CN114283174A - Moving target tracking method and device and electronic equipment - Google Patents

Abstract

The present invention provides a moving target tracking method, device and electronic device. Wherein, the method is applied to a high-altitude parabolic detection system, and the method includes: acquiring an original image; preprocessing the original image to obtain an edge-enhanced image; wherein, the preprocessing includes down-sampling processing and filtering processing; The target tracking processing obtains the moving target in the edge-enhanced image; wherein, the target tracking processing includes inter-frame difference processing and KLT feature point tracking processing. Through the filtering process, the integrity of the parabola can be guaranteed as much as possible and the influence of the background can be reduced. Through the inter-frame difference processing, it can effectively detect whether the falling object is deformed or disintegrated according to the adjacent frame images. Continue to track and detect accurately, thereby improving the detection accuracy of fluid parabola in the process of high-altitude parabola, so that the high-altitude parabola detection system can work effectively and accurately.

Description

Moving target tracking method, device and electronic device

technical field

The present invention relates to the technical field of image processing, and in particular, to a moving target tracking method, device and electronic device.

Background technique

With the acceleration of the urbanization process, high-rise buildings are rising from the ground, and the problem of high-altitude parabola is very serious. As an urban uncivilized behavior, the high-altitude parabola also brings great social harm. Since most of the uncivilized behaviors of high-altitude parabolic behavior are carried out on high-altitude floors, the descending speed of the parabola is extremely fast, and the time of the parabola is extremely short. High-altitude parabolic monitoring and early warning system.

At present, most of the existing high-altitude parabolic monitoring and early warning systems use image capture technology based on video surveillance to identify the location and time of high-altitude parabolas by installing cameras on the roof of high-rise buildings or around buildings. However, the above-mentioned high-altitude parabolic monitoring and early warning systems The main tracked object is a rigid body, and the object actually thrown may not be a rigid body. The process of free fall will also be accompanied by motion deformation, disintegration, decomposition, etc. The landing of these parabolas will be accompanied by irregular surface deformation, which will affect the detection of the parabolic detection system.

SUMMARY OF THE INVENTION

In view of this, the purpose of the present invention is to provide a moving target tracking method, device and electronic device, so as to improve the detection accuracy of fluid parabola in the process of high-altitude parabola.

In a first aspect, an embodiment of the present invention provides a moving target tracking method, which is applied to a high-altitude parabolic detection system. The method includes: acquiring an original image; preprocessing the original image to obtain an edge-enhanced image; wherein the preprocessing includes reducing Sampling processing and filtering processing; target tracking processing is performed on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein, the target tracking processing includes inter-frame difference processing and KLT feature point tracking processing.

In a preferred embodiment of the present invention, the above-mentioned steps of preprocessing the original image to obtain an edge-enhanced image include: performing down-sampling processing on the original image to reduce the sampling rate of the original image to the target sampling rate; down-sampling The processed original image is filtered to obtain an edge-enhanced image.

In a preferred embodiment of the present invention, the above-mentioned steps of performing filtering processing on the original image after downsampling processing to obtain an edge-enhanced image include: sequentially passing the preset Lee filter, Kuwahara filter and Gaussian filter to The original image after the down-sampling process is filtered to obtain an edge-enhanced image.

In a preferred embodiment of the present invention, the template of the above-mentioned Lee filter is 15×15, the noise variance of the Lee filter is 155; the template of the above-mentioned Kuwahara filter is 13×13; the above-mentioned Gaussian filter is a zero mean filter .

In a preferred embodiment of the present invention, after the above-mentioned steps of filtering the original image after downsampling processing through the preset Lee filter, Kuwahara filter and Gaussian filter to obtain the edge-enhanced image, the method also further Including: collecting the edge information of the edge-enhanced image through the preset Canny edge detection operator.

In a preferred embodiment of the present invention, the above-mentioned steps of performing target tracking processing on the edge-enhanced image to obtain the moving object in the edge-enhanced image include: determining the original frame image of the edge-enhanced image; Inter-frame difference processing detects the feature points of moving objects; KLT feature point tracking processing is performed on the feature points of moving objects to obtain moving objects in edge-enhanced images.

In a preferred embodiment of the present invention, the above-mentioned step of performing inter-frame difference processing on the original frame image to obtain the feature points of the moving target includes: calculating the pixel points of the corresponding positions of adjacent frame images in the original frame image. The absolute value of the difference between the grayscale values; the pixel points whose absolute value is greater than the preset threshold are used as the feature points of the moving target.

In a preferred embodiment of the present invention, after the above-mentioned step of performing KLT feature point tracking processing on the feature points of the moving target to obtain the moving target in the edge-enhanced image, the method further includes: constructing adjacent edges in the edge-enhanced image. Transforming affine model of frame images; determining feature point positions of moving objects in each frame image of the edge-enhanced image based on the transforming affine model; determining moving regions of moving objects based on the feature point positions of moving objects.

In a second aspect, an embodiment of the present invention further provides a moving target tracking device, which is applied to a high-altitude parabolic detection system. The device includes: an image acquisition module for acquiring an original image; a preprocessing module for preprocessing the original image, obtaining an edge-enhanced image; wherein, the preprocessing includes down-sampling processing and filtering processing; a tracking detection module is used to perform target tracking processing on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein, the target tracking processing includes Inter-frame difference processing and KLT feature point tracking processing.

In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor and a memory, the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the above-mentioned moving target tracking method A step of.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are invoked and executed by the processor, the computer-executable instructions cause the processor to Implement the steps of the above-mentioned moving target tracking method.

The embodiments of the present invention have brought the following beneficial effects:

A moving target tracking method, device, and electronic device provided by the embodiments of the present invention can preprocess an original image through downsampling processing and filtering processing to obtain an edge-enhanced image; through frame difference processing and KLT feature point tracking processing The object tracking process is performed on the edge-enhanced image to obtain the moving object in the edge-enhanced image. In this method, the integrity of the parabola can be ensured as much as possible and the influence of the background can be reduced as much as possible through the filtering process, and whether the falling object is deformed or disintegrated can be effectively detected according to the adjacent frame images through the inter-frame difference processing. The disintegrated target can continue to be accurately tracked and detected, thereby improving the detection accuracy of the fluid parabola in the process of high-altitude parabola, so that the high-altitude parabola detection system can work effectively and accurately.

Additional features and advantages of the present disclosure will be set forth in the description that follows, or some may be inferred or unambiguously determined from the description, or may be learned by practicing the above-described techniques of the present disclosure.

In order to make the above-mentioned objects, features and advantages of the present disclosure more obvious and easy to understand, the preferred embodiments are exemplified below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

1 is a schematic diagram of a high-altitude parabolic detection system according to an embodiment of the present invention;

2 is a flowchart of a method for tracking a moving target according to an embodiment of the present invention;

3 is a flowchart of another moving target tracking method provided by an embodiment of the present invention;

4 is a schematic diagram of a method for preprocessing an original image according to an embodiment of the present invention;

5 is a schematic diagram of a method for performing target tracking processing on an edge-enhanced image according to an embodiment of the present invention;

6 is a schematic diagram of a method for inter-frame difference processing provided by an embodiment of the present invention;

7 is a schematic structural diagram of a moving target tracking device according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. example. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

At present, with the acceleration of urbanization, high-rise buildings are rising, and the problem of high-altitude parabola is very serious. As an urban uncivilized behavior, the high-altitude parabola also brings great social harm. Since most of the uncivilized behaviors of high-altitude parabolic behavior are carried out on high-altitude floors, the descending speed of the parabola is extremely fast, and the time of the parabola is extremely short. High-altitude parabolic monitoring and early warning system.

Most of the existing high-altitude parabolic monitoring and early warning systems use video surveillance-based image capture technology to identify the location and time of high-altitude parabolas by installing cameras on the roof of high-rise buildings or around buildings. This technology is monitored by the camera angle and building height. Restrictions, as well as the influence of weather and environmental factors such as rain, fog and light, in the case of adverse environmental factors, it is impossible to quickly and accurately lock the specific location of the high-altitude parabola.

The estimation of the state of a moving target under complex environmental conditions is an important difficulty in accurate target tracking and an important difficulty in effectively detecting high-altitude paraboloids.

In many existing studies, the main tracked object is a rigid body, and the object actually thrown may not be a rigid body. The process of free fall will also be accompanied by motion deformation, disintegration, decomposition, etc., such as throwing objects in garbage bags. Fruit peels, construction waste packed in foam bags, etc. The landing of these parabolas will be accompanied by irregular deformation of the appearance, which will affect the detection of the parabola detection system.

Based on this, the embodiments of the present invention provide a method, device and electronic device for tracking a moving target, in particular to a parabola detection algorithm, which can improve the detection accuracy of fluid parabola in the process of high-altitude parabola.

In order to facilitate the understanding of this embodiment, a moving target tracking method disclosed in the embodiment of the present invention is first introduced in detail.

This embodiment provides a moving target tracking method, and the moving target tracking method is applied to a high-altitude parabolic detection system. Referring to the schematic diagram of a high-altitude parabolic detection system shown in Figure 1, the high-altitude parabolic detection system is generally composed of a data acquisition module, a moving target detection module, a moving target tracking module, a parabolic judgment module and a result display alarm module. .

Among them, the data acquisition module is mainly used to obtain video frame sequence, video stream decoding and so on. The moving eye detection module is mainly used for video image preprocessing, moving target detection, target feature extraction, etc., to obtain parabolic feature information in video images. The moving target tracking module is mainly used for motion trajectory acquisition, specifically, motion trajectory prediction, tracking module update, motion trajectory matching, etc., to obtain the parabolic motion trajectory in the video image. The parabolic judgment module is used for parabolic judgment. The result display alarm module is used for high-altitude parabolic behavior alarm, high-altitude parabolic result display, high-altitude parabolic video storage, etc., and the processing is made according to the judgment result. If it is judged to be high-altitude parabolic behavior, the parabolic video will be saved, and the alarm will be reminded in time for later accountability. Use; if it is judged to be something else, it will not be dealt with.

For the high-altitude parabola detection system, the moving target tracking process and feedback the relevant features of the target, such as the position, speed, shape, texture, etc., to realize the recognition and prediction of the real-time position and movement path of the moving target in the video image sequence. It is an important part of the high-altitude parabolic detection system. The moving target tracking algorithm generally includes three parts: target feature extraction, similarity metric calculation and target position matching.

In many existing studies, the main tracked object is a rigid body, and the object actually thrown may not be a rigid body. The process of free fall will also be accompanied by motion deformation, disintegration, decomposition, etc., such as throwing objects in garbage bags. Fruit peels, construction waste packed in foam bags, etc. The landing of these parabolas will be accompanied by irregular deformation of the appearance, which will affect the detection of the parabola detection system.

Based on the above description, referring to the flowchart of a method for tracking a moving target shown in FIG. 2 , the method for tracking a moving target includes the following steps:

Step S200, acquiring the original image.

The original pattern in this embodiment of the present invention may be a video frame sequence or a decoded video stream, including multiple video frames or image frames.

Step S202 , preprocessing the original image to obtain an edge-enhanced image; wherein, the preprocessing includes downsampling processing and filtering processing.

The high-altitude parabolic detection system in the embodiment of the present invention may include a preprocessing module and a tracking detection module, wherein the preprocessing module is used to preprocess the original image, and the tracking detection module is used to perform target tracking processing on the edge-enhanced image.

Specifically, the sampling process refers to reducing the sampling rate of each image frame of the original image, for example, the sampling rate of each image frame of the original image may be reduced to 800×800. The preprocessing module in the embodiment of the present invention may include a plurality of filters, and the edge enhancement processing of the sampled image is performed through the filters to obtain an edge enhanced image, and edge information of the edge enhanced image may also be collected.

Step S204, performing target tracking processing on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein, the target tracking processing includes inter-frame difference processing and KLT feature point tracking processing.

In the embodiment of the present invention, the tracking effect of the fluid can be improved by means of difference processing between frames. Among them, inter-frame difference processing is a method to obtain the outline of moving objects by performing difference operations on two adjacent frames in a video image sequence, which can be well applied to the situation where there are multiple moving objects and cameras moving. When there is abnormal object motion in the monitoring scene, there will be a more obvious difference between the frames. Subtract the two frames to obtain the absolute value of the brightness difference between the two frames, and determine whether it is greater than the threshold to analyze the motion of the video or image sequence. feature to determine whether there is object motion in the image sequence. The frame-by-frame difference of the image sequence is equivalent to performing high-pass filtering on the image sequence in the time domain.

KLT (Kanade Lucas Tomasi) feature point tracking processing is an optical flow tracking method. It can first establish a fixed-size window in the two frames of images before and after, and then find the displacement that minimizes the sum of the squares of the pixel intensity differences between the two windows. , the movement of pixels in the window is approximated as such a displacement vector, so as to perform target tracking.

In a moving target tracking method provided by an embodiment of the present invention, an original image can be preprocessed through downsampling processing and filtering processing to obtain an edge-enhanced image; an edge-enhanced image can be obtained through inter-frame difference processing and KLT feature point tracking processing. The target tracking process is performed to obtain the moving target in the edge-enhanced image. In this method, the integrity of the parabola can be ensured as much as possible and the influence of the background can be reduced as much as possible through the filtering process, and whether the falling object is deformed or disintegrated can be effectively detected according to the adjacent frame images through the inter-frame difference processing. The disintegrated target can continue to be accurately tracked and detected, thereby improving the detection accuracy of the fluid parabola in the process of high-altitude parabola, so that the high-altitude parabola detection system can work effectively and accurately.

This embodiment provides another moving target tracking method, which is implemented on the basis of the foregoing embodiment; this embodiment focuses on describing the specific implementation of preprocessing. Referring to the flowchart of another moving target tracking method shown in FIG. 3 , the moving target tracking method in this embodiment includes the following steps:

Step S300, acquiring the original image.

Step S302, performing down-sampling processing on the original image to reduce the sampling rate of the original image to the target sampling rate.

Referring to the schematic diagram of a method for preprocessing the original image shown in FIG. 4 , the preprocessing may first downsample the original image to the target sampling rate of each frame of image, for example: 600pixel×1000pixel.

Step S304 , filtering the original image after the down-sampling process to obtain an edge-enhanced image.

Specifically, the original image after the down-sampling process can be filtered through the following steps: the original image after the down-sampling process is filtered through the preset Lee filter, the Kuwahara filter and the Gaussian filter in turn to obtain the edge Enhanced image.

As shown in Figure 4, two stages of preprocessing can be performed on the original image after downsampling: edge enhancement and edge detection. Among them, the Lee filter with a template of 15×15 and a noise variance of 155 can be used for filtering first, then the Kuwahara filter with a template of 13×13 can be used for filtering, and finally a Gaussian filter with zero mean value can be used for filtering. processing to obtain an edge-enhanced image.

Among them, the Lee filter is an image denoising filter with good denoising effect. The Lee filter can effectively remove image noise by combining various wavelets. Lee filtering is one of the typical methods for image speckle filtering using the local statistical properties of images. It is based on a fully developed speckle noise model and selects a window of a certain length as a local area. It is assumed that the prior mean and variance can be calculated by calculating the local mean and variance is obtained.

The basic principle of the Kuwahara filter is to calculate the mean and variance in the neighborhood of the image template, and select the mean value of the area with relatively uniform gray value of the image to replace the gray value of the central pixel of the template, so as to achieve the filtering effect.

Gaussian filtering is a linear smoothing filter, suitable for removing Gaussian noise, and is widely used in the noise reduction process of image processing. Gaussian filtering is a process of weighted averaging of the entire image. The value of each pixel is obtained by weighted averaging of itself and other pixel values in its neighborhood. The specific operation of Gaussian filtering is: use a template (or convolution, mask) to scan each pixel in the image, and replace the value of the center pixel of the template with the weighted average gray value of the pixels in the neighborhood determined by the template.

In addition, as shown in FIG. 4 , in this embodiment, the Canny edge detection operator may also be used to detect the edge information of the edge-enhanced image. For example, the edge information of the edge-enhanced image is collected through a preset Canny edge detection operator.

Among them, the Canny edge detection operator can first use a Gaussian filter to smooth the image and filter out noise. Then calculate the gradient strength and direction of each pixel in the image, apply Non-Maximum Suppression to eliminate spurious responses caused by edge detection, and apply Double-Threshold detection to determine the real and potential edges. Finally, the edge detection is finally completed by suppressing the isolated weak edge, and the edge information of the image is collected.

In this method, the preprocessing including filtering processing can ensure the integrity of the parabola and reduce the influence of the background as much as possible, and the preprocessing effect is good. An input image with obvious features and small errors.

Step S306 , perform target tracking processing on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein, the target tracking processing includes inter-frame difference processing and KLT feature point tracking processing.

Specifically, in this embodiment of the present invention, frame-to-frame difference processing and KLT feature point tracking processing can be implemented through the following steps: determining the original frame image of the edge-enhanced image; performing frame-to-frame difference processing on the original frame image to detect the characteristics of the moving target point; KLT feature point tracking processing is performed on the feature points of the moving target to obtain the moving target in the edge-enhanced image.

Referring to the schematic diagram of a method of performing target tracking processing on edge-enhanced images shown in FIG. 5, for the original frame images obtained through preprocessing, the detection feature points of the parabolic target can be obtained first through the inter-frame difference method, for example: calculating The absolute value of the difference between the grayscale values of each pixel point at the corresponding position of the adjacent frame image in the original frame image; the pixel point whose absolute value is greater than the preset threshold is used as the feature point of the moving target.

Referring to the schematic diagram of an inter-frame difference processing method shown in FIG. 6, first determine the current frame and the previous frame of the current frame as adjacent frame images, and determine the gray level of each pixel at the corresponding position of the current frame and the previous frame. For each pixel, calculate the difference between the gray value of the current frame and the previous frame, and then take the absolute value, and perform image binarization based on the absolute value, that is, pixels whose absolute value is greater than the preset threshold are used as motion. feature points of the target.

For example, for the coordinates (200, 300), the gray value of the pixel at the coordinates (200, 300) of the current frame is 200, and the gray value of the pixel at the coordinates (200, 300) of the previous frame is 100. , the absolute value of the difference between the above two grayscale values is |100-200|=100. If the preset threshold is 80, since the absolute value of 100 is greater than the preset threshold of 80, the pixel at the coordinates (200, 300) can be used as Feature points of moving targets.

For another example, for the coordinates (100, 200), the gray value of the pixel at the coordinates (100, 200) of the current frame is 120, and the gray value of the pixel at the coordinates (100, 200) of the previous frame is 160. The absolute value of the difference between the above two grayscale values is |120-160|=40. If the preset threshold is 80, since the absolute value of 40 is less than the preset threshold of 80, the pixel at the coordinates (100, 200) cannot be used as Feature points of moving targets.

In this method, since the object in the scene is moving, the position of the image of the object in different image frames is different. The difference operation is performed on the images of two consecutive frames, the pixels corresponding to different frames are subtracted, and the absolute value of the grayscale difference is judged. When the absolute value exceeds a certain threshold, it can be judged as a moving target.

As shown in Fig. 5, after the inter-frame difference processing, the KLT algorithm can be used for feature point tracking. KLT algorithm is a target tracking algorithm based on feature points, which is a kind of optical flow method. The KLT algorithm has three assumptions: the brightness is constant, and it is guaranteed not to be affected by the brightness; the time is continuous or the movement displacement is small, which can ensure that the KLT algorithm can find the point; the spatial consistency, the adjacent points have similar motions, remain adjacent, and can be in the same Within a window, all points are offset by the same amount. The main steps of the KLT algorithm can be:

(1) Detect Harris corners in the first frame; (2) Perform motion estimation for each corner by translation or affine between consecutive frames; (3) Connect the motion vectors in consecutive frames to obtain the motion of each corner (4) For each feature point, judge the quality of its tracking in each frame. Some features can be removed (such as those that are occluded or cannot be tracked accurately), and some new features can be added periodically (such as every 5 frames); (5) Use steps (1)-(3) to track new features and old corners.

After the KLT feature point tracking process is performed on the feature points of the moving target, the position of the feature points and the moving area of the moving target can also be determined, for example: constructing a transformation affine model of the adjacent frame images in the edge-enhanced image; based on The transformation affine model determines the position of the feature point of the moving object in each frame image of the edge-enhanced image; and determines the moving area of the moving object based on the position of the feature point of the moving object.

As shown in Figure 5, first, the feature points of the tracking target can be obtained by the inter-frame difference method, and then the KLT algorithm can be used to track the feature points. Finally, the Ransac algorithm can be used to construct the transformation affine model between adjacent frame images, and the estimated image The feature point position and parabolic area (that is, the motion area of the moving target). Calculate the displacement information of the tracked marker, the change of the flip angle and other related parameters, and finally loop the calculation until the end of the last frame. The motion trajectory of the parabola is obtained through the above process, which can facilitate the subsequent judgment and use of the high-altitude parabolic system.

Because as the parabola falls, the moving target will be accompanied by irregular deformation of the appearance. If the feature point detection with a long delay is used, the features of decomposing small objects will be missed. The inter-frame difference processing adopted in this method can ensure that the features of the decomposed small objects are not missed according to the small changes between the current frame and the previous frame.

The above method provided by the embodiment of the present invention can ensure the integrity of the parabola as much as possible and reduce the influence of the background through filtering processing, and can effectively detect whether the falling object is deformed or not according to the adjacent frame images through the inter-frame difference processing. Disintegration, can continue to accurately track and detect the deformed or disintegrated target, thereby improving the detection accuracy of fluid parabola in the process of high-altitude parabola, so that the high-altitude parabola detection system can work effectively and accurately.

Corresponding to the above method embodiments, an embodiment of the present invention provides a moving target tracking device, which is applied to a high-altitude parabola detection system; referring to a schematic structural diagram of a moving target tracking device shown in FIG. 7 , the moving target tracking device includes:

an image acquisition module 71, for acquiring an original image;

The preprocessing module 72 is used for preprocessing the original image to obtain the edge-enhanced image; wherein, the preprocessing includes downsampling processing and filtering processing;

The tracking detection module 73 is configured to perform target tracking processing on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein, the target tracking processing includes inter-frame difference processing and KLT feature point tracking processing.

A moving target tracking device provided by an embodiment of the present invention can preprocess an original image through downsampling processing and filtering processing to obtain an edge-enhanced image; and an edge-enhanced image can be processed through frame difference processing and KLT feature point tracking processing The target tracking process is performed to obtain the moving target in the edge-enhanced image. In this method, the integrity of the parabola can be ensured as much as possible and the influence of the background can be reduced as much as possible through the filtering process, and whether the falling object is deformed or disintegrated can be effectively detected according to the adjacent frame images through the inter-frame difference processing. The disintegrated target can continue to be accurately tracked and detected, thereby improving the detection accuracy of the fluid parabola in the process of high-altitude parabola, so that the high-altitude parabola detection system can work effectively and accurately.

The above-mentioned preprocessing module is used for down-sampling the original image, reducing the sampling rate of the original image to the target sampling rate; filtering the original image after the down-sampling processing to obtain an edge-enhanced image.

The above-mentioned preprocessing module is used to perform filtering processing on the original image after down-sampling processing through the preset Lee filter, Kuwahara filter and Gaussian filter in sequence to obtain an edge-enhanced image.

The template of the above-mentioned Lee filter is 15×15, and the noise variance of the Lee filter is 155; the template of the above-mentioned Kuwahara filter is 13×13; the above-mentioned Gaussian filter is a zero-mean filter.

The above-mentioned preprocessing module is further configured to collect edge information of the edge-enhanced image through a preset Canny edge detection operator.

The above tracking detection module is used to determine the original frame image of the edge-enhanced image; perform inter-frame difference processing on the original frame image to detect the feature points of the moving target; perform KLT feature point tracking processing on the feature points of the moving target to obtain edge enhancement moving objects in the image.

The above-mentioned tracking detection module is used to calculate the absolute value of the difference between the grayscale values of each pixel point at the corresponding position of the adjacent frame image in the original frame image; the pixel point whose absolute value is greater than the preset threshold is used as the feature point of the moving target .

The above-mentioned tracking detection module is also used to construct a transformation affine model of adjacent frame images in the edge-enhanced image; determine the feature point position of the moving target in each frame image of the edge-enhanced image based on the transformation affine model; The position of the feature point of the target determines the moving area of the moving target.

The implementation principle and technical effects of the moving target tracking device provided by the embodiments of the present invention are the same as the aforementioned embodiments of the moving target tracking method. For a brief description, for the parts not mentioned in the embodiments of the moving target tracking device, reference may be made to the aforementioned embodiments. Corresponding content in the embodiment of the moving target tracking method.

An embodiment of the present invention also provides an electronic device for running the above-mentioned moving target tracking method; refer to a schematic structural diagram of an electronic device shown in FIG. 8 , the electronic device includes a memory 100 and a processor 101 , wherein the memory 100 For storing one or more computer instructions, the one or more computer instructions are executed by the processor 101 to implement the above-mentioned moving target tracking method.

Further, the electronic device shown in FIG. 8 further includes a bus 102 and a communication interface 103 , and the processor 101 , the communication interface 103 and the memory 100 are connected through the bus 102 .

The memory 100 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the network element of the system and at least one other network element is implemented through at least one communication interface 103 (which may be wired or wireless), which may use the Internet, a wide area network, a local network, a metropolitan area network, and the like. The bus 102 may be an ISA bus, a PCI bus, an EISA bus, or the like. The bus can be divided into address bus, data bus, control bus and so on. For ease of presentation, only one bidirectional arrow is used in FIG. 8, but it does not mean that there is only one bus or one type of bus.

The processor 101 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above-mentioned method may be completed by an integrated logic circuit of hardware in the processor 101 or an instruction in the form of software. The above-mentioned processor 101 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (Digital Signal Processor, DSP for short) , Application Specific Integrated Circuit (ASIC for short), Field-Programmable Gate Array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. Various methods, steps, and logical block diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art. The storage medium is located in the memory 100, and the processor 101 reads the information in the memory 100, and completes the steps of the methods in the foregoing embodiments in combination with its hardware.

Embodiments of the present invention further provide a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to realize For the specific implementation of the above-mentioned moving target tracking method, reference may be made to the method embodiments, which will not be repeated here.

The moving target tracking method, device, and computer program product of the electronic device provided by the embodiments of the present invention include a computer-readable storage medium storing program codes, and the instructions included in the program codes can be used to execute the methods in the foregoing method embodiments. For implementation, reference may be made to the method embodiments, which will not be repeated here.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the system and/or device described above, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrally connected; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or the internal communication between the two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific situations.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. The indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation or a specific orientation. construction and operation, and therefore should not be construed as limiting the invention. Furthermore, the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed to indicate or imply relative importance.

Finally, it should be noted that the above-mentioned embodiments are only specific implementations of the present invention, and are used to illustrate the technical solutions of the present invention, but not to limit them. The protection scope of the present invention is not limited thereto, although referring to the foregoing The embodiment has been described in detail the present invention, and those of ordinary skill in the art should understand that: any person skilled in the art is within the technical scope disclosed by the present invention, and he can still modify the technical solutions described in the foregoing embodiments. Or can easily think of changes, or equivalently replace some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be covered in the present invention. within the scope of protection. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (11)

1. A moving target tracking method is applied to a high-altitude parabolic detection system, and comprises the following steps:

acquiring an original image;

preprocessing the original image to obtain an edge-enhanced image; wherein the preprocessing comprises down-sampling processing and filtering processing;

performing target tracking processing on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein the target tracking processing comprises interframe difference processing and KLT characteristic point tracking processing.

2. The method of claim 1, wherein the step of preprocessing the original image to obtain an edge-enhanced image comprises:

carrying out down-sampling processing on the original image, and reducing the sampling rate of the original image to be a target sampling rate;

and filtering the original image after the down-sampling processing to obtain an edge-enhanced image.

3. The method according to claim 2, wherein the step of filtering the original image after the down-sampling process to obtain an edge-enhanced image comprises:

and filtering the original image after the down-sampling treatment by a preset Lee filter, a Kuwahara filter and a Gaussian filter in sequence to obtain an edge-enhanced image.

4. The method of claim 3, wherein the template of the Lee filter is 15 x 15, and the noise variance of the Lee filter is 155; the template of the Kuwahara filter is 13 multiplied by 13; the gaussian filter is a zero-mean filter.

5. The method according to claim 3, wherein after the step of filtering the original image after the down-sampling process by a preset Lee filter, a Kuwahara filter and a Gaussian filter in order to obtain the edge-enhanced image, the method further comprises:

and acquiring the edge information of the edge-enhanced image through a preset Canny edge detection operator.

6. The method according to claim 1, wherein the step of performing the target tracking process on the edge-enhanced image to obtain the moving target in the edge-enhanced image comprises:

determining an original frame image of the edge-enhanced image;

performing interframe difference processing on the original frame image, and detecting feature points of a moving target;

and carrying out KLT characteristic point tracking processing on the characteristic points of the moving target to obtain the moving target in the edge enhanced image.

7. The method of claim 6, wherein the step of performing inter-frame difference processing on the original frame image to obtain the feature points of the moving object comprises:

calculating the absolute value of the difference of the gray values of all pixel points at the corresponding positions of the adjacent frame images in the original frame images;

and taking the pixel points with the absolute values larger than a preset threshold value as the characteristic points of the moving target.

8. The method according to claim 6, wherein after the KLT feature point tracking processing is performed on the feature points of the moving object to obtain the moving object in the edge-enhanced image, the method further comprises:

constructing a transformed affine model of adjacent frame images in the edge-enhanced image;

determining feature point positions of a moving object in each frame image of the edge-enhanced image based on the transformed affine model;

determining a motion region of the moving object based on the feature point position of the moving object.

9. A moving object tracking device, applied to a high altitude parabolic detection system, the device comprising:

the image acquisition module is used for acquiring an original image;

the preprocessing module is used for preprocessing the original image to obtain an edge-enhanced image; wherein the preprocessing comprises down-sampling processing and filtering processing;

the tracking detection module is used for carrying out target tracking processing on the edge-enhanced image to obtain a moving target in the edge-enhanced image; wherein the target tracking processing comprises interframe difference processing and KLT characteristic point tracking processing.

10. An electronic device comprising a processor and a memory, said memory storing computer-executable instructions executable by said processor, said processor executing said computer-executable instructions to perform the steps of the moving object tracking method of any one of claims 1-8.

11. A computer-readable storage medium having stored thereon computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the steps of the moving object tracking method of any of claims 1-8.

Images