Truck non-stop steering judgment method based on video analysis

Abstract

The invention discloses a truck non-stop steering judgment method based on video analysis, and relates to the technical field of image processing, and the method comprises the steps: extracting video stream information corresponding to a to-be-detected region, and analyzing the video stream information to determine track point information corresponding to each target vehicle; preprocessing the track point information of each target vehicle to generate smoothed first track point information of each target vehicle; and according to the first track point information corresponding to each target vehicle, determining the steering of any target vehicle, and according to the included angle between the driving direction of the next moment and the driving direction of the previous moment, judging whether the target vehicle completes turning. According to the method, the track point information corresponding to each target vehicle is determined, real and reliable data support can be provided for subsequent steering or not, in addition, steering or not is judged by combining the included angle between the driving directions of the previous moment and the next moment, and the judgment accuracy can be improved.

Description

Background Art

[0002] In urban traffic, trucks turning right often require extra attention and precautions to avoid traffic accidents and pedestrian injuries. However, traditional traffic monitoring systems often fail to accurately identify trucks turning right or turning right without stopping, resulting in frequent traffic and pedestrian safety accidents. The existing technology for identifying turning situations has the following problems:

[0003] 1. Low recognition accuracy: Traditional methods may have misjudgments or missed judgments in vehicle recognition, especially in complex traffic scenarios, where recognition accuracy is easily affected.

[0004] 2. Difficulty in accurately detecting parking behavior: Some traditional methods may not be able to accurately detect the parking behavior of vehicles, including violations such as turning right without stopping, resulting in the inability to timely discover traffic safety hazards.

[0005] 3. Data labeling is a heavy task: Some methods may require a large amount of labeled data for training. Labeling large-scale video data is a heavy and time-consuming task, which increases the cost of system development and maintenance.

[0006] 4. High equipment cost: Some traditional methods may require additional sensors or devices for vehicle monitoring, which increases equipment cost and system complexity. Summary of the invention

[0007] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a method for judging whether a truck has not stopped and turned based on video analysis, which is as follows:

[0008] 1) In the first aspect, the present invention provides a method for judging whether a truck has turned without stopping based on video analysis, and the specific technical solution is as follows:

[0009] Extracting video stream information corresponding to the area to be detected, and analyzing the video stream information to determine the track point information corresponding to each target vehicle;

[0010] Preprocessing the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle;

[0011] The turning direction of any target vehicle is determined by the first trajectory point information corresponding to each target vehicle, and whether the target vehicle has completed the turn is judged by the angle between the driving direction at the next moment and the driving direction at the previous moment.

[0012] The beneficial effects of the method for judging whether a truck has turned without stopping based on video analysis provided by the present invention are as follows:

[0013] By determining the trajectory point information corresponding to each target vehicle, it is possible to provide real and reliable data support for whether a turn will occur later. In addition, preprocessing the trajectory point information can improve the accuracy and continuity of the data. In addition, combining the angle between the driving directions at the previous moment and the next moment to determine whether a turn has occurred can improve the accuracy of the judgment.

[0014] Based on the above solution, the present invention can also be improved as follows.

[0015] Furthermore, the preprocessing includes: noise reduction processing and smoothing processing.

[0016] Furthermore, the process of judging whether the target vehicle has completed the turn is specifically as follows, based on the angle between the driving direction at the next moment and the driving direction at the previous moment:

[0017] It is continuously determined whether the degrees of the n included angles exceed the degrees of the preset included angle, and when the determination result is yes, it is determined that the target vehicle has completed the turn.

[0018] Furthermore, the method further includes: removing discrete points in the trajectory point information of any target vehicle.

[0019] 2) In the second aspect, the present invention also provides a truck non-stop turning judgment system based on video analysis, and the specific technical solution is as follows:

[0020] The extraction module is used to: extract the video stream information corresponding to the area to be detected, and analyze the video stream information to determine the track point information corresponding to each target vehicle;

[0021] The preprocessing module is used to: preprocess the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle;

[0022] The judgment module is used to determine the turning of any target vehicle through the first trajectory point information corresponding to each target vehicle, and to judge whether the target vehicle has completed the turn through the angle between the driving direction at the next moment and the driving direction at the previous moment.

[0023] Based on the above solution, the present invention can also be improved as follows.

[0024] Furthermore, the preprocessing includes: noise reduction processing and smoothing processing.

[0025] Furthermore, the process of judging whether the target vehicle has completed the turn is specifically as follows, based on the angle between the driving direction at the next moment and the driving direction at the previous moment:

[0026] It is continuously determined whether the degrees of the n included angles exceed the degrees of the preset included angle, and when the determination result is yes, it is determined that the target vehicle has completed the turn.

[0027] Furthermore, it also includes: a removal module for removing discrete points in the trajectory point information of any target vehicle.

[0028] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, wherein the processor is coupled to a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements any of the above methods.

[0029] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above methods.

[0030] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0032] Figure 1 A schematic flow chart of a method for judging whether a truck has turned without stopping based on video analysis according to an embodiment of the present invention;

[0033] Figure 2 The figure is a schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0034] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0035] like Figure 1 As shown, a method for judging whether a truck has turned without stopping based on video analysis in an embodiment of the present invention comprises the following steps:

[0036] S1, extracting video stream information corresponding to the area to be detected, and analyzing the video stream information to determine the track point information corresponding to each target vehicle;

[0037] S2, preprocessing the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle;

[0038] S3, determining the turning direction of any target vehicle through the first trajectory point information corresponding to each target vehicle, and judging whether the target vehicle has completed the turn through the angle between the driving direction at the next moment and the driving direction at the previous moment.

[0039] The beneficial effects of the method for judging whether a truck has turned without stopping based on video analysis provided by the present invention are as follows:

[0040] By determining the trajectory point information corresponding to each target vehicle, it is possible to provide real and reliable data support for whether a turn will occur later. In addition, preprocessing the trajectory point information can improve the accuracy and continuity of the data. In addition, combining the angle between the driving directions at the previous moment and the next moment to determine whether a turn has occurred can improve the accuracy of the judgment.

[0041] S1, extracting the video stream information corresponding to the area to be detected, and analyzing the video stream information to determine the track point information corresponding to each target vehicle.

[0042] The area to be detected refers to a traffic intersection or a road section where vehicles are traveling.

[0043] Video stream information is collected by a camera installed at a high place or a roadside monocular camera.

[0044] The brightness of each frame image in the video stream is adjusted according to a fixed preset cycle. During the brightness adjustment process, the corresponding brightness adjustment scheme is searched in the historical database in combination with the current month and the current time, and the brightness of each frame image in the current fixed preset cycle is adjusted based on the corresponding brightness adjustment scheme.

[0045] The vehicle type corresponding to each track point information, the coordinates of the track point in each track point information, the vehicle width, the vehicle length and the vehicle heading angle are given.

[0046] S2, preprocessing the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle.

[0047] Preprocessing includes but is not limited to: removing noise points, smoothing or interpolating trajectory points.

[0048] S3, determining the turning direction of any target vehicle through the first trajectory point information corresponding to each target vehicle, and judging whether the target vehicle has completed the turn through the angle between the driving direction at the next moment and the driving direction at the previous moment.

[0049] In another embodiment of the present solution, a camera is set up at each intersection to collect video. During the entire process of completing the right turn, it is necessary to associate the video collection camera before the right turn with the video collection camera after the right turn is completed, and verify the right turn completion action of the target vehicle through the associated cameras and corresponding data. The specific process is:

[0050] The target vehicle A completes a right turn at a certain intersection, and the video acquisition camera a before the right turn is associated with the video acquisition camera b after the right turn. It should be noted that at the crossroads or T-junctions, camera b is located on the right side of camera a, that is, the area captured by camera b is the section of the road where the target vehicle A travels after turning. The information about the target vehicle A collected by camera a is extracted, and the information about the target vehicle A includes but is not limited to: the unique ID (license plate number) of the target vehicle A, the appearance time of the target vehicle A, the disappearance time of the target vehicle A, and the vehicle characteristics of the target vehicle A (vehicle category, vehicle scratches, etc.). At this time, the monitoring cycle is preset at intervals, and the video captured by camera b is searched for information that interferes with the target vehicle A. If not, it means that the target vehicle A has not completed the right turn. At this time, an early warning message is generated, and other cameras are called to complete the search for the target vehicle A and determine the next direction of travel of the target vehicle A. If yes, it means that the target vehicle A has completed the right turn. The above solution can further improve the judgment of whether the right turn action is completed. In addition, since multiple cameras are combined for judgment, it can also solve the misjudgment of the right turn action caused by the blind spot of a single camera.

[0051] In addition, in other embodiments of this solution, it also includes:

[0052] Sliding window size selection: Select the appropriate sliding window size based on the speed of the vehicle and the required accuracy.

[0053] The role of the sliding window is to assist in determining the right turn of the vehicle through local detection and then infer the result of the overall right turn.

[0054] 1) By setting the sliding window size and step size:

[0055] Window size: For example, if the truck turns right within 5 seconds, the window size covers all position data within the 5 seconds.

[0056] Step size: The distance the window moves each time, such as a small step size of 1 second.

[0057] 2) Window sliding and continuous analysis:

[0058] a) The window advances one step at a time, such as one second, to determine the distribution of trajectory points within the step.

[0059] b) Analyze and evaluate the characteristics of the trajectory points in the new window.

[0060] Continuous monitoring: Continue this process until the entire trajectory sequence is traversed. And so on to determine the overall situation of the vehicle turning right. The advantage of the sliding window is that the local analysis and then inference of the overall analysis will help to obtain the accuracy of the results.

[0061] Curvature calculation: Select the appropriate curvature calculation method for calculation and calibration.

[0062] The function of curvature is to reflect the curvature of the path when the vehicle turns right, which is a very important judgment point for identifying whether the vehicle turns right.

[0063] The sliding window is combined with the curvature to jointly judge the behavior of right turn.

[0064] 1. Explanation on curvature estimation

[0065] a) Since the vehicle trajectory consists of discrete trajectory points, these points are used to estimate the curvature.

[0066] b) Three consecutive points: Select three consecutive trajectory points A, B, and C in each sliding window.

[0067] c) Calculate the curvature:

[0068] If the three points are not collinear, a unique circle (approximately an arc) can be determined by them. The reciprocal of the radius R of the arc is the average curvature of this path k = 1 / R.

[0069] If the three points are almost collinear, the curvature can be considered close to 0, which means that the path is almost straight.

[0070] 2. Curvature analysis in window sliding

[0071] The curvature value is continuously updated and calculated as the window slides within the sliding window.

[0072] 1) Initialize the window

[0073] a) Initially select the first three points as the curvature calculation objects within the window.

[0074] 2) Window sliding

[0075] a) Moving step, the first point will be removed and a new point will be added to form three connected points for curvature calculation.

[0076] 3) Continuous Updates

[0077] a) Repeat this process throughout the whole process to obtain a series of time-varying curvature values.

[0078] 3. Curvature judgment and steering

[0079] 1) Increased curvature: When a vehicle enters a curve, the curvature will gradually increase. If it increases significantly and in the same direction, it is definitely heading to the right.

[0080] 2) The curvature is stabilized at a higher value: Once the vehicle is in the middle of the curve, the curvature will maintain a relatively high and stable value.

[0081] Curvature decreases back to low values: When the vehicle completes a turn, the curvature decreases until it approaches 0. The surface returns to a straight-line state.

[0082] In another embodiment of the present invention, an early warning process is also included, that is, when the angle of the target vehicle continues to be abnormal for a fixed period of time, an alarm is generated to remind the driver to pay attention. The abnormality refers to: when the angle exceeds the safety range corresponding to the preset angle, it is judged as abnormal.

[0083] Based on the above solution, the present invention can also be improved as follows.

[0084] Furthermore, the preprocessing includes: noise reduction processing and smoothing processing.

[0085] Furthermore, the process of judging whether the target vehicle has completed the turn is specifically as follows, based on the angle between the driving direction at the next moment and the driving direction at the previous moment:

[0086] It is continuously determined whether the degrees of the n included angles exceed the degrees of the preset included angle, and when the determination result is yes, it is determined that the target vehicle has completed the turn.

[0087] Furthermore, the method further includes: removing discrete points in the trajectory point information of any target vehicle.

[0088] That is, this solution can detect the truck turning right and the location of the personnel, and can preset alarms at the same time. The information can be uploaded to the server (the server can push notifications, such as nearby instrument amplification / strobe equipment to warn to pay attention to the safe distance);

[0089] In addition, if some trucks are equipped with vehicle-road equipment, they can also notify or ask the driver to slow down by reporting to the server when a situation is detected, thereby avoiding dangerous accidents.

[0090] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0091] The present invention also provides a truck non-stop turning judgment system based on video analysis, and the specific technical solution is as follows:

[0092] The extraction module is used to: extract the video stream information corresponding to the area to be detected, and analyze the video stream information to determine the track point information corresponding to each target vehicle;

[0093] The preprocessing module is used to: preprocess the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle;

[0094] The judgment module is used to determine the turning of any target vehicle through the first trajectory point information corresponding to each target vehicle, and to judge whether the target vehicle has completed the turn through the angle between the driving direction at the next moment and the driving direction at the previous moment.

[0095] Based on the above solution, the present invention can also be improved as follows.

[0096] Furthermore, the preprocessing includes: noise reduction processing and smoothing processing.

[0097] Furthermore, the process of judging whether the target vehicle has completed the turn is specifically as follows, based on the angle between the driving direction at the next moment and the driving direction at the previous moment:

[0098] It is continuously determined whether the degrees of the n included angles exceed the degrees of the preset included angle, and when the determination result is yes, it is determined that the target vehicle has completed the turn.

[0099] Furthermore, it also includes: a removal module for removing discrete points in the trajectory point information of any target vehicle.

[0100] It should be noted that the beneficial effects of the truck non-stop turning judgment system based on video analysis provided by the above embodiment are the same as the beneficial effects of the truck non-stop turning judgment method based on video analysis, which will not be repeated here. In addition, when the system provided by the above embodiment realizes its functions, it only uses the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0101] like Figure 2As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above methods, specifically:

[0102] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements a method for judging whether a truck has not stopped and turned based on video analysis provided in the above embodiment. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the electronic device 300 may also include other components for realizing the functions of the device, which will not be described in detail here.

[0103] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements any one of the above methods.

[0104] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0105] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above methods.

[0106] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0107] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0108] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0109] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for judging whether a truck has turned without stopping based on video analysis, characterized in that: include: Extracting video stream information corresponding to the area to be detected, and analyzing the video stream information to determine the track point information corresponding to each target vehicle; Preprocessing the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle; The turning direction of any target vehicle is determined by the first trajectory point information corresponding to each target vehicle, and whether the target vehicle has completed the turn is judged by the angle between the driving direction at the next moment and the driving direction at the previous moment.

2. A method for judging whether a truck has not stopped and turned based on video analysis according to claim 1, characterized in that: The preprocessing includes: noise reduction processing and smoothing processing.

3. The method for judging whether a truck has not stopped and turned based on video analysis according to claim 1, characterized in that: The process of judging whether the target vehicle has completed the turn by the angle between the driving direction at the next moment and the driving direction at the previous moment is as follows: It is continuously determined whether the degrees of the n included angles exceed the degrees of the preset included angle, and when the determination result is yes, it is determined that the target vehicle has completed the turn.

4. The method for judging whether a truck has not stopped and turned based on video analysis according to claim 1, characterized in that: Also includes: The discrete points in the trajectory point information of any target vehicle are eliminated.

5. A truck non-stop turning judgment system based on video analysis, characterized in that: include: The extraction module is used to: extract the video stream information corresponding to the area to be detected, and analyze the video stream information to determine the track point information corresponding to each target vehicle; The preprocessing module is used to: preprocess the trajectory point information of each target vehicle to generate smoothed first trajectory point information of each target vehicle; The judgment module is used to determine the turning of any target vehicle through the first trajectory point information corresponding to each target vehicle, and to judge whether the target vehicle has completed the turn through the angle between the driving direction at the next moment and the driving direction at the previous moment.

6. The system for judging whether a truck has not stopped and turned based on video analysis according to claim 5, characterized in that: The preprocessing includes: noise reduction processing and smoothing processing.

7. The system for judging whether a truck has not stopped and turned based on video analysis according to claim 5, characterized in that: The process of judging whether the target vehicle has completed the turn by the angle between the driving direction at the next moment and the driving direction at the previous moment is as follows: It is continuously determined whether the degrees of the n included angles exceed the degrees of the preset included angle, and when the determination result is yes, it is determined that the target vehicle has completed the turn.

8. The system for judging whether a truck has not stopped and turned based on video analysis according to claim 5, characterized in that: Also includes: The elimination module is used to eliminate discrete points in the trajectory point information of any target vehicle.

9. An electronic device, characterized in that: The electronic device comprises a processor, the processor is coupled to a memory, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements the method according to any one of claims 1 to 4.

Images