moving vehicle 1202 Line sensor camera A 1203 Line sensor camera B 1301 Moving vehicle 1302 Moving direction 1303 Line sensor camera A 1304 Line sensor camera B 1305 Line axis distance L 1401 Time series image data A 1402 of line sensor camera A Time series image data B 1403 of line sensor camera B Moving time Tv 1404 Shooting time Tm 1405 Time axis 1601 Line sensor camera A Time series image data A 1602 Temporal change of change amount between one line image and one line image immediately before it 1603 Image change point 1604 Threshold value for change amount 1605 Time axis 1801 Time series image data A 1802 of line sensor camera A Background Image A 1803 Temporal change of change amount from background image 1804 Image change point (start point) 1805 Image change point (end point) 1806 Threshold for change amount 1807 Time axis 1901 Moving vehicle 1902 Line sensor Camera A 1903 Line sensor Camera B 2001 Moving vehicle 2002 Moving direction 2003 Line sensor camera A 2004 Line sensor camera B 2005 Distance between line axes L 2006 Angle θ 2007 Moving distance Lr 2101 Moving vehicle 2102 Line sensor camera A 2103 Line sensor camera B 2104 Area sensor 2201 Moving vehicle 2202 line sensor camera A 2203 line sensor camera B 2204 area sensor 3101 moving vehicle 3102 line sensor camera A 3103 line sensor camera B 3104 infrared illumination 3105 license plate 3201 moving vehicle 3202 moving direction 3203 line sensor camera A 3204 line sensor camera B 3205 line Inter-axis distance L 3206 Angle θ 3207 Moving distance Lr 3208 Infrared illumination 3301 line Time-series image data A 3302 of the sensor camera A Time-series image data B 3303 of the line sensor camera B Time axis 3501 Time-series image data A 3502 of the line sensor camera A The change amount between the one-line image and the immediately preceding one-line image Time change 3503 Image change point 3504 Threshold for change amount 3505 Time axis 3601 Time series image data A 3602 of line sensor camera A 3602 Time series image data B of line sensor camera B 3603 Time axis 3604 Moving time Tv 3701 Time axis 3702 License plate 3703 Time-series image data of the license plate (when the speed is low) 3703 Time-series image data of the license plate (when the speed is high) 3704 Image of the license plate normalized based on the speed

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G06T 7/20 G06T 7/20 200B 200 G08G 1/01 A G08G 1/01 1/04 C 1/04 G01B 11/24 K (72) Inventor Akio Shio 2-3-1 Otemachi, Chiyoda-ku, Tokyo Nippon Telegraph and Telephone Corporation (72) Inventor Sakuichi Otsuka 2-3-1 Otemachi, Chiyoda-ku, Tokyo Nippon Telegraph and Telephone Corporation

Claims (20)

[Claims] 1. An image processing method for measuring a relative moving speed when a target object moves on a predetermined trajectory relative to an observation point, wherein a line axis is parallel and relatively moves. Synchronizing a plurality of line image acquisition means installed across the trajectory of the target object to acquire each time-series image data taken in a time-series at a fixed line imaging cycle time, and calculating a similarity By doing so, the image of the target object is associated with each of the time-series image data, and the target object between each line image acquisition unit is calculated from the shift amount of the target object between the associated images and the line shooting cycle time. Calculating a moving time of the object; and calculating a relative moving speed between the target object and the observation point from the moving time and a distance between image acquisition positions of the line image acquiring means on the trajectory. An image processing method comprising: 2. An image processing method for measuring a moving speed of a target object moving on a predetermined trajectory, wherein the plurality of lines are arranged such that line axes are parallel and traverse the trajectory of the moving target object. A step of acquiring each time-series image data taken in a time-series manner at a fixed line photographing cycle time by synchronizing the line image acquisition device, based on each of the time-series image data, By associating the target object between the time-series image data, a shift amount between the image acquisition positions of the line image acquisition devices of the target object is calculated, and a moving time is calculated from the shift amount and the line shooting cycle time. Obtaining the moving speed of the target object from the moving time and the distance between the image obtaining positions of the respective line image obtaining devices on the trajectory. Image processing method for. 3. A moving time is calculated by calculating a similarity between the respective time-series image data, thereby associating the target object with each of the time-series image data. The image processing method according to 1. 4. A method for detecting an image change point at which a difference between each of the time-series image data and a previously acquired background image is equal to or greater than a threshold value, and detecting the target object based on the image change point in each of the time-series image data. The image processing method according to claim 2, wherein the moving time is obtained by performing association. 5. An image change point where a difference between each line image in each of the time-series image data and a line image one cycle before is greater than or equal to a threshold, and the image change point in each of the time-series image data is detected. 3. A moving time is obtained by associating the target object based on
The image processing method according to 1. 6. An image processing method for recognizing a target object having a specific shape pattern recognizable as an image when the target object moves on a predetermined trajectory relatively to an observation point, Obtaining a relative moving speed between an observation point and a target object by using the image processing method according to claim 1; and correcting a scale in a time axis direction based on the relative moving speed, thereby obtaining a time-series image. Matching the scale of the data and the template of the specific shape pattern prepared in advance; and calculating a similarity between the time-series image data with the matched scale and the template of the specific shape pattern, Recognizing the specific shape pattern in the time-series image data. 7. An image processing method for recognizing a target object having a specific shape pattern recognizable as an image when the target object moves on a predetermined trajectory, the image processing according to claim 2. Calculating the moving speed of the target object using the method, and correcting the scale in the time axis direction based on the moving speed, thereby obtaining a scale between the time-series image data and the template of the specific shape pattern prepared in advance. Recognizing the specific shape pattern in the time-series image data by calculating a similarity between the time-series image data and the template of the specific shape pattern whose scales match. An image processing method comprising: 8. An image processing method for photographing a target object moving on a predetermined trajectory from a fixed observation point and measuring a length of the target object from each time-series image data. Obtaining a moving speed of the target object using the image processing method described in 2 above; and determining whether a difference between the background image acquired in advance is equal to or greater than a threshold value to thereby obtain an object from each of the time-series image data. Detecting the starting point and the ending point of the object; determining the shooting time from the starting point to the ending point of the target object based on the line shooting cycle time; and determining the shooting time of the target object from the shooting time and the moving speed of the target object. Calculating the length. 9. An image processing method for measuring the length of a target object from each time-series image data of a target object moving on a predetermined trajectory from a fixed observation point, Obtaining a moving speed of the target object by using the image processing method according to 2, and determining whether a difference between each line image and a line image one cycle before the line image is equal to or more than a threshold value,
Detecting a start point and an end point of the target object from each of the time-series image data; obtaining a shooting time from the start point to the end point based on the line shooting cycle time; and obtaining the target object from the moving speed and the shooting time. Calculating the length of the object. 10. An image processing apparatus for measuring a relative moving speed when a target object moves on a predetermined trajectory relative to an observation point, wherein the line axes are parallel and relatively move. A plurality of line image acquisition units installed so as to traverse the trajectory of the target object, and an image acquisition unit that acquires each time-series image data taken in a time-series manner at a fixed line imaging cycle time while synchronizing, By calculating, the image of the target object is associated with each of the time-series image data, and the shift amount of the target object between the associated images and the line photographing cycle time are used to calculate each line image acquisition means. Time calculating means for calculating the moving time of the target object; calculating the relative moving speed between the target object and the observation point from the moving time and the distance between the image obtaining positions of the line image obtaining means on the trajectory. An image processing apparatus comprising: 11. An image processing apparatus for measuring a moving speed of a target object moving on a predetermined trajectory, wherein the plurality of lines are arranged such that line axes are parallel and traverse the trajectory of the moving target object. Image acquisition means for acquiring each time-series image data taken in a time-series manner at a fixed line imaging cycle time while the line image acquisition means is synchronized, based on each of the time-series image data, By associating the target object between the respective time-series image data, a shift amount between the image acquisition positions of the line image acquisition means of the target object is calculated, and a moving time is calculated from the shift amount and the line shooting cycle time. And a speed calculating means for calculating a moving speed of the target object from the moving time and a distance between image acquisition positions of the respective line image acquiring means on the trajectory. The image processing apparatus according to claim Rukoto. 12. The apparatus according to claim 11, wherein the time calculation unit calculates the similarity between the time-series image data to associate the target object with the time-series image data. Image processing device. 13. The time calculating means detects an image change point at which a difference between each of the time-series image data and a previously acquired background image is equal to or greater than a threshold value, and determines the image change point in each of the time-series image data. The image processing apparatus according to claim 11, wherein the target object is associated with the target object. 14. The time calculating means detects an image change point at which a difference between each line image in each of the time-series image data and the line image one cycle before is equal to or more than a threshold value, and detects each of the time-series image data. The image processing apparatus according to claim 11, wherein the target object is associated based on the image change point in data. 15. An image processing apparatus for recognizing a target object including a specific shape pattern recognizable as an image when the target object moves on a predetermined trajectory relative to an observation point, A speed measuring unit comprising the image processing device according to claim 10, and a time axis scale is corrected based on a relative moving speed obtained by the speed measuring unit, thereby acquiring the speed measuring unit. Scale correction means for matching the scale of the time-series image data obtained and the template of the specific shape pattern prepared in advance, and the similarity between the time-series image data and the template of the specific shape pattern whose scales match. And a pattern detecting means for detecting and recognizing the specific shape pattern by calculating apparatus. 16. An apparatus for recognizing a target object at a stationary observation point when the target object including a specific shape pattern recognizable as an image moves on a predetermined orbit. Speed measuring means comprising the image processing device according to the above, by correcting the scale in the time axis direction based on the moving speed obtained by the speed measuring means, the time series image data acquired by the speed measuring means and Scale correction means for matching the scale of the prepared template with the specific shape pattern, and calculating the similarity between the time-series image data with the matched scale and the template with the specific shape pattern, An image processing apparatus comprising: a pattern detection unit that detects and recognizes a specific shape pattern. 17. An image processing apparatus for measuring a length of a target object moving on a predetermined trajectory from a fixed observation point, wherein the speed measuring means comprises the image processing apparatus according to claim 11. Image change point detecting means for detecting a start point and an end point of the target object from each of the time-series image data by determining whether a difference between the background image acquired in advance is not less than a threshold value, and the speed measuring means Length calculating means for calculating a shooting time from the start point to the end point of the target object based on the line shooting cycle time, and calculating a length of the target object from the shooting time and a moving speed of the target object. An image processing apparatus comprising: 18. An image processing device for measuring the length of a target object moving on a predetermined trajectory from a fixed observation point, wherein the speed measuring means comprises the image processing device according to claim 11. By determining whether the difference between each line image and each line image one cycle before is equal to or greater than a threshold,
Image change point detecting means for detecting a start point and an end point of the target object from each of the time-series image data; and obtaining a shooting time from the start point to the end point based on the line shooting cycle time, the moving speed and the shooting time. And a length calculating means for calculating the length of the target object from the following. 19. A recording unit for recording the image data acquired by the line image acquiring unit together with the measured moving speed of the target object and the pattern recognition result, and the line image acquiring unit is provided with a polarizing filter. The image processing apparatus according to claim 16, wherein: 20. Recording means for recording the image data acquired by said line image acquiring means together with the measured moving speed of the target object and the pattern recognition result, wherein said line image acquiring means cuts visible light and emits infrared light. The image processing apparatus according to claim 16, further comprising a visible light cut filter that transmits light.