CN114743191B - A method and related device for judging fake license plates based on license plate trajectory - Google Patents
A method and related device for judging fake license plates based on license plate trajectoryInfo
- Publication number
- CN114743191B CN114743191B CN202210437432.3A CN202210437432A CN114743191B CN 114743191 B CN114743191 B CN 114743191B CN 202210437432 A CN202210437432 A CN 202210437432A CN 114743191 B CN114743191 B CN 114743191B
- Authority
- CN
- China
- Prior art keywords
- license plate
- track
- fake
- characteristic
- axis direction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
本申请实施例公开了一种伪车牌判断方法，包括：获取车牌数据；根据所述车牌数据确定第一车牌轨迹；根据所述第一车牌轨迹进行计算得到第一轨迹特征值；判断是否满足预设数量的所述第一轨迹特征值处于对应的特征范围内，所述特征范围为训练得到的非伪车牌轨迹的特征值范围；若不满足，则将所述第一车牌轨迹对应的车牌确定为伪车牌，所述伪车牌为对可通过道闸的车牌进行伪造仿制得到的车牌。
The embodiment of the present application discloses a method for judging a fake license plate, including: obtaining license plate data; determining a first license plate trajectory according to the license plate data; calculating a first trajectory feature value according to the first license plate trajectory; judging whether a preset number of the first trajectory feature values are within a corresponding feature range, the feature range being the feature value range of a non-fake license plate trajectory obtained through training; if not, determining the license plate corresponding to the first license plate trajectory as a fake license plate, the fake license plate being a license plate obtained by forging and imitating a license plate that can pass through a barrier.
Description
Technical Field
The embodiment of the application relates to the field of video monitoring, in particular to a fake license plate judging method based on license plate tracks and a related device.
Background
In order to bring convenience to parking management, license plate recognition apparatuses for recognizing license plates have been widely used at entrances and exits of parking lots. Currently, mainstream license plate recognition equipment is provided with cameras to collect data, the collected license plates of vehicles are recognized to switch on and off, the vehicles enter and leave a parking place, and the parking place charges according to the parking time of the vehicles.
However, in order to avoid charging, some owners attack by using fake license plates, such as mobile phone license plates, paper license plates, manufactured license plates and other fake and imitated license plates, and the fake license plates imitating the license plates which can pass through the barrier gate truly are opened by placing the fake license plates in front of an erected camera, so that the method does not meet the expectations of users. How to judge the authenticity of license plates is an important problem.
Disclosure of Invention
The embodiment of the application provides a fake license plate judging method based on a license plate track and a related device.
A fake license plate judging method based on license plate tracks comprises the following steps:
Obtaining license plate data;
Determining a first license plate track according to the license plate data;
Calculating according to the first vehicle license plate track to obtain a first track characteristic value;
Judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic ranges, wherein the characteristic ranges are the characteristic value ranges of the trained non-fake license plate tracks;
if the license plate is not satisfied, the license plate corresponding to the first license plate track is determined to be a fake license plate, and the fake license plate is obtained by forging and imitating the license plate which can pass through the gate.
Optionally, determining the first license plate track according to the license plate data includes:
obtaining a license plate frame of each frame according to the license plate data;
judging whether license plate numbers corresponding to license plate frames of every two adjacent frames are the same or not;
if so, extracting a license plate frame of a previous frame in every two adjacent frames with the same license plate number;
And determining a first license plate track according to the extracted license plate frame.
Optionally, after judging whether license plate numbers corresponding to license plate frames of every two adjacent frames are the same, before determining the first license plate track according to the extracted license plate frames, the method further includes:
if not, judging whether the license plate numbers of every two adjacent frames with different license plate numbers have the condition of continuous four bits and more than the same bit number;
If the number of the license plate is four or more, extracting the license plate frame of the previous frame in every two adjacent frames with the same number of bits.
Optionally, after judging whether the license plate numbers of every two adjacent frames with different license plate numbers have the same continuous four digits or more, before determining the first license plate track according to the extracted license plate frame, the method further includes:
If the number of the license plate does not meet the continuous four-bit and more than the same number of the adjacent two frames, calculating the intersection ratio;
judging whether the cross ratio is larger than a preset threshold value or not;
If the number is larger than the number, extracting the license plate frame of the previous frame in every two adjacent frames with the same number of continuous four digits and more digits not met by the license plate number.
Optionally, after the license plate track is a pseudo license plate track, the method further includes:
And uploading the early warning information and the license plate data to a server.
Optionally, before determining whether the preset number of first track feature values is within the corresponding feature range, the method further includes:
Acquiring training data;
Determining a second license plate track and a third license plate track according to the training data, wherein the second license plate track is a plurality of non-fake license plate tracks in the training data, and the third license plate track is a plurality of fake license plate tracks in the training data;
calculating according to the second license plate track to obtain a second track characteristic value, and calculating according to the third license plate track to obtain a third track characteristic value;
and screening according to the second track characteristic value and the third track characteristic value to obtain the characteristic range.
Optionally, the characteristic range includes an average speed characteristic range of the track in the x-axis direction, a variance characteristic range of the track in the x-axis direction, an average speed characteristic range of the track in the y-axis direction, a variance characteristic range of the track in the y-axis direction, and a slope characteristic range of the track.
A fake license plate judgment device, comprising:
The acquisition unit is used for acquiring license plate data;
the determining unit is used for determining a first license plate track according to the license plate data;
The calculating unit is used for calculating according to the first vehicle license plate track to obtain a first track characteristic value;
The judging unit is used for judging whether the preset number of first track characteristic values are in a corresponding characteristic range or not, wherein the characteristic range is a characteristic value range of a non-fake license plate track obtained through training;
the determining unit is further configured to determine, when the preset number of license plates corresponding to the first license plate track is not met, a fake license plate, where the fake license plate is a license plate obtained by forging and imitating a license plate that can pass through the channel gate.
A fake license plate judgment device, comprising:
a central processing unit, a memory and an input/output interface;
the memory is a short-term memory or a persistent memory;
the central processor is configured to communicate with the memory and to execute the instruction operations in the memory to perform the aforementioned methods.
A computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the aforementioned method.
From the above technical solutions, the embodiment of the present application has the following advantages:
after license plate data are acquired, a first license plate track is determined, and then a first track characteristic value is calculated. And judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic ranges, and determining the license plate corresponding to the first license plate track as a fake license plate when the preset quantity is not met. Based on the license plate track, whether the license plate is a fake license plate track or not is judged through the feature range of the trained non-fake license plate track, namely whether the license plate is a fake license plate or not is judged, so that the authenticity of the license plate can be accurately judged, and the expected of a user is met.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for determining a fake license plate according to the present application;
FIG. 2 is a schematic diagram of another embodiment of a method for determining a fake license plate according to the present application;
FIG. 3 is a schematic diagram of an embodiment of a license plate judgment device according to the present application;
fig. 4 is a schematic diagram of another embodiment of a license plate determining device according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a fake license plate judging method based on a license plate track and a related device.
The license plate can be called as the name of the vehicle, and the relevant information of the vehicle can be obtained by detecting the license plate. The license plate recognition device at the entrance and the exit of the existing parking lot evades charges under the attack of fake license plates of some car owners. In order to solve the above problems, the embodiments of the present application provide a method and related apparatus for determining a fake license plate.
The method for judging the fake license plate based on the license plate track and the related device are described below.
Referring to fig. 1, an embodiment of a method for determining a fake license plate according to the present application includes:
101. obtaining license plate data;
License plate data are acquired through the camera equipment. The license plate data are video data of a time period from when the license plate starts to appear in the identification area to when the license plate disappears in the identification area, namely video data of movement of the license plate in the identification area of the image pickup device. The most common camera equipment is a camera, which is used for monitoring and collecting license plate data at the entrance and the exit of a parking lot. When the camera deflects the body for external reasons, a clear, complete image can be captured by controlling the swing of the camera to complete the subsequent operation.
102. Determining a first license plate track according to the license plate data;
After license plate data is obtained, a first license plate track is determined according to the license plate data. Specifically, after the video data of the license plate is obtained, the video data is divided into data of different frames, and then the license plate data of each frame is identified to obtain the license plate number, the license plate frame and the position of the license plate frame of the license plate. And judging and confirming according to the obtained result, so that the first vehicle license track can be obtained. The first license plate track is composed of the extracted license plate frames and reflects the movement condition of the license plate in the identification area of the camera in the video recording time.
103. Calculating according to the first vehicle license plate track to obtain a first track characteristic value;
and calculating according to the first vehicle track to obtain a first track characteristic value. After the first vehicle license track is obtained, a plane coordinate system is established, the coordinates of the central point of a license plate frame forming the first vehicle license track are marked, and then the relevant track characteristic value of the first vehicle license track is calculated. The track characteristic value comprises a speed on an x-axis, an average speed on the x-axis, a variance on the x-axis, a speed on a y-axis, an average speed on the y-axis, a variance on the y-axis, a slope of the track, an acceleration on the x-axis, an acceleration on the y-axis and the like, which represent the characteristic of the track.
104. Judging whether the preset number of first track characteristic values are in the corresponding characteristic range or not, if not, executing a step 105, and if so, executing a step 106;
Judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic range. Specifically, the preset number may be considered to be set according to the requirement, for example, set to number 3, number 5, or the like. The characteristic range is a characteristic value range of the non-fake license plate track obtained through training. For example, assume that this step is to determine whether 3 or more first track feature values are within the corresponding feature range. The characteristic range representing the non-fake license plate includes an average speed characteristic range of 10 to 15 in the x-axis direction of the track, a variance characteristic range of 2 to 3 in the x-axis direction of the track, an average speed characteristic range of 11 to 16 in the y-axis direction of the track, a variance characteristic range of 3.5 to 5 in the y-axis direction of the track, and a slope characteristic range of 0.5 to 0.8 of the track. Assume that the first track characteristic value of the first card track includes an average speed on the x-axis of 11, a variance on the x-axis of 2.6, an average speed on the y-axis of 9, a variance on the y-axis of 5.1, and a slope of the track of 0.6. And determining that the first license plate track is a non-fake license plate, namely a true license plate, by judging that 3 first track characteristic values fall into the characteristic range.
105. Determining a license plate corresponding to the first license plate track as a fake license plate;
If the number of the first track characteristic values which are not preset is in the corresponding characteristic range, the license plate corresponding to the first license plate track is determined to be a fake license plate. The fake license plate is obtained by forging and imitating the license plate which can pass through the channel gate, and the concept of the fake license plate is opposite to that of the fake license plate.
106. And determining the license plate corresponding to the first license plate track as a non-fake license plate.
If the preset number of first track characteristic values are in the corresponding characteristic range, the license plate corresponding to the first license plate track is determined to be a non-fake license plate.
In the embodiment of the application, after license plate data are acquired, a first license plate track is determined, and then a first track characteristic value is calculated. And judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic ranges, and determining the license plate corresponding to the first license plate track as a fake license plate when the preset quantity is not met. Based on the license plate track, whether the license plate is a fake license plate track or not is judged through the feature range of the trained non-fake license plate track, namely whether the license plate is a fake license plate or not is judged, so that the authenticity of the license plate can be accurately judged, and the expected of a user is met.
Referring to fig. 2, another embodiment of the method for determining a fake license plate according to the present application includes:
201. acquiring training data;
Training data is acquired. The training data comprise non-fake license plate data and fake license plate data, and the non-fake license plate data are obtained through cameras erected at the entrances and exits. The fake license plate data comprises a mobile phone license plate, a paper license plate and a imitated license plate, and is recorded by simulating an attack means possibly used by a vehicle owner. In order to ensure that the non-fake license plate data of the real vehicle is representative, the data of the passing gates of a plurality of vehicles in a plurality of scenes are required to be collected, and the data validity can be ensured by collecting the data of the non-fake license plate data of 100 vehicles. In addition, in order to improve the accuracy, data acquisition can be performed in the daytime and at night respectively.
202. Determining a second license plate track and a third license plate track according to the training data;
And determining a second license plate track and a third license plate track according to the training data, wherein the second license plate track is a plurality of non-fake license plate tracks in the training data, and the third license plate track is a plurality of fake license plate tracks in the training data. Specifically, the training data comprises data of a plurality of license plates, after the training data is obtained, each piece of license plate data in the training data is divided into data of different frames, and then the license plate data of each frame is identified to obtain the license plate number, the license plate frame and the position of the license plate frame of the license plate. And judging and confirming according to the obtained result. The second license plate track and the third license plate track can be obtained by carrying out a series of judgment on license plate numbers and the intersection ratio of two adjacent frames. For example, the training data includes 100 pieces of non-fake license plate data and 100 pieces of fake license plate data, and if one piece of data obtains one track, 100 pieces of true license plate tracks and 100 pieces of fake license plate tracks can be obtained.
203. Calculating according to the second license plate track to obtain a second track characteristic value, and calculating according to the third license plate track to obtain a third track characteristic value;
And calculating according to the second license plate track and the third license plate track to obtain a second track characteristic value and a third track characteristic value. And calculating the track characteristic value of each real license plate track and the track characteristic value of each fake license plate track so as to carry out subsequent operation. Specifically, after the tracks are obtained, a plane coordinate system is established, and coordinates (x 1, y 1), (x 2, y 2), (x 3, y 3), (x 4, y 4) and the like can be obtained by marking the coordinates of the central points of the corresponding license plate frames forming each license plate track. And then calculating the relevant track characteristic value of the license plate track. The track characteristic value comprises a speed on an x-axis, an average speed on the x-axis, a variance on the x-axis, a speed on a y-axis, an average speed on the y-axis, a variance on the y-axis, a slope of the track, an acceleration on the x-axis, an acceleration on the y-axis and the like, which represent the characteristic of the track. The slope of the trace is described in terms of velocity, average velocity and variance on the x-axis.
The speed of the license plate track on the x-axis is calculated by the following formula:
Where v x is the speed between two frames, Δx is the speed difference between two frames, and Δf is the number of frame intervals between two frames.
The average speed of the license plate track on the x-axis can be obtained by averaging a plurality of v x.
The variance of license plate tracks on the x-axis is calculated by the following formula:
Where s x is the variance on the x-axis, i denotes the i-th coordinate, n denotes the total number of coordinates, v xi is the speed of the i-th coordinate on the x-axis, mean (v x) denotes the average speed on the x-axis.
The method for calculating the speed and variance of the license plate track on the y-axis is similar to that described above, and will not be repeated here.
The slope of the license plate track is calculated by the following formula:
k is the slope, Δx is the speed difference on the x-axis, and Δy is the speed difference on the y-axis.
204. Screening according to the second track characteristic value and the third track characteristic value to obtain the characteristic range;
And screening according to the second track characteristic value and the third track characteristic value to obtain the characteristic range. Specifically, after a plurality of second track characteristic values and a plurality of third track characteristic values are obtained, the ranges are respectively divided, so that a plurality of ranges of true license plate track characteristic values and a plurality of ranges of false license plate track characteristic values are obtained. And setting the coincidence rate of the range of the characteristic value of the real license plate track and the range of the characteristic value of the pseudo license plate track to be not more than a certain percentage, such as twenty percent, and if the coincidence rate is not more than a certain percentage, determining the range of the corresponding characteristic value of the real license plate track as the characteristic range. For example, the average speed characteristic value range on the x-axis of the real license plate track is 1 to 10, the average speed characteristic value range on the x-axis of the fake license plate track is 9 to 15, the coincidence rate is ten percent, and the average speed characteristic value range on the x-axis of the real license plate track can be determined as the characteristic range.
According to practice, the characteristic range includes an average speed characteristic range of the track in the x-axis direction, a variance characteristic range of the track in the x-axis direction, an average speed characteristic range of the track in the y-axis direction, a variance characteristic range of the track in the y-axis direction, and a slope characteristic range of the track.
205. Obtaining license plate data;
License plate data are acquired through the camera equipment. The license plate data are video data of a time period from when the license plate starts to appear in the identification area to when the license plate disappears in the identification area, namely video data of movement of the license plate in the identification area of the image pickup device. The most common camera equipment is a camera, which is used for monitoring and collecting license plate data at the entrance and the exit of a parking lot. When the camera deflects the body for external reasons, a clear, complete image can be captured by controlling the swing of the camera to complete the subsequent operation.
206. Obtaining a license plate frame of each frame according to the license plate data;
After license plate data is obtained, a license plate frame of each frame is obtained according to the license plate data. Specifically, after the video data of the license plate is obtained, the video data is divided into data of different frames, and then the license plate data of each frame is identified to obtain the license plate number, the license plate frame and the position of the license plate frame of the license plate.
207. Judging whether license plate numbers corresponding to license plate frames of every two adjacent frames are the same, if so, executing step 208, and if not, executing step 209;
Judging whether license plate numbers corresponding to the license plate frames of every two adjacent frames are identical or not, specifically, judging from a first frame to a last second frame in video data, and detecting whether the license plate numbers corresponding to the license plate frames of the two adjacent frames are completely identical or not. For example, the 1 st frame and the 2 nd frame are firstly determined, then the 2 nd frame and the 3 rd frame are determined, and so on, which are not described herein.
208. Extracting a license plate frame of a previous frame in every two adjacent frames with the same license plate number;
And extracting the license plate frame of the previous frame in every two adjacent frames with the same license plate number. Specifically, in every two adjacent frames, the license plate frames of the previous frame are extracted, wherein the license plate numbers are identical. For example, if the 1 st frame license plate number is the same as the 2 nd frame license plate number, the 1 st frame license plate frame is extracted.
209. Judging whether the license plate numbers of every two adjacent frames with different license plate numbers have the condition of identical continuous four bits and more bits, if so, executing the step 210, and if not, executing the step 211;
Judging whether the license plate numbers of every two adjacent frames with different license plate numbers have the condition of continuous four digits and more digits, specifically, judging whether the license plate numbers of every two adjacent frames are not consistent with the condition that the license plate numbers are the same, and judging whether the license plate numbers have the condition of continuous four digits and more digits.
210. Extracting license plate frames of a previous frame in every two adjacent frames with the same number of continuous four bits and more than four bits of license plate numbers;
And extracting the license plate frame of the previous frame in every two adjacent frames with the same number of continuous four bits and more than four bits of the license plate number. Specifically, in every two adjacent frames, the license plate number is not identical but the number of continuous four bits and more bits are identical, the license plate frame of the previous frame is extracted, for example, the license plate number of the 2 nd frame is identified as 123456, the license plate number of the 3 rd frame is identified as 123465, and if 1234 exists in both frames, the license plate frame of the 2 nd frame is extracted.
211. Calculating the intersection ratio of every two adjacent frames with the same continuous four-bit number and more than the continuous four-bit number of the license plate number;
and calculating the cross ratio of every two adjacent frames with the same continuous four-bit number and more than the continuous four-bit number. Specifically, in every two adjacent frames, the license plate number is identified as not conforming to the condition that the number of continuous four bits and more is the same, and the cross ratio is calculated. For example, if the 3 rd frame license plate number is identified as 123465, the 4 th frame license plate number is identified as 123654, and only 123 are identical, the intersection ratio of the two frames is calculated. The intersection ratio refers to the overlapping ratio of two frames, i.e. the ratio of the intersection to the union of two frames, and is commonly used for target detection.
212. Judging whether the cross ratio is greater than a preset threshold, if so, executing step 213, and if not, executing step 207;
and after calculating the cross-over ratio, judging whether the cross-over ratio is larger than a preset threshold value or not. Specifically, the preset threshold may be set according to experience and requirements, and is generally set to 0.5.
213. Extracting a license plate frame of a previous frame in every two adjacent frames with the same number of continuous four bits and more than the number of the license plate;
And extracting the license plate frame of the previous frame in every two adjacent frames with the same number of bits, wherein the number of the license plate does not meet the continuous four bits or more. Specifically, in every two adjacent frames, the license plate number does not meet the condition that the number of continuous four bits and more is the same and the intersection ratio is larger than a preset threshold value, and the license plate frame of the previous frame is extracted. For example, the 3 rd frame license plate number is identified as 123465, the 4 th frame license plate number is identified as 123654, the intersection ratio of the two frames is 0.6 and is larger than 0.5, and then the 3 rd frame license plate frame is extracted.
214. Determining a first license plate track according to the extracted license plate frame;
and determining a first license plate track according to the extracted license plate frame. Specifically, the license plate frames of the previous frame in the two adjacent frames with the same number of digits, the same number of continuous four digits and more digits and the same intersection ratio larger than a preset threshold are extracted, and the first license plate track can be determined by the license plate frames and the positions of the license plate frames.
215. Calculating according to the first vehicle license plate track to obtain a first track characteristic value;
And calculating according to the first vehicle track to obtain a first track characteristic value. After the first vehicle license track is obtained, a plane coordinate system is established, the coordinates of the central point of a license plate frame forming the first vehicle license track are marked, and then the relevant track characteristic value of the first vehicle license track is calculated. The track characteristic value comprises a speed on an x-axis, an average speed on the x-axis, a variance on the x-axis, a speed on a y-axis, an average speed on the y-axis, a variance on the y-axis, a slope of the track, an acceleration on the x-axis, an acceleration on the y-axis and the like, which represent the characteristic of the track. The specific calculation formula may refer to the content related to step 203, and will not be described herein.
216. Judging whether the preset number of first track characteristic values are in the corresponding characteristic range or not, if not, executing step 217, and if yes, executing step 218;
Judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic range. Specifically, the preset number may be considered to be set according to the requirement, for example, set to number 3, number 5, or the like. The characteristic range is a characteristic value range of the non-fake license plate track obtained through training. For example, assume that this step is to determine whether 3 or more first track feature values are within the corresponding feature range. The characteristic range representing the non-fake license plate includes an average speed characteristic range of 10 to 15 in the x-axis direction of the track, a variance characteristic range of 2 to 3 in the x-axis direction of the track, an average speed characteristic range of 11 to 16 in the y-axis direction of the track, a variance characteristic range of 3.5 to 5 in the y-axis direction of the track, and a slope characteristic range of 0.5 to 0.8 of the track. Assume that the first track characteristic value of the first card track includes an average speed on the x-axis of 11, a variance on the x-axis of 2.6, an average speed on the y-axis of 9, a variance on the y-axis of 5.1, and a slope of the track of 0.6. And determining that the first license plate track is a non-fake license plate, namely a true license plate, by judging that 3 first track characteristic values fall into the characteristic range.
217. Determining a license plate corresponding to the first license plate track as a fake license plate;
If the number of the first track characteristic values which are not preset is in the corresponding characteristic range, the license plate corresponding to the first license plate track is determined to be a fake license plate. The fake license plate is obtained by forging and imitating the license plate which can pass through the channel gate, and the concept of the fake license plate is opposite to that of the fake license plate.
218. Determining a license plate corresponding to the first license plate track as a non-fake license plate;
If the preset number of first track characteristic values are in the corresponding characteristic range, the license plate corresponding to the first license plate track is determined to be a non-fake license plate.
219. And uploading the early warning information and the license plate data to a server.
After judging that the license plate in the license plate data is a fake license plate, uploading the early warning information and the license plate data to a server. The early warning information can prompt a server operator to process, and license plate data can be stored in the server as evidence. If the real license plate track is judged to be the fake license plate track, an operator can learn the license plate track through setting and update the characteristics of the learned characteristic range, and the automatic update of the characteristic range is realized through adding configuration items on the platform.
In this embodiment, the license plate track is trained first to obtain the feature range. After license plate data are acquired, a first license plate track is determined, and then a first track characteristic value is calculated. And judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic ranges, and determining the license plate corresponding to the first license plate track as a fake license plate when the preset quantity is not met. In the training process, three kinds of judgment are used to improve the judgment accuracy, and in addition, based on the license plate track, whether the feature range of the trained non-fake license plate track is a fake license plate track or not is judged, namely whether the license plate is a fake license plate or not is judged, so that the authenticity of the license plate can be accurately judged. After the fake license plate is judged, the fake license plate can be uploaded to a server for early warning, evidence is saved, and the method meets the expectations of users.
Referring to fig. 3, an embodiment of the pseudo license plate determining device according to the present application includes:
an acquiring unit 301, configured to acquire license plate data;
a determining unit 302, configured to determine a first license plate track according to the license plate data;
A calculating unit 303, configured to calculate a first track feature value according to the first vehicle license plate track;
The judging unit 304 is configured to judge whether a preset number of first track feature values are within a corresponding feature range, where the feature range is a feature value range of a non-pseudo license plate track obtained through training;
the determining unit 302 is further configured to determine, when the preset number of license plates corresponding to the first license plate track is not satisfied, a license plate corresponding to the first license plate track as a fake license plate, where the fake license plate is a license plate obtained by forging and imitating a license plate that can pass through the aisle gate.
In the embodiment of the present application, after the obtaining unit 301 obtains license plate data, the determining unit 302 determines the first license plate track, and the calculating unit 303 calculates the first track feature value. And then judging whether the first track characteristic values meeting the preset quantity are in the corresponding characteristic ranges or not through the judging unit 304, and determining the license plate corresponding to the first license plate track as a fake license plate when the preset quantity is not met. Based on the license plate track, whether the license plate is a fake license plate track or not is judged through the feature range of the trained non-fake license plate track, namely whether the license plate is a fake license plate or not is judged, so that the authenticity of the license plate can be accurately judged, and the expected of a user is met.
The functions and procedures executed by each unit in the fake license plate judgment device in this embodiment are similar to those executed by the fake license plate judgment device in fig. 1 to 2, and are not repeated here.
Fig. 4 is a schematic structural diagram of a fake license plate judging device according to an embodiment of the present application, where the fake license plate judging device 400 may include one or more central processing units (central processing units, CPU) 401 and a memory 405, and one or more application programs or data are stored in the memory 405.
Wherein the memory 405 may be volatile storage or persistent storage. The program stored in the memory 405 may include one or more modules, each of which may include a series of instruction operations in the fake license plate judgment device. Still further, the central processor 401 may be configured to communicate with the memory 405, and execute a series of instruction operations in the memory 405 on the license plate pseudo judgment device 400.
The fake license plate determination device 400 may also include one or more power supplies 402, one or more wired or wireless network interfaces 403, one or more input/output interfaces 404, and/or one or more operating systems, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.
The cpu 401 may execute the operations executed by the pseudo license plate determining device in the embodiments shown in fig. 1 to 2, and detailed descriptions thereof are omitted herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a usb disk, a removable hard disk, a read-only memory (ROM), a random-access memory (RAM, random access memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
Claims (9)
1. A fake license plate judging method based on a license plate track is characterized by comprising the following steps:
Obtaining license plate data;
Determining a first license plate track according to the license plate data;
Calculating according to the first vehicle license plate track to obtain a first track characteristic value;
Judging whether a preset number of first track characteristic values are in a corresponding characteristic range or not, wherein the characteristic range is a characteristic value range of a non-fake license plate track obtained through training, the preset number is at least three, the first track characteristic values comprise average speed of the track in the x-axis direction, variance of the track in the x-axis direction, average speed of the track in the y-axis direction, variance of the track in the y-axis direction and slope of the track, and the characteristic range comprises average speed characteristic range of the track in the x-axis direction, variance characteristic range of the track in the x-axis direction, average speed characteristic range of the track in the y-axis direction, variance characteristic range of the track in the y-axis direction and slope characteristic range of the track;
if the license plate is not satisfied, the license plate corresponding to the first license plate track is determined to be a fake license plate, and the fake license plate is obtained by forging and imitating the license plate which can pass through the gate.
2. The method of claim 1, wherein determining a first license plate trajectory from the license plate data comprises:
obtaining a license plate frame of each frame according to the license plate data;
judging whether license plate numbers corresponding to license plate frames of every two adjacent frames are the same or not;
if so, extracting a license plate frame of a previous frame in every two adjacent frames with the same license plate number;
And determining a first license plate track according to the extracted license plate frame.
3. The method according to claim 2, wherein after determining whether license plate numbers corresponding to license plate frames of each two adjacent frames are identical, before determining the first license plate track according to the extracted license plate frames, the method further comprises:
if not, judging whether the license plate numbers of every two adjacent frames with different license plate numbers have the condition of continuous four bits and more than the same bit number;
If the number of the license plate is four or more, extracting the license plate frame of the previous frame in every two adjacent frames with the same number of bits.
4. The method according to claim 3, wherein after judging whether four or more consecutive license plates in each adjacent two frames having different license plate numbers are identical, the method further comprises, before determining the first license plate track based on the extracted license plate frame:
If the number of the license plate does not meet the continuous four-bit and more than the same number of the adjacent two frames, calculating the intersection ratio;
judging whether the cross ratio is larger than a preset threshold value or not;
If the number is larger than the number, extracting the license plate frame of the previous frame in every two adjacent frames with the same number of continuous four digits and more digits not met by the license plate number.
5. The method for determining a fake license plate according to claim 1, wherein after the license plate track is a fake license plate track, the method further comprises:
And uploading the early warning information and the license plate data to a server.
6. The method according to claim 1, wherein before determining whether a preset number of the first track feature values are within the corresponding feature ranges, the method further comprises:
Acquiring training data;
Determining a second license plate track and a third license plate track according to the training data, wherein the second license plate track is a plurality of non-fake license plate tracks in the training data, and the third license plate track is a plurality of fake license plate tracks in the training data;
calculating according to the second license plate track to obtain a second track characteristic value, and calculating according to the third license plate track to obtain a third track characteristic value;
and screening according to the second track characteristic value and the third track characteristic value to obtain the characteristic range.
7. A fake license plate judgment device, characterized by comprising:
The acquisition unit is used for acquiring license plate data;
the determining unit is used for determining a first license plate track according to the license plate data;
The calculating unit is used for calculating according to the first vehicle license plate track to obtain a first track characteristic value;
The judging unit is used for judging whether the preset number of first track characteristic values are in a corresponding characteristic range or not, wherein the characteristic range is a characteristic value range of a non-fake license plate track obtained through training, the preset number is at least three, the first track characteristic values comprise average speed of the track in the x-axis direction, variance of the track in the x-axis direction, average speed of the track in the y-axis direction, variance of the track in the y-axis direction and slope of the track, and the characteristic range comprises average speed characteristic range of the track in the x-axis direction, variance characteristic range of the track in the x-axis direction, average speed characteristic range of the track in the y-axis direction, variance characteristic range of the track in the y-axis direction and slope characteristic range of the track;
the determining unit is further configured to determine, when the preset number of license plates corresponding to the first license plate track is not met, a fake license plate, where the fake license plate is a license plate obtained by forging and imitating a license plate that can pass through the channel gate.
8. A fake license plate judgment device, characterized by comprising:
a central processing unit, a memory and an input/output interface;
the memory is a short-term memory or a persistent memory;
The central processor is configured to communicate with the memory and to execute instruction operations in the memory to perform the method of any of claims 1 to 6.
9. A computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210437432.3A CN114743191B (en) | 2022-04-22 | 2022-04-22 | A method and related device for judging fake license plates based on license plate trajectory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210437432.3A CN114743191B (en) | 2022-04-22 | 2022-04-22 | A method and related device for judging fake license plates based on license plate trajectory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114743191A CN114743191A (en) | 2022-07-12 |
| CN114743191B true CN114743191B (en) | 2025-07-15 |
Family
ID=82283896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210437432.3A Active CN114743191B (en) | 2022-04-22 | 2022-04-22 | A method and related device for judging fake license plates based on license plate trajectory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114743191B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079751A (en) * | 2019-12-16 | 2020-04-28 | 深圳市芊熠智能硬件有限公司 | Method and device for identifying authenticity of license plate, computer equipment and storage medium |
| CN112997190A (en) * | 2020-12-29 | 2021-06-18 | 深圳市锐明技术股份有限公司 | License plate recognition method and device and electronic equipment |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8798325B2 (en) * | 2012-02-21 | 2014-08-05 | Xerox Corporation | Efficient and fault tolerant license plate matching method |
| CN106251635A (en) * | 2016-08-18 | 2016-12-21 | 武汉中科通达高新技术股份有限公司 | The recognition methods of a kind of deck suspicion license plate number and system |
| CN111881741B (en) * | 2020-06-22 | 2024-06-14 | 浙江大华技术股份有限公司 | License plate recognition method, license plate recognition device, computer equipment and computer readable storage medium |
| KR20220014525A (en) * | 2020-07-29 | 2022-02-07 | 케이원파킹 주식회사 | Method for providing parking management for parking lots with one way entrance |
| CN112861797A (en) * | 2021-03-12 | 2021-05-28 | 济南博观智能科技有限公司 | Method and device for identifying authenticity of license plate and related equipment |
| CN113128507B (en) * | 2021-05-12 | 2023-03-21 | 锐捷网络股份有限公司 | License plate recognition method and device, electronic equipment and storage medium |
| CN113808167B (en) * | 2021-09-17 | 2023-11-17 | 北京赛搏体育科技股份有限公司 | Volleyball motion trail extraction method based on video data |
-
2022
- 2022-04-22 CN CN202210437432.3A patent/CN114743191B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079751A (en) * | 2019-12-16 | 2020-04-28 | 深圳市芊熠智能硬件有限公司 | Method and device for identifying authenticity of license plate, computer equipment and storage medium |
| CN112997190A (en) * | 2020-12-29 | 2021-06-18 | 深圳市锐明技术股份有限公司 | License plate recognition method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114743191A (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038176B (en) | Method and device for establishing passerby library, electronic equipment and medium | |
| CN106600977B (en) | Multi-feature recognition-based illegal parking detection method and system | |
| CN110706247B (en) | Target tracking method, device and system | |
| CN102902955B (en) | Intelligent analysis method and system for vehicle behavior | |
| CN104392239B (en) | License plate recognition method and system | |
| CN103927508B (en) | Target vehicle tracking method and device | |
| CN201255897Y (en) | Human flow monitoring device for bus | |
| CN111753797B (en) | Vehicle speed measuring method based on video analysis | |
| CN108009473A (en) | Based on goal behavior attribute video structural processing method, system and storage device | |
| CN112257541A (en) | License plate recognition method, electronic device, and computer-readable storage medium | |
| CN112580531B (en) | Identification detection method and system for true and false license plates | |
| CN110517500A (en) | A kind of people's vehicle association process method and device | |
| CN112883866A (en) | Method, system and storage medium for detecting regional invasion in real time | |
| JP6681965B2 (en) | Apparatus and method for extracting learning target image for autonomous driving | |
| CN108830204B (en) | Anomaly detection method in target-oriented surveillance video | |
| CN114140762A (en) | Method for automatically identifying vehicle driving direction | |
| CN112597924B (en) | Electric bicycle track tracking method, camera device and server | |
| CN115762172A (en) | A method, device, equipment and medium for identifying vehicles entering and exiting parking spaces | |
| CN114743191B (en) | A method and related device for judging fake license plates based on license plate trajectory | |
| CN114863372A (en) | Parking management method, parking management device and computer-readable storage medium | |
| CN117437792B (en) | Real-time road traffic state monitoring method, device and system based on edge calculation | |
| CN114882074B (en) | Target motion state identification method, device, equipment and medium | |
| CN117115801A (en) | License plate authenticity identification method, device, equipment and storage medium | |
| KR100869139B1 (en) | Vehicle license plate recognition system using image input signal to portable terminal and its recognition method | |
| CN116310946A (en) | Intelligent traffic jam detection method and system based on multi-target tracking detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |