An intelligent traffic management and control method, system and program product

Abstract

The application belongs to the technical field of intelligent traffic, and specifically discloses an intelligent traffic management and control method, system and program product, which extracts image ROI and detects moving targets through collecting monitoring image sequences of each traffic direction at an intersection, so as to determine the moving target information in the corresponding interval, then establishes the moving track of each moving target to calculate the congestion index of the corresponding traffic direction, and finally determines the green light passing time of each traffic direction according to the comprehensive congestion index of each traffic direction, so as to realize fine and dynamic adjustment of the signal light time of the traffic intersection. The application allocates the signal light time of the intersection based on the congestion index, can more accurately determine the congestion of each traffic direction at the traffic intersection, makes the signal light timing capable of responding to the change of the traffic demand of each direction in real time, significantly improves the overall passing efficiency of the intersection, and is highly adaptable, can comprehensively evaluate the congestion of the vehicle flow and the pedestrian flow, and is suitable for mixed traffic scenes.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, specifically relating to an intelligent traffic control method, system, and program product. Background Technology

[0002] With rapid urbanization, traffic congestion has become a widespread problem. Traditional traffic light control systems often employ fixed timing or simple induction coil triggering modes, making it difficult to adapt to real-time changes in traffic flow. Some existing intelligent traffic light control methods use cameras to capture images of intersections, detect and count vehicles, and then estimate traffic flow to adjust the traffic lights. However, these methods have the following shortcomings: 1. Relying solely on vehicle counting fails to effectively depict the movement of traffic flow and the nature of "congestion"; 2. It is difficult to consider the congestion assessment of other pedestrian groups (such as pedestrians); 3. It lacks a comprehensive analysis of the dynamic changes in traffic flow in time and space, leading to inaccurate judgments. Therefore, there is an urgent need for a method that can more accurately and comprehensively reflect the true congestion situation of pedestrians in all directions at intersections, thereby achieving intelligent control of traffic lights. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent traffic management method, system, and program product to solve the aforementioned problems existing in the prior art.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, an intelligent traffic management method is provided, including: The traffic monitoring image sequence is obtained from the image acquisition device on one side of each direction of traffic at the intersection. The traffic monitoring image sequence contains several traffic monitoring images arranged in chronological order. The ROI of each traffic monitoring image in the traffic monitoring image sequence is extracted to obtain the target area image, and the target area image sequence is composed of the target area images. Moving target detection is performed on the target region image sequence to identify each moving target, and the image coordinates of each moving target are marked in each target region image of the target region image sequence; The motion trajectory of each moving target in the image coordinate system is determined based on the image coordinates of each moving target in the image of each target area, and the comprehensive position standard deviation parameter of all moving targets is determined based on the motion trajectory of each moving target. The single-sided congestion index for the corresponding direction of travel is calculated based on the comprehensive position standard deviation parameter of all moving targets. The comprehensive congestion index for the corresponding traffic direction is calculated using the single-sided congestion index on both sides of the corresponding traffic direction, and the green light duration for each traffic direction at the intersection is determined based on the comprehensive congestion index for each traffic direction at the intersection. Based on the green light duration for each direction of traffic at the intersection, a signal light duration adjustment command is generated and sent to the signal light controller at the intersection.

[0005] In one possible design, the step of extracting the Region of Interest (ROI) from each traffic monitoring image in the traffic monitoring image sequence to obtain images of each target region includes: Image filtering and image enhancement processing are performed on each traffic monitoring image in the traffic monitoring image sequence to obtain preprocessed traffic monitoring images. Based on the set image ROI cropping location parameters, the corresponding target area image is cropped from each preprocessed traffic monitoring image.

[0006] In one possible design, the step of performing moving target detection on the target region image sequence, identifying each moving target, and marking the image coordinates of each moving target in each target region image of the target region image sequence includes: Optical flow is used to detect moving targets in the target region image sequence, identify each moving target, and mark the bounding box of each moving target in each target region image of the target region image sequence; Determine the image coordinates of the center point of the bounding box of each moving target in each target region image, and use the image coordinates of the center point of the bounding box of each moving target in each target region image as the image coordinates of each moving target in each target region image.

[0007] In one possible design, determining the comprehensive position standard deviation parameter of all moving targets based on their motion trajectories includes: Mark each trajectory point on the trajectory of each moving target and determine the image coordinates of each trajectory point in the image coordinate system. On the trajectory of the same moving target, one trajectory point corresponds to one image of the target area. Calculate the standard deviation σ of the positions of all motion trajectory points in the image coordinate system along the x-axis. x And the standard deviation σ of the positions of all motion trajectory points in the y-axis direction. y Using the position standard deviation σ x and location standard deviation σ y The combined position standard deviation parameter that makes up all moving targets.

[0008] In one possible design, the calculation of the one-sided congestion index for the corresponding traffic direction based on the comprehensive position standard deviation parameter of all moving targets includes: The comprehensive location standard deviation parameter is substituted into the preset one-sided congestion index formula for calculation to obtain the one-sided congestion index for the corresponding traffic direction. The one-sided congestion index formula is as follows:

[0009] Where P is the one-sided congestion index, and R... x R is the pixel length of the target region image along the x-axis of the image coordinate system. y Let be the pixel length of the target region image along the y-axis of the image coordinate system, N be the number of moving targets, A be the pixel area of ​​the target region image, F be the number of target region images in the target region image sequence, α be the set first weight coefficient, and β be the set second weight coefficient.

[0010] In one possible design, the calculation of the comprehensive congestion index for the corresponding traffic direction using the unilateral congestion indices on both sides of the corresponding traffic direction includes: The average of the congestion indices on both sides of the corresponding traffic direction is used to obtain the comprehensive congestion index for that traffic direction.

[0011] In one possible design, determining the green light duration for each direction of traffic at the intersection based on the comprehensive congestion index for each direction includes: The comprehensive congestion index for each direction of traffic at the intersection is substituted into a pre-set green light duration calculation model to obtain the green light duration for each direction of traffic at the intersection. The green light duration calculation model is as follows:

[0012] Where i is the direction number, M is the total number of directions, and T i T represents the green light duration for traffic direction i. i-min T is the lower limit of the green light duration for the set traffic direction i. i-max P is the maximum green light duration for the set traffic direction i. i ’ The overall congestion index is for traffic direction i.

[0013] Secondly, an intelligent traffic control system is provided, comprising an image acquisition unit, an image processing unit, a target detection unit, a trajectory determination unit, an index calculation unit, a duration calculation unit, and an adjustment and control unit, wherein: The image acquisition unit is used to acquire a sequence of traffic monitoring images collected by the image acquisition device on one side of each direction of traffic at the intersection. The sequence of traffic monitoring images includes several traffic monitoring images arranged in chronological order. The image processing unit is used to extract the ROI of each traffic monitoring image in the traffic monitoring image sequence to obtain the target area image, and to use the target area images to form a target area image sequence. The target detection unit is used to detect moving targets in the target region image sequence, identify each moving target, and mark the image coordinates of each moving target in each target region image of the target region image sequence. The trajectory determination unit is used to determine the motion trajectory of each moving target in the image coordinate system based on the image coordinates of each moving target in the image of each target area, and to determine the comprehensive position standard deviation parameter of all moving targets based on the motion trajectory of each moving target. The index calculation unit is used to calculate the single-sided congestion index for the corresponding direction of travel based on the comprehensive position standard deviation parameter of all moving targets. The duration calculation unit is used to calculate the comprehensive congestion index of the corresponding traffic direction using the single-sided congestion index on both sides of the corresponding traffic direction, and to determine the green light duration of each traffic direction at the traffic intersection based on the comprehensive congestion index of each traffic direction at the traffic intersection. The adjustment control unit is used to generate traffic light duration adjustment instructions based on the green light duration for each direction of traffic at the intersection, and send the traffic light duration adjustment instructions to the traffic light controller at the intersection.

[0014] Thirdly, an intelligent traffic management system is provided, including: Memory, used to store instructions; A processor is configured to read instructions stored in the memory and execute the method described in any one of the first aspects above, according to the instructions.

[0015] Fourthly, a computer-readable storage medium is provided, on which instructions are stored, which, when executed on a computer, cause the computer to perform any of the methods described in the first aspect. A computer program product is also provided, which, when executed on a computer, performs any of the methods described in the first aspect.

[0016] Beneficial Effects: This invention extracts the ROI and detects moving targets by collecting monitoring image sequences of each traffic direction at an intersection. This determines the information of moving targets within the corresponding time intervals. Then, it establishes the motion trajectory of each moving target and calculates the congestion index for the corresponding traffic direction. Finally, it determines the green light duration for each traffic direction based on the comprehensive congestion index, achieving refined and dynamic adjustment of traffic light durations at intersections. This invention allocates intersection traffic light durations based on the congestion index, allowing for more accurate assessment of congestion in each traffic direction. This enables the traffic light timing to respond in real-time to changes in traffic demand in each direction, significantly improving the overall traffic efficiency of the intersection. Furthermore, it is highly adaptable, comprehensively assessing the congestion of both vehicle and pedestrian flows, and is suitable for mixed traffic scenarios. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the steps in the method of Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the system configuration in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the system configuration in Embodiment 3 of the present invention. Detailed Implementation

[0019] It should be noted that the descriptions of these embodiments are intended to aid in understanding the invention and do not constitute a limitation thereof. The specific structural and functional details disclosed herein are merely for describing exemplary embodiments of the invention. However, the invention may be embodied in many alternative forms and should not be construed as being limited to the embodiments described herein.

[0020] It should be understood that, unless otherwise explicitly specified and limited, the corresponding terms should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments according to the specific circumstances.

[0021] Specific details are provided in the following description to provide a complete understanding of the exemplary embodiments. However, those skilled in the art will understand that the exemplary embodiments can be implemented without these specific details. For example, apparatus may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other embodiments, well-known processes, structures, and techniques may be omitted with non-essential details to avoid obscuring the embodiments.

[0022] Example 1: This embodiment provides an intelligent traffic control method, which can be applied to corresponding intelligent traffic control terminals, such as... Figure 1 As shown, the method includes the following steps: S1. Obtain a sequence of traffic monitoring images collected by image acquisition devices on one side of each direction of traffic at the intersection, wherein the sequence of traffic monitoring images includes several traffic monitoring images arranged in chronological order.

[0023] In practice, image acquisition devices, such as high-definition surveillance cameras, can be installed on both sides of each direction of traffic at intersections. These devices acquire real-time traffic monitoring video streams within a single area of ​​each direction of traffic. Frames are then extracted from the video stream at intervals, forming traffic monitoring images at various time points. These images are arranged chronologically to create a sequence of traffic monitoring images for the corresponding time period. This sequence is then sent to an intelligent traffic control terminal for further analysis and processing.

[0024] S2. Extract the ROI of each traffic monitoring image in the traffic monitoring image sequence to obtain the target area image, and use the target area images to form the target area image sequence.

[0025] In practice, the control terminal can first perform image filtering and image enhancement processing on each traffic monitoring image in the traffic monitoring image sequence to obtain preprocessed traffic monitoring images. Then, based on the set image ROI (Region of Interest) cropping position parameters (i.e., the set cropping image coordinate parameters), the corresponding target area image is cropped from each preprocessed traffic monitoring image. Since a fixed range cropping method is used, the image range of each target area image is the same, and the same image coordinate system can be used. Finally, the target area images are used to form a target area image sequence in sequence.

[0026] S3. Perform moving target detection on the target region image sequence, identify each moving target, and mark the image coordinates of each moving target in each target region image of the target region image sequence.

[0027] In practical implementation, the control terminal can use optical flow (or other moving target detection methods, such as background subtraction, frame subtraction, etc., depending on actual needs) to detect moving targets in the target region image sequence, identify each moving target, and mark the bounding box of each moving target in each target region image of the target region image sequence. Then, the image coordinates of the center point of each moving target bounding box in each target region image are determined, and the image coordinates of the center point of each moving target bounding box in each target region image are used as the image coordinates of each moving target in each target region image.

[0028] S4. Determine the motion trajectory of each moving target in the image coordinate system based on the image coordinates of each moving target in the image of each target area, and determine the comprehensive position standard deviation parameter of all moving targets based on the motion trajectory of each moving target.

[0029] In practice, the control terminal can construct the motion trajectory of each moving target in the image coordinate system (all target area images use the same image coordinate system) based on the image coordinates of each moving target in the images of each target area. Then, each motion trajectory point is marked on the motion trajectory of each moving target, and the image coordinates of each motion trajectory point in the image coordinate system are determined. On the motion trajectory of the same moving target, one motion trajectory point corresponds to one target area image. Finally, the standard deviation σ of the positions of all motion trajectory points in the image coordinate system (including the x-axis and y-axis) along the x-axis direction is calculated. x And the standard deviation σ of the positions of all motion trajectory points in the y-axis direction. y Using the position standard deviation σ x and location standard deviation σ y The combined position standard deviation parameter that makes up all moving targets.

[0030] S5. Calculate the single-sided congestion index for the corresponding direction of travel based on the comprehensive position standard deviation parameter of all moving targets.

[0031] In practice, the control terminal substitutes the comprehensive location standard deviation parameter into a preset one-sided congestion index formula to calculate the one-sided congestion index for the corresponding traffic direction. The one-sided congestion index formula is as follows:

[0032] Where P is the one-sided congestion index, and a larger value indicates greater congestion. σ x ·σ y It can approximately characterize the spatial dispersion of each trajectory point; when the flow is smooth, the moving targets are more dispersed, and the product is larger; when the flow is congested, the moving targets are concentrated, and the product is smaller. R x R is the pixel length of the target region image along the x-axis of the image coordinate system. y R is the pixel length of the target region image along the y-axis of the image coordinate system. x and R y It is used as a normalization constant. (σ) x ·σ y ) / (R x ·R y The term N / (A·F) represents the normalized spatial dispersion, with a value between 0 and 1. To ensure it is positively correlated with the degree of crowding, this term is subtracted from 1. N is the number of moving targets, A is the pixel area of ​​the target region image, and F is the number of target region images in the target region image sequence. The term N / (A·F) represents the target occurrence density per unit space-time range. α is a set first weighting coefficient, and β is a set second weighting coefficient, α+β=1. For example, α=0.6 and β=0.4 can be chosen to place more emphasis on the dispersion of the motion state.

[0033] The method proposed in this paper abandons the simple counting method for calculating congestion index. It defines the congestion index based on the essential characteristic of traffic flow "spatiotemporal dispersion". By calculating the positional standard deviation of the trajectory points of moving targets, it can effectively distinguish between two states: "uniform and smooth passage" and "slow and dense creeping". In this way, even if the number of vehicles / pedestrians is the same, it can be determined that the dispersion of the latter state is lower and the congestion index is higher, making the judgment more accurate.

[0034] S6. Calculate the comprehensive congestion index of the corresponding traffic direction using the single-sided congestion index on both sides of the corresponding traffic direction, and determine the green light duration for each traffic direction at the traffic intersection based on the comprehensive congestion index of each traffic direction.

[0035] In practice, the control terminal can average the congestion indices on both sides of the corresponding traffic direction to obtain the comprehensive congestion index for that traffic direction. Then, the comprehensive congestion index for each traffic direction at the intersection is substituted into a pre-set green light duration calculation model to calculate the green light duration for each traffic direction at the intersection. The green light duration calculation model is as follows:

[0036] Where i is the direction of travel number, M is the total number of directions of travel, and M=2 at intersections; T i T represents the green light duration for traffic direction i. i-min T is the lower limit of the green light duration for the set traffic direction i. i-max P is the maximum green light duration for the set traffic direction i; i ’ The overall congestion index is for traffic direction i.

[0037] This calculation model ensures that the direction with higher congestion levels receives a greater extension of green light duration, with the total duration exceeding T. i-min With T i-max The green light duration is allocated based on congestion ratio. Additionally, a priority factor (e.g., higher priority for main roads results in a larger priority factor value) can be introduced to adjust the green light duration for each direction. Furthermore, to ensure fairness, the consecutive green light time for any direction cannot exceed its T value. i-max .

[0038] S7. Based on the green light duration for each direction of traffic at the intersection, generate a traffic light duration adjustment command and send the traffic light duration adjustment command to the traffic light controller at the intersection.

[0039] In practice, the control terminal can use the green light duration for each direction of traffic at the intersection to generate a traffic light duration adjustment command. Then, the traffic light duration adjustment command is sent to the traffic light controller at the intersection so that the traffic light controller can execute the corresponding traffic light duration adjustment command to dynamically adjust the duration of the traffic lights at the intersection.

[0040] This method allocates traffic light durations at intersections based on the congestion index, which can more accurately determine the congestion situation in each direction of traffic at the intersection. This allows the traffic light timing to respond in real time to changes in traffic demand in each direction, significantly improving the overall traffic efficiency of the intersection. Furthermore, it is highly adaptable, can comprehensively assess the congestion of vehicle and pedestrian flows, and is suitable for mixed traffic scenarios.

[0041] Example 2: This embodiment provides an intelligent traffic control system, such as Figure 2 As shown, it includes an image acquisition unit, an image processing unit, a target detection unit, a trajectory determination unit, an index calculation unit, a duration calculation unit, and an adjustment and control unit, wherein: The image acquisition unit is used to acquire a sequence of traffic monitoring images collected by the image acquisition device on one side of each direction of traffic at the intersection. The sequence of traffic monitoring images includes several traffic monitoring images arranged in chronological order. The image processing unit is used to extract the ROI of each traffic monitoring image in the traffic monitoring image sequence to obtain the target area image, and to use the target area images to form a target area image sequence. The target detection unit is used to detect moving targets in the target region image sequence, identify each moving target, and mark the image coordinates of each moving target in each target region image of the target region image sequence. The trajectory determination unit is used to determine the motion trajectory of each moving target in the image coordinate system based on the image coordinates of each moving target in the image of each target area, and to determine the comprehensive position standard deviation parameter of all moving targets based on the motion trajectory of each moving target. The index calculation unit is used to calculate the single-sided congestion index for the corresponding direction of travel based on the comprehensive position standard deviation parameter of all moving targets. The duration calculation unit is used to calculate the comprehensive congestion index of the corresponding traffic direction using the single-sided congestion index on both sides of the corresponding traffic direction, and to determine the green light duration of each traffic direction at the traffic intersection based on the comprehensive congestion index of each traffic direction at the traffic intersection. The adjustment control unit is used to generate traffic light duration adjustment instructions based on the green light duration for each direction of traffic at the intersection, and send the traffic light duration adjustment instructions to the traffic light controller at the intersection.

[0042] Example 3: This embodiment provides an intelligent traffic control system, such as Figure 3 As shown, at the hardware level, it includes: The data interface is used to establish data communication between the processor and the image acquisition device and the traffic light controller; Memory, used to store instructions; The processor is used to read instructions stored in the memory and execute the intelligent traffic control method in Embodiment 1 according to the instructions.

[0043] Optionally, the system also includes an internal bus, through which the processor, memory, and data interface can be interconnected. This internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0044] The memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0045] Example 4: This embodiment provides a computer-readable storage medium storing instructions. When these instructions are executed on a computer, the computer performs the intelligent traffic control method described in Embodiment 1. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0046] This embodiment also provides a computer program product that, when run on a computer, executes the intelligent traffic management method in Embodiment 1. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0047] Finally, it should be noted that the above description is merely a preferred embodiment 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 within the scope of protection of the present invention.

Claims

1. An intelligent traffic control method, characterized in that, include: The traffic monitoring image sequence is obtained from the image acquisition device on one side of each direction of traffic at the intersection. The traffic monitoring image sequence contains several traffic monitoring images arranged in chronological order. The ROI of each traffic monitoring image in the traffic monitoring image sequence is extracted to obtain the target area image, and the target area image sequence is composed of the target area images. Moving target detection is performed on the target region image sequence to identify each moving target, and the image coordinates of each moving target are marked in each target region image of the target region image sequence; The motion trajectory of each moving target in the image coordinate system is determined based on the image coordinates of each moving target in the image of each target area, and the comprehensive position standard deviation parameter of all moving targets is determined based on the motion trajectory of each moving target. The single-sided congestion index for the corresponding direction of travel is calculated based on the comprehensive position standard deviation parameter of all moving targets. The comprehensive congestion index for the corresponding traffic direction is calculated using the single-sided congestion index on both sides of the corresponding traffic direction, and the green light duration for each traffic direction at the intersection is determined based on the comprehensive congestion index for each traffic direction at the intersection. Based on the green light duration for each direction of traffic at the intersection, a signal light duration adjustment command is generated and sent to the signal light controller at the intersection.

2. The intelligent traffic control method according to claim 1, characterized in that, The step of extracting the Region of Interest (ROI) from each traffic monitoring image in the traffic monitoring image sequence to obtain images of each target region includes: Image filtering and image enhancement processing are performed on each traffic monitoring image in the traffic monitoring image sequence to obtain preprocessed traffic monitoring images. Based on the set image ROI cropping location parameters, the corresponding target area image is cropped from each preprocessed traffic monitoring image.

3. The intelligent traffic control method according to claim 1, characterized in that, The step of detecting moving targets in the target region image sequence, identifying each moving target, and marking the image coordinates of each moving target in each target region image of the target region image sequence includes: Optical flow is used to detect moving targets in the target region image sequence, identify each moving target, and mark the bounding box of each moving target in each target region image of the target region image sequence; Determine the image coordinates of the center point of the bounding box of each moving target in each target region image, and use the image coordinates of the center point of the bounding box of each moving target in each target region image as the image coordinates of each moving target in each target region image.

4. The intelligent traffic control method according to claim 1, characterized in that, The determination of the comprehensive position standard deviation parameter of all moving targets based on the motion trajectory of each moving target includes: Mark each trajectory point on the trajectory of each moving target and determine the image coordinates of each trajectory point in the image coordinate system. On the trajectory of the same moving target, one trajectory point corresponds to one image of the target area. Calculate the standard deviation σ of the positions of all motion trajectory points in the image coordinate system along the x-axis. x And the standard deviation σ of the positions of all motion trajectory points in the y-axis direction. y Using the position standard deviation σ x and location standard deviation σ y The combined position standard deviation parameter that makes up all moving targets.

5. The intelligent traffic control method according to claim 4, characterized in that, The calculation of the single-sided congestion index for the corresponding traffic direction based on the comprehensive position standard deviation parameter of all moving targets includes: The comprehensive location standard deviation parameter is substituted into the preset one-sided congestion index formula for calculation to obtain the one-sided congestion index for the corresponding traffic direction. The one-sided congestion index formula is as follows: Where P is the one-sided congestion index, and R... x R is the pixel length of the target region image along the x-axis of the image coordinate system. y Let be the pixel length of the target region image along the y-axis of the image coordinate system, N be the number of moving targets, A be the pixel area of ​​the target region image, F be the number of target region images in the target region image sequence, α be the set first weight coefficient, and β be the set second weight coefficient.

6. The intelligent traffic control method according to claim 1, characterized in that, The calculation of the comprehensive congestion index for the corresponding traffic direction using the single-sided congestion indexes on both sides of the corresponding traffic direction includes: The average of the congestion indices on both sides of the corresponding traffic direction is used to obtain the comprehensive congestion index for that traffic direction.

7. The intelligent traffic control method according to claim 1, characterized in that, The determination of the green light duration for each direction of traffic at an intersection based on the comprehensive congestion index includes: The comprehensive congestion index for each direction of traffic at the intersection is substituted into a pre-set green light duration calculation model to obtain the green light duration for each direction of traffic at the intersection. The green light duration calculation model is as follows: Where i is the direction number, M is the total number of directions, and T i T represents the green light duration for traffic direction i. i-min T is the lower limit of the green light duration for the set traffic direction i. i-max P is the maximum green light duration for the set traffic direction i. i ’ The overall congestion index is for traffic direction i.

8. An intelligent traffic control system, characterized in that, It includes an image acquisition unit, an image processing unit, a target detection unit, a trajectory determination unit, an index calculation unit, a duration calculation unit, and an adjustment and control unit, wherein: The image acquisition unit is used to acquire a sequence of traffic monitoring images collected by the image acquisition device on one side of each direction of traffic at the intersection. The sequence of traffic monitoring images includes several traffic monitoring images arranged in chronological order. The image processing unit is used to extract the ROI of each traffic monitoring image in the traffic monitoring image sequence to obtain the target area image, and to use the target area images to form a target area image sequence. The target detection unit is used to detect moving targets in the target region image sequence, identify each moving target, and mark the image coordinates of each moving target in each target region image of the target region image sequence. The trajectory determination unit is used to determine the motion trajectory of each moving target in the image coordinate system based on the image coordinates of each moving target in the image of each target area, and to determine the comprehensive position standard deviation parameter of all moving targets based on the motion trajectory of each moving target. The index calculation unit is used to calculate the single-sided congestion index for the corresponding direction of travel based on the comprehensive position standard deviation parameter of all moving targets. The duration calculation unit is used to calculate the comprehensive congestion index of the corresponding traffic direction using the single-sided congestion index on both sides of the corresponding traffic direction, and to determine the green light duration of each traffic direction at the traffic intersection based on the comprehensive congestion index of each traffic direction at the traffic intersection. The adjustment control unit is used to generate traffic light duration adjustment instructions based on the green light duration for each direction of traffic at the intersection, and send the traffic light duration adjustment instructions to the traffic light controller at the intersection.

9. An intelligent traffic control system, characterized in that, include: Memory, used to store instructions; A processor is configured to read instructions stored in the memory and execute the intelligent traffic control method according to any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on a computer, it executes the intelligent traffic control method according to any one of claims 1-7.

Images