A video image acquisition jitter processing method and system

Abstract

The present invention discloses a video image acquisition jitter processing method and system, which relates to the field of intelligent parking management, including: selecting an interested ROI region from a monitoring video image, and determining a preset number of corner points and the coordinate value of each corner point from the ROI region; selecting a de-jitter reference corner point from the preset number of corner points according to the coordinates of the corner points and the coordinates of the edge points in the preset direction in the image; determining the jitter translation amount according to the difference between the coordinate value of the de-jitter reference corner point in the first frame image and the coordinate value of the de-jitter reference corner point in any other frame image; and de-jittering the vehicle target position according to the jitter offset. Since only a small part of the interested ROI region is selected from the entire image as the original image for de-jittering, it is not necessary to perform calculation processing on the entire image, which can improve the efficiency of image de-jittering, reduce processing time, and realize real-time de-jittering of the video vehicle position in the radar video data fusion algorithm.

Description

Technical Field

[0001] The present invention relates to the field of intelligent parking management, and in particular to a video image acquisition jitter processing method and system. Background Art

[0002] During the image acquisition process, the camera may shake due to the influence of factors such as the surrounding environment and weather, which may lead to errors in image acquisition. Therefore, the concept of video de-shaking is derived. Video de-shaking refers to the use of relevant algorithms to process the original video sequence captured by the video device to remove the shake. The purpose of video stabilization is, on the one hand, to make the human eye feel comfortable and facilitate manual observation and discrimination, and on the other hand, it also serves as a preprocessing stage for many other subsequent processes, such as detection, tracking and compression.

[0003] At present, when performing video de-shaking, affine transformation is usually used to de-shake the image. Affine transformation is an image position conversion achieved by linear transformation between two-dimensional coordinates to two-dimensional coordinates. However, when performing video de-shaking by affine transformation, the entire image needs to be calculated and processed, resulting in a large amount of calculation required in the existing de-shaking process. In addition, since multiple image frames need to be smoothed, the real-time performance of video image de-shaking cannot be guaranteed. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a video image acquisition jitter processing method and system, which can solve the problems of large processing computational complexity and inability to perform real-time jitter removal in existing video jitter removal methods.

[0005] To achieve the above object, on the one hand, the present invention provides a video image acquisition jitter processing method, the method comprising:

[0006] Selecting an ROI region of interest from the surveillance video image, and determining a preset number of corner points and coordinate values ​​of each corner point from the ROI region;

[0007] Selecting a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image;

[0008] Determine the jitter translation amount according to the difference between the coordinate value of the jitter removal reference corner point in the first frame image and the coordinate value of the jitter removal reference corner point in any other frame image;

[0009] According to the jitter offset, a de-jittering process is performed on the vehicle target position in the video frame image corresponding to the jitter offset.

[0010] Furthermore, the step of selecting a region of interest (ROI) from the surveillance video image includes:

[0011] An image containing a background area and a region containing clear corner points is selected from the surveillance video image as the ROI region.

[0012] Furthermore, the step of determining a preset number of corner points and the coordinate value of each corner point from the ROI area includes:

[0013] Obtaining the Harris corner point response function value corresponding to each corner point in the ROI area;

[0014] According to the Harris corner point response function value corresponding to each corner point, a preset number of corner points and the coordinates corresponding to the corner points are selected from all the corner points.

[0015] Furthermore, the step of selecting a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image comprises:

[0016] Acquire the distance between each of the preset number of corner points and the edge point in the preset direction according to the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image;

[0017] A corner point having the smallest distance from an edge point in the preset direction is selected from the preset number of corner points as the de-jittering reference corner point.

[0018] Further, the step of performing de-jitter processing on the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset includes:

[0019] Determining whether the jitter offset is within a preset offset range;

[0020] If yes, de-jittering the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset;

[0021] If not, de-jitter processing is performed on the vehicle target position in the current video frame image according to the jitter offset corresponding to the adjacent frame image.

[0022] On the other hand, the present invention provides a video image acquisition jitter processing system, the system comprising: a selection unit, for selecting an interested ROI region from a surveillance video image, and determining a preset number of corner points and coordinate values ​​of each corner point from the ROI region;

[0023] The selection unit is further configured to select a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image;

[0024] A determination unit, configured to determine a jitter translation amount according to a difference between a coordinate value of the jitter removal reference corner point in the first frame image and a coordinate value of the jitter removal reference corner point in any other frame image;

[0025] The de-jitter unit is used to perform de-jitter processing on the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset.

[0026] Furthermore, the selection unit is specifically used to select an image containing a background area and a region containing clear corner points from the surveillance video image as the ROI region.

[0027] Furthermore, the determination unit is specifically configured to obtain a Harris corner point response function value corresponding to each corner point in the ROI area; and select a preset number of corner points and coordinates corresponding to the corner points from all corner points according to the Harris corner point response function value corresponding to each corner point.

[0028] Furthermore, the selection unit is specifically used to obtain the distance between each corner point of a preset number of corner points and the edge point in the preset direction based on the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image; and select the corner point with the smallest distance to the edge point in the preset direction from the preset number of corner points as the de-jittering reference corner point.

[0029] Furthermore, the de-jitter unit is specifically used to determine whether the jitter offset is within a preset offset range; if so, de-jittering the vehicle target position in the video frame image corresponding to the jitter offset is performed according to the jitter offset; if not, de-jittering the vehicle target position in the current video frame image is performed according to the jitter offset corresponding to the adjacent frame image.

[0030] The present invention provides a video image acquisition jitter processing method and system, firstly, selects an ROI region of interest from a surveillance video image, calculates the jitter translation amount based on the coordinates of the corner points in the selected ROI region of interest, and completes the image de-jittering process based on the jitter translation amount. Since only a small part of the ROI region of interest is selected from the entire image as the original image for de-jittering, it is not necessary to perform calculation processing on the entire image, which can improve the efficiency of image de-jittering, reduce processing time, and realize real-time image de-jittering. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1It is a flow chart of a video image acquisition jitter processing method provided by the present invention;

[0032] Figure 2 It is a structural schematic diagram of a video image acquisition jitter processing system provided by the present invention;

[0033] Figure 3 It is a schematic diagram of the ROI area provided by the present invention;

[0034] Figure 4 This is a schematic diagram of corner point detection provided by the present invention. DETAILED DESCRIPTION

[0035] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.

[0036] like Figure 1 As shown, a video image acquisition jitter processing method provided by an embodiment of the present invention includes the following steps:

[0037] 101. Select an interested ROI region from a surveillance video image, and determine a preset number of corner points and coordinate values ​​of each corner point from the ROI region.

[0038] The preset number may be 2, 3, 4, etc., and the embodiment of the present invention does not limit this. Because the street lamp where the camera is located where the jitter occurs is a small local jitter in a plane, the embodiment of the present invention selects a small area to detect the jitter translation amount, which can avoid a large amount of calculations for the entire image and the matching of a large number of corner points. The moving target in the foreground area is prone to occlusion, so the ROI area of ​​interest is selected from the background area and contains clearer corner points. For example, a background area image with high contrast between the foreground and background, acute angles of the corner points, and a single pixel value of the background can be selected as the ROI area of ​​interest.

[0039] For the embodiment of the present invention, step 101 may specifically include: selecting an image containing a background area and a region containing clear corner points from a surveillance video image as the ROI region; obtaining a Harris corner point response function value corresponding to each corner point from the ROI region; and selecting a preset number of corner points and the coordinates corresponding to the corner points from all corner points according to the Harris corner point response function value corresponding to each corner point.

[0040] The following is a detailed description of the Harris corner point response function value corresponding to each corner point and the process of obtaining the coordinates of the corner point, including:

[0041] 1) Input the ROI area of ​​the corner point to be detected. If the ROI area is a color image, it is first necessary to convert the grayscale image according to the formula. The conversion formula is as follows, where R, G, and B are the three channels of the original image, and I is the converted grayscale image.

[0042] I=0.2989R+0.5870G+0.1140B

[0043] 2) Find the pixel at the coordinate (x, y) position in image I and calculate the gradient I in both directions x , I y , the calculation formula is as follows, where I(x+1,y) is the pixel value at the (x+1,y) position.

[0044] I x =I(x+1,y)-I(x-1,y)

[0045] I y =I(x,y+1)-I(x,y-1)

[0046] 3) Due to the gradient I x ,I y The edge of is invalid, so remove the edge pixels with a width of 1. The specific formula is as follows. H and W in the formula are the gradient matrix I x ,I y The height and width of the

[0047] I x =I x (2, H-1, 2, W-1)

[0048] I y =I y (2:H-1, 2:W-1)

[0049] 4) According to the gradient matrix I x ,I y Calculate the Harris matrix M. The specific formula is as follows:

[0050]

[0051] A=I x I x

[0052] B=I y I y

[0053] C=I x I y

[0054] 5) According to the following formula, Gaussian filtering is performed on the matrix M to smooth and denoise it, so as to prevent the noise from affecting the eigenvalues ​​of the M matrix and thus affecting the extraction of corner points. The calculation result matrix takes the same size as I.

[0055]

[0056]

[0057]

[0058] Where ω is the Gaussian filter coefficient, which can be selected to be 5*5:

[0059]

[0060] 6) Calculate the Harris response function value R of the corner point according to the following formula, where k is an empirical constant, generally 0.04-0.06.

[0061] R = detM-k(traceM) 2 =AB-CC-k(A+B) 2

[0062] 7) Find the position of the corner point according to the Harris response function value and determine the integer coordinate value of the corner point. The specific method includes: selecting the local maximum value in the 8-neighborhood as the integer coordinate value of the corner point, and satisfying that the Harris response function value of the corner point>T, where T is the threshold and max(R) is the corner response function value corresponding to the strongest corner point. Since there is no 8-neighborhood area at the boundary position, the boundary position is not considered during the search.

[0063] T=0.01·max(R)

[0064] 8) Get the decimal coordinate value x of the corner point according to the integer coordinate values ​​x and y of the corner point offset and offset .

[0065]

[0066]

[0067]

[0068]

[0069]

[0070]

[0071] x offset=-0.5(dy2·dx-0.5dxy·dy)·detinv

[0072] y offset =-0.5(dx2·dy-0.5dxy·dx)·detinv

[0073] 9) The integer coordinates x and y of the corner point and the decimal coordinates x of the corner point are offset and offset Add them together to get the coordinates of the corner points.

[0074] 102. Select a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image.

[0075] The preset direction may be a diagonal direction of the image.

[0076] For an embodiment of the present invention, step 102 may specifically include: obtaining the distance between each corner point of a preset number of corner points and the edge point in the preset direction according to the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image; and selecting the corner point with the smallest distance to the edge point in the preset direction from the preset number of corner points as the de-jittering reference corner point.

[0077] 103. Determine a jitter translation amount according to a difference between a coordinate value of the jitter removal reference corner point in the first frame image and a coordinate value of the jitter removal reference corner point in any other frame image.

[0078] For example, you can Figure 3 As shown, the green box is the selected ROI area. Figure 4 This is the corner point detection result of the first frame. The jitter offsets obtained for frames 2-10 are shown in the following table:

[0079] X-direction offset Y-direction offset Frame 2 -0.00444793701171875 -1.80067825317383 Frame 3 -0.00886154174804688 -1.98818969726563 Frame 4 0.0586204528808594 -3.10218811035156 Frame 5 0.460063934326172 -2.22249221801758 Frame 6 -0.646316528320313 -1.95912551879883 Frame 7 0.276443481445313 -0.334548950195313 Frame 8 0.109294891357422 0.508811950683594 Frame 9 0.151401519775391 1.45162200927734 Frame 10 0.0879478454589844 2.15146636962891

[0080] 104. Perform de-jittering processing on a vehicle target position in a video frame image corresponding to the jitter offset according to the jitter offset.

[0081] For the embodiment of the present invention, step 104 may specifically include: determining whether the jitter offset is within a preset offset range; if so, de-jittering the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset; if not, de-jittering the vehicle target position in the current video frame image according to the jitter offset corresponding to the adjacent frame image. The absolute value of the preset offset range in the x direction is usually within 5, and the absolute value of the preset offset range in the y direction is within 10. By setting a reasonable preset offset range, the problem of excessive de-jittering caused by errors in offset calculation can be avoided.

[0082] For the embodiments of the present invention, the specific application scenario can be as follows, but is not limited to this, specifically including: inputting the current frame image; then selecting the ROI area of ​​the corner point to be extracted from the background area outside the road vehicle of the current frame image; performing corner point detection on the ROI area to obtain the coordinates of the corner point and the Harris response function value, the Harris response function value represents the probability of the point becoming a corner point; then selecting the three with the largest response function values ​​from all the corner points as the three strongest corner points in the ROI area; calculating the distances from the three corner points to the edge points of the image in the preset direction in the current frame image, and selecting the corner point corresponding to the smallest distance as the corner point used for de-jittering the current frame image; finally, using the corner point coordinates to subtract the corresponding corner point coordinates in the first frame image to obtain the jitter translation amount of the current frame image.

[0083] The present invention provides a video image acquisition jitter processing method, which first selects an interested ROI region from a monitoring video image, calculates the jitter translation amount based on the coordinates of the corner points in the selected interested ROI region, and completes the image de-jittering process based on the jitter translation amount. Since only a small part of the interested ROI region is selected from the entire image as the original image for de-jittering, it is not necessary to perform calculation processing on the entire image, which can improve the efficiency of image de-jittering, reduce processing time, and realize real-time image de-jittering.

[0084] To implement the method provided by the embodiment of the present invention, the embodiment of the present invention provides a video image acquisition jitter processing system, such as Figure 2 As shown, the system includes: a selection unit 21, a determination unit 22, and a de-jittering unit 23.

[0085] The selection unit 21 is used to select an interesting ROI region from the monitoring video image, and determine a preset number of corner points and coordinate values ​​of each corner point from the ROI region.

[0086] The preset number may be 2, 3, 4, etc., and the embodiment of the present invention does not limit this. Because the street lamp where the camera is located where the jitter occurs is a small local jitter in a plane, the embodiment of the present invention selects a small area to detect the jitter translation amount, which can avoid a large amount of calculations for the entire image and the matching of a large number of corner points. The moving target in the foreground area is prone to occlusion, so the ROI area of ​​interest is selected from the background area and contains clearer corner points. For example, a background area image with high contrast between the foreground and background, acute angles of the corner points, and a single pixel value of the background can be selected as the ROI area of ​​interest.

[0087] The selection unit 21 is further configured to select a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image.

[0088] The determination unit 22 is used to determine the jitter translation amount according to the difference between the coordinate value of the jitter removal reference corner point in the first frame image and the coordinate value of the jitter removal reference corner point in any other frame image.

[0089] The de-jittering unit 23 is used to perform de-jittering processing on the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset.

[0090] Furthermore, the selection unit 21 is specifically configured to select an image containing a background area and a region containing clear corner points from the surveillance video image as the ROI region.

[0091] Furthermore, the determination unit 22 is specifically used to obtain the Harris corner point response function value corresponding to each corner point in the ROI area; and select a preset number of corner points and the coordinates corresponding to the corner points from all corner points according to the Harris corner point response function value corresponding to each corner point.

[0092] Furthermore, the selection unit 21 is specifically used to obtain the distance between each corner point of a preset number of corner points and the edge point in the preset direction based on the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image; and select the corner point with the smallest distance to the edge point in the preset direction from the preset number of corner points as the de-jittering reference corner point.

[0093] Furthermore, the de-jitter unit 23 is specifically used to determine whether the jitter offset is within a preset offset range; if so, de-jitter processing is performed on the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset; if not, de-jitter processing is performed on the vehicle target position in the current video frame image according to the jitter offset corresponding to the adjacent frame image.

[0094] Among them, the absolute value of the preset offset range in the x direction is usually within 5, and the absolute value of the preset offset range in the y direction is within 10. By setting a reasonable preset offset range, the problem of excessive de-jittering caused by errors in offset calculation can be avoided.

[0095] The video image acquisition jitter processing system provided by the present invention first selects an ROI region of interest from a surveillance video image, calculates the jitter translation amount based on the coordinates of the corner points in the selected ROI region of interest, and completes the image de-jittering process based on the jitter translation amount. Since only a small portion of the ROI region of interest is selected from the entire image as the original image for de-jittering, it is not necessary to perform calculation processing on the entire image, which can improve the efficiency of image de-jittering, reduce processing time, and realize real-time image de-jittering.

[0096] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0097] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0098] The disclosed embodiments are described above to enable any person skilled in the art to implement or use the present invention. Various modifications of these embodiments are obvious to those skilled in the art, and the general principles defined herein may also be applied to other embodiments without departing from the spirit and scope of the present disclosure. Therefore, the present disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0099] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

[0100] Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps described above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.

[0101] The various illustrative logic blocks or units described in the embodiments of the present invention can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic system, a discrete gate or transistor logic, a discrete hardware component, or any combination of the above. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing systems, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0102] The steps of the method or algorithm described in the embodiments of the present invention can be directly embedded in hardware, a software module executed by a processor, or a combination of the two. The software module can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or other storage media of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a user terminal. Optionally, the processor and the storage medium can also be arranged in different components in the user terminal.

[0103] In one or more exemplary designs, the above functions described in the embodiments of the present invention can be implemented in hardware, software, firmware or any combination of the three. If implemented in software, these functions can be stored on a computer-readable medium, or transmitted in the form of one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. Storage media can be any available media that can be accessed by any general or special computer. For example, such computer-readable media can include but are not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage systems, or any other medium that can be used to carry or store program codes in the form of instructions or data structures and other forms that can be read by general or special computers, or general or special processors. In addition, any connection can be appropriately defined as a computer-readable medium, for example, if the software is transmitted from a website site, server or other remote resource through a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wirelessly, such as infrared, wireless and microwave, it is also included in the defined computer-readable medium. The disk and disc include compact disk, laser disk, optical disk, DVD, floppy disk and blue-ray disk. Disks usually copy data magnetically, while discs usually copy data optically with lasers. The above combination can also be included in computer readable media.

[0104] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A video image acquisition jitter processing method, characterized in that: The method comprises: Selecting an interested ROI region from the surveillance video image, and determining a preset number of corner points and coordinate values ​​of each corner point from the ROI region; Selecting a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image; Determine a jitter offset according to a difference between a coordinate value of the jitter removal reference corner point in the first frame image and a coordinate value of the jitter removal reference corner point in any other frame image; De-jittering the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset; The step of determining a preset number of corner points and the coordinate value of each corner point from the ROI area comprises: Obtaining the Harris corner point response function value corresponding to each corner point in the ROI area; According to the Harris corner point response function value corresponding to each corner point, a preset number of corner points and the coordinates corresponding to the corner points are selected from all the corner points.

2. The video image acquisition jitter processing method according to claim 1, characterized in that: The step of selecting an ROI region of interest from a surveillance video image comprises: An image containing a background area and a region containing clear corner points is selected from the surveillance video image as the ROI region.

3. The video image acquisition jitter processing method according to claim 1, characterized in that: The step of selecting a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image comprises: Acquire the distance between each of the preset number of corner points and the edge point in the preset direction according to the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image; A corner point having the smallest distance from an edge point in the preset direction is selected from the preset number of corner points as the de-jittering reference corner point.

4. The video image acquisition jitter processing method according to claim 1, characterized in that: The step of performing de-jitter processing on the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset comprises: Determining whether the jitter offset is within a preset offset range; If yes, de-jittering the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset; If not, de-jitter processing is performed on the vehicle target position in the current video frame image according to the jitter offset corresponding to the adjacent frame image.

5. A video image acquisition jitter processing system, characterized in that: The system comprises: A selection unit, used to select an interested ROI region from the surveillance video image, and determine a preset number of corner points and coordinate values ​​of each corner point from the ROI region; The selection unit is further configured to select a de-jittering reference corner point from the preset number of corner points according to the coordinates of the corner point and the coordinates of an edge point in a preset direction in the image; A determination unit, configured to determine a jitter offset according to a difference between a coordinate value of the jitter removal reference corner point in the first frame image and a coordinate value of the jitter removal reference corner point in any other frame image; A de-jittering unit, configured to perform de-jittering processing on a vehicle target position in a video frame image corresponding to the jitter offset according to the jitter offset; The determination unit is specifically used to obtain the Harris corner point response function value corresponding to each corner point in the ROI area; and select a preset number of corner points and the coordinates corresponding to the corner points from all corner points according to the Harris corner point response function value corresponding to each corner point.

6. A video image acquisition jitter processing system according to claim 5, characterized in that: The selection unit is specifically configured to select an image containing a background area and a region containing clear corner points from the surveillance video image as the ROI region.

7. The video image acquisition jitter processing system according to claim 5, characterized in that: The selection unit is specifically used to obtain the distance between each corner point of a preset number of corner points and the edge point in the preset direction according to the coordinates of the corner point and the coordinates of the edge point in the preset direction in the image; and select the corner point with the smallest distance to the edge point in the preset direction from the preset number of corner points as the de-jittering reference corner point.

8. The video image acquisition jitter processing system according to claim 5, characterized in that: The de-jitter unit is specifically used to determine whether the jitter offset is within a preset offset range; if so, de-jitter processing is performed on the vehicle target position in the video frame image corresponding to the jitter offset according to the jitter offset; if not, de-jitter processing is performed on the vehicle target position in the current video frame image according to the jitter offset corresponding to the adjacent frame image.

Images