A traffic monitoring system based on machine vision

Abstract

The present invention relates to the technical field of traffic management, and specifically discloses a traffic monitoring system based on machine vision, including: a zoning module: determining target buildings within a preset monitoring area and determining an initial area according to the locations of the target buildings; a processing module: determining the vehicle density within the initial area, determining a congestion radius according to the vehicle density; determining a theoretical center according to the locations of the vehicles within the congestion radius, and correcting the congestion radius according to the theoretical center to obtain a standard radius; drawing a curve of the change of the standard radius over time, calculating a target radius and determining a target area; a prompting module: determining the intersection with the shortest distance to the boundary of the target area on a pending route, and sending a warning message when the vehicle reaches the intersection. The present invention can prompt the driving route of the vehicle according to the vehicle density, and avoid noise pollution caused by too high vehicle density.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and particularly relates to a traffic monitoring system based on machine vision. Background Art

[0002] Machine vision is a technology that enables a computer or machine to have the ability of "vision". It aims to simulate the functions of the human visual system through image processing, pattern recognition, and data analysis to perceive, understand, and analyze image or video content. Its core principle is to convert image data into digital signals that can be processed, and process them through software and algorithms to identify the features and patterns therein.

[0003] Noise refers to the sound emitted when a sounding body vibrates irregularly. Sound is generated by the vibration of an object and propagates in a certain medium (such as a solid, liquid, or gas) in the form of waves. Usually, the so-called noise pollution is caused by humans. From a physiological perspective, any sound that interferes with people's rest, study, and work and the sound you want to hear, that is, the unwanted sound, is collectively called noise. When noise has an adverse impact on people and the surrounding environment, it forms noise pollution.

[0004] When a vehicle is in motion, it usually makes noise, which mainly comes from multiple factors such as the engine, exhaust system, friction between the wheels and the road surface, and aerodynamics. In areas with heavy traffic flow, the noise generated by vehicles is likely to accumulate and form noise pollution, bringing troubles to the lives and work of residents. Summary of the Invention

[0005] The purpose of the present invention is to provide a traffic monitoring system based on machine vision to solve the following technical problems:

[0006] When a vehicle is in motion, it usually makes noise, which mainly comes from multiple factors such as the engine, exhaust system, friction between the wheels and the road surface, and aerodynamics. In areas with heavy traffic flow, the noise generated by vehicles is likely to accumulate and form noise pollution, bringing troubles to the lives and work of residents.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A traffic monitoring system based on machine vision, comprising:

[0009] A zoning module: setting a monitoring area, determining the target buildings within the monitoring area, where the target buildings include but are not limited to schools, hospitals, and residential communities, and taking the location of the target building as the center and a preset radius r to draw a circle to obtain an initial area;

[0010] Processing module: Obtain the position information of vehicles in the monitored area, determine the vehicle density P in the initial area, set the vehicle density threshold Pys. When the vehicle density P ≥ Pys, let the radius r = r + Δr and re-determine the initial area, where Δr is a preset radius adjustment value. Repeat the above steps until the vehicle density P < Pys after a certain radius adjustment. Mark the radius at this time as the congestion radius R;

[0011] Determine the initial area A corresponding to the congestion radius R, determine the theoretical center G according to the positions of the vehicles in the initial area A, where the theoretical center is the average distribution center of the vehicles. Correct the congestion radius according to the distance between the location of the target building and the theoretical center G to obtain the standard radius;

[0012] Periodically obtain the standard radius and draw the curve f(t) of the standard radius changing with time, where t ∈ [Tcur - n*ΔT, Tcur], Tcur represents the current time, ΔT is a preset time interval, and n is a preset number. Calculate the target radius Rgoa = f(Tcur + ΔT), and draw a circle with the location of the target building as the center and the target radius Rgoa to obtain the target area;

[0013] Prompt module: Take the routes in the monitored area that have intersections with the boundary of the target area as the pending routes, determine the fork B on the pending route that is closest to the boundary of the target area, and send a warning message to prompt the vehicle when the vehicle reaches the fork B.

[0014] As a further solution of the present invention: In the processing module, the process of correcting the congestion radius to obtain the standard radius specifically includes:

[0015] Determine the position coordinates Wi(Xi, Yi) of the i-th vehicle in the initial area A, where Xi and Yi are the abscissa and ordinate of the i-th vehicle respectively, and determine the theoretical center G(Xthe, Ythe), where N represents the total number of vehicles in the initial area A;

[0016] Determine the distance D between the theoretical center G and the location of the target building, and calculate the standard radius RBZ = R - ε*D, where ε is a preset correction coefficient.

[0017] As a further solution of the present invention: In the processing module, during the process of determining the congestion radius, the following steps are further included:

[0018] Set a maximum radius \(r_{max}\). During the process of adjusting the radius \(r\), if when the radius \(r = r_{max}\), the corresponding vehicle density is still greater than or equal to the vehicle density threshold \(P_{ys}\), send a warning message to prompt the management staff, and execute a preset reduction step to determine the congestion radius.

[0019] As a further solution of the present invention: The reduction step specifically includes:

[0020] Let the radius \(r = r-\Delta r\) and re - determine the initial area until the radius \(r\lt r_{min}\), where \(r_{min}\) represents a preset minimum radius. Determine the density value \(H_j\). When the vehicle density \(P\geq P_{ys}\) after the \(j\) - th adjustment of the radius, \(H_j = 1\); when the vehicle density \(P\lt P_{ys}\) after the \(j\) - th adjustment of the radius, \(H_j = 0\).

[0021] Sort the density values in the order of the time axis. Starting from the first in the sorting, determine the sorting position \(c\) where the last density value of 1 is located in the sorting. Determine the target position \(c'\). Use the radius corresponding to the target position \(c'\) as the congestion radius, and the target position \(c'\) satisfies the constraint: the density values in the sorting position interval \([c', c]\) are all 1.

[0022] Among them, when there is no density value of 1 in the sorting, mark it as the unobstructed state, and let the congestion radius be 0 at this time.

[0023] As a further solution of the present invention: In the processing module, when the vehicle density \(P\lt P_{ys}\) in the initial area, execute the reduction step to determine the congestion radius.

[0024] As a further solution of the present invention: When there is no sorting position that satisfies the constraint condition, use the radius corresponding to the sorting position \(c\) as the congestion radius.

[0025] As a further solution of the present invention: In the processing module, the process of determining the vehicle density \(P\) specifically includes:

[0026] \(P=a / (\pi r\) 2 ), where \(a\) represents the total number of vehicles in the initial area.

[0027] As a further solution of the present invention: In the processing module, obtain the position information of the vehicle based on the target detection algorithm.

[0028] Advantages of the present invention: In the present invention, the target building within the monitoring area is first determined, and the initial area is determined according to the location of the target building; the target buildings (such as schools, hospitals, residential communities, etc.) are sensitive to noise pollution because noise will directly affect people's health, learning efficiency, rest quality, etc. The initial area is to define a potential noise interference range and provide a basis for subsequent analysis that can be dynamically adjusted. The radius r of this initial range is not a fixed value but a reference value. This preset initial area is mainly to provide a basis for subsequent detection and dynamic adjustment of vehicle density. Based on the spatial correlation between vehicle distribution and noise sources, fixing the initial area can help simplify the analysis and reduce the monitoring workload; Pys (density threshold) is set as a scale to distinguish whether the noise impact exceeds the area's tolerance range. When the vehicle density exceeds Pys, it indicates that the noise pollution may reach or exceed the acceptance limit of the building area. In this case, the radius r is expanded and the monitoring continues to enable the area to contain more vehicles and better analyze the overall density. Thus, by dynamically adjusting the monitoring range, it effectively ensures real-time adjustment of the noise monitoring of the building; after calculating the theoretical center of the vehicles, the distance D from the target building to the theoretical center is used as a correction factor for measuring the noise impact range because when the center of gravity of the vehicle distribution is close to the target building, the noise impact is greater; conversely, when the theoretical center is relatively far from the target building, the noise intensity will attenuate due to distance. This correction helps to avoid ineffective monitoring. When the vehicle distribution is far from the target building but dense, this distribution has a relatively small impact on the building's noise; then, the target radius is obtained based on the historical change trend of the standard radius and the target area is determined, that is, the standard radius at the predicted time Tcur + ΔT. Substituting the time Tcur + ΔT into the curve f(t) can achieve this; this prediction method can help managers formulate practical prevention and control measures in advance and avoid unreasonable prevention and control situations through dynamic adjustment of prevention and control measures; finally, the fork in the road closest to the boundary of the target area on the undetermined route is determined, and a warning message is sent when the vehicle reaches this fork in the road; doing so can prompt the vehicle when it is approaching the noise-sensitive area, enabling the vehicle to adjust its driving strategy in advance, thereby effectively reducing the risk of noise spreading to the target area. The present invention can prompt the driving route of the vehicle according to the vehicle density and avoid noise pollution caused by too high vehicle density. Description of the Drawings

[0029] The present invention will be further described below with reference to the drawings.

[0030] Figure 1 It is a flowchart of a traffic monitoring system based on machine vision according to the present invention. Detailed Embodiments

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 As shown, the present invention is a traffic monitoring system based on machine vision, comprising:

[0033] Partitioning module: set the monitoring area, determine the target building in the monitoring area, the target building includes but is not limited to schools, hospitals and residential areas, and draw a circle with the location of the target building as the center and a preset radius r to obtain the initial area;

[0034] Processing module: obtain the location information of the vehicles in the monitoring area, determine the vehicle density P in the initial area, set the vehicle density threshold Pys, and when the vehicle density P≥Pys, set the radius r=r+Δr and redetermine the initial area, Δr is the preset radius adjustment value, repeat the above steps until the vehicle density P<Pys after a certain radius adjustment, and mark the radius at this time as the congestion radius R;

[0035] Determine an initial area A corresponding to the congestion radius R, determine a theoretical center G according to the positions of vehicles in the initial area A, the theoretical center is the average distribution center of vehicles, and correct the congestion radius according to the distance between the position of the target building and the theoretical center G to obtain a standard radius;

[0036] The standard radius is periodically obtained and a curve f(t) of the standard radius changing with time is drawn, t∈[Tcur-n*ΔT, Tcur], Tcur represents the current time, ΔT is a preset time interval, n is a preset number, and the target radius Rgoa=f(Tcur+ΔT) is calculated. A circle is drawn with the target building location as the center and the target radius Rgoa to obtain the target area;

[0037] Prompt module: take the route with intersection between the boundary of the monitoring area and the target area as the pending route, determine the fork B on the pending route that is closest to the boundary of the target area, and send warning information to the vehicle when the vehicle arrives at the fork B.

[0038] It should be noted that the target building within the monitoring area is first determined, and the initial area is determined according to the location of the target building. Target buildings (such as schools, hospitals, residential communities, etc.) are sensitive to noise pollution because noise can directly affect people's health, learning efficiency, rest quality, etc. The initial area is to define a potential noise interference range and provide a basis for subsequent analysis that can be dynamically adjusted. The radius r of this preset initial area is not a fixed value but a reference value. This preset initial area mainly provides a basis for subsequent detection and dynamic adjustment of vehicle density. Based on the spatial correlation between vehicle distribution and noise sources, fixing the initial area can help simplify the analysis and reduce the monitoring workload. Pys (density threshold) is set as a scale to distinguish whether the noise impact exceeds the area's tolerance range. When the vehicle density exceeds Pys, it indicates that the noise pollution may reach or exceed the acceptable limit of the building area. In this case, the radius r is expanded and continuous monitoring is carried out to enable the area to include more vehicles and better analyze the overall density. In this way, by dynamically adjusting the monitoring range, the real-time adjustment of noise monitoring for buildings is effectively ensured. After calculating the theoretical center of the vehicles, the distance D from the target building to the theoretical center is used as a correction factor for measuring the noise impact range because when the center of gravity of the vehicle distribution is close to the target building, the noise impact is greater; conversely, when the theoretical center is relatively far from the target building, the noise intensity will attenuate due to the distance. This correction helps to avoid ineffective monitoring. When the vehicle distribution is far from the target building but dense, this distribution has a relatively small impact on the noise of the building. Then, the target radius is obtained based on the historical change trend of the standard radius and the target area is determined, that is, the standard radius at the predicted time Tcur + ΔT. Substituting the time Tcur + ΔT into the curve f(t) can achieve this. This prediction method can help managers formulate practical prevention and control measures in advance and avoid unreasonable prevention and control situations by dynamically adjusting the prevention and control measures. Finally, the fork in the road with the shortest distance to the boundary of the target area on the undetermined route is determined, and a warning message is sent when the vehicle reaches this fork in the road. This can prompt the vehicle when it is approaching the noise-sensitive area, enabling the vehicle to adjust its driving strategy in advance, thereby effectively reducing the risk of noise spreading to the target area.

[0039] In another preferred embodiment of the present invention, in the processing module, the process of correcting the congestion radius to obtain the standard radius specifically includes:

[0040] Determine the position coordinates Wi(Xi, Yi) of the i-th vehicle in the initial area A, where Xi and Yi are the abscissa and ordinate of the i-th vehicle respectively, and determine the theoretical center G(Xthe, Ythe), where N represents the total number of vehicles in the initial area A;

[0041] Determine the distance D between the theoretical center G and the location of the target building, and calculate the standard radius RBZ = R - ε * D, where ε is a preset correction coefficient.

[0042] It is worth noting that the core purpose of this process is to ensure that the noise monitoring range more accurately reflects the impact of actual noise on the target building. The initial "crowding radius" is based on vehicle density, but does not fully consider the specific distribution of vehicles and the actual distance between the noise source and the building. This correction enables the system to dynamically adjust the monitoring range to adapt to different vehicle distribution situations, thereby reducing the unnecessary monitoring burden; the standard radius RBZ obtained through correction is an optimization of the initial noise radius, making the monitoring results more accurate and effective, and reducing the inefficient judgment of the noise impact on the target building.

[0043] In another preferred embodiment of the present invention, in the processing module, during the process of determining the crowding radius, the following steps are further included:

[0044] Set the maximum radius rmax. During the process of adjusting the radius r, if the radius r = rmax and the corresponding vehicle density is still greater than or equal to the vehicle density threshold Pys, send a warning message to prompt the management staff, and execute a preset reduction step to determine the crowding radius.

[0045] It can be understood that setting the maximum radius rmax can prevent the monitoring area from expanding excessively. When the radius reaches rmax, if the vehicle density is still higher than the threshold Pys, this indicates that the vehicles in the area are very dense and the noise has exceeded the management limit. At this time, the system sends a warning message to notify the management staff to take additional measures, such as diversion or traffic restrictions, to alleviate the noise pollution.

[0046] In another preferred embodiment of the present invention, the reduction step specifically includes:

[0047] Let the radius r = r - Δr and re - determine the initial area until the radius r < rmin, where rmin represents the preset minimum radius. Determine the density value Hj. When the vehicle density P corresponding to the j - th adjustment of the radius is ≥ Pys, Hj = 1; when the vehicle density P corresponding to the j - th adjustment of the radius is < Pys, Hj = 0;

[0048] Sort the density values in the order of the time axis. Starting from the first in the sorting, determine the sorting position c of the last density value of 1 in the sorting, determine the target position c'. Use the radius corresponding to the target position c' as the crowding radius, and the target position c' satisfies the constraint: the density values in the sorting position interval [c', c] are all 1;

[0049] Among them, when there is no density value of 1 in the sorting, it is marked as the unobstructed state, and let the crowding radius be 0 at this time.

[0050] It should be noted that the density values in the sorting position interval [c', c] are all 1, in order to ensure that the setting of the current monitoring radius can cover a continuously high-density area, rather than a single-point density (that is, it is not suddenly detected a high-density value when adjusting the radius). By finding this stable area at the current time, the system can determine the most appropriate congestion radius; that is, when adjusting the monitoring radius in a vehicle-dense area, it can determine the effective monitoring range according to the high-density values in adjacent intervals (rather than a single high value detected by accident), which helps to avoid over-expanding or shrinking the monitoring area.

[0051] In another preferred embodiment of the present invention, in the processing module, when the vehicle density P in the initial area < Pys, the reduction step is executed to determine the congestion radius.

[0052] In another preferred embodiment of the present invention, when there is no sorting position that satisfies the constraint condition, the radius corresponding to the sorting position c is used as the congestion radius.

[0053] In another preferred embodiment of the present invention, in the processing module, the process of determining the vehicle density P specifically includes:

[0054] P = a / (πr 2 ), where a represents the total number of vehicles in the initial area.

[0055] In another preferred embodiment of the present invention, in the processing module, the position information of the vehicle is obtained based on the object detection algorithm.

[0056] It is worth noting that the object detection algorithm can identify and locate each vehicle in the monitoring area in real time and accurately. By obtaining the position information of the vehicle in this way, the distribution of the vehicles can be intuitively understood, which is convenient for monitoring the density and the spatial distribution characteristics of the noise source; the object detection algorithm, especially modern deep learning algorithms, such as YOLO, Faster R-CNN, etc., can identify vehicles in complex environments and even locate the vehicle positions in case of congestion or fast movement.

[0057] The above has described in detail an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A traffic monitoring system based on machine vision, characterized in that: include: Partitioning module: set the monitoring area, determine the target building in the monitoring area, the target building includes but is not limited to schools, hospitals and residential areas, and draw a circle with the location of the target building as the center and a preset radius r to obtain the initial area; Processing module: obtain the location information of the vehicles in the monitoring area, determine the vehicle density P in the initial area, set the vehicle density threshold Pys, and when the vehicle density P≥Pys, set the radius r=r+Δr and redetermine the initial area, Δr is the preset radius adjustment value, repeat the above steps until the vehicle density P<Pys after a certain radius adjustment, and mark the radius at this time as the congestion radius R; Determine an initial area A corresponding to the congestion radius R, determine a theoretical center G according to the positions of vehicles in the initial area A, the theoretical center is the average distribution center of vehicles, and correct the congestion radius according to the distance between the position of the target building and the theoretical center G to obtain a standard radius; Periodically obtain the standard radius and draw a curve f(t) of the standard radius changing with time. , Tcur represents the current time, ΔT is the preset time interval, n is the preset number, calculate the target radius , a circle is drawn with the location of the target building as the center and the target radius Rgoa to obtain the target area; Prompt module: taking a route having an intersection with the boundary of the target area in the monitoring area as a pending route, determining a fork in the road B which is closest to the boundary of the target area on the pending route, and sending a warning message to the vehicle when the vehicle arrives at the fork in the road B; The process of correcting the congestion radius to obtain the standard radius specifically includes: determining the position coordinates W of the i-th vehicle in the initial area A i (X i , Y i ), X i and Y i are the horizontal and vertical coordinates of the i-th vehicle, respectively, to determine the theoretical center G (X the , Y the ),in , N represents the total number of vehicles in the initial area A; Determine the distance D between the theoretical center G and the location of the target building, and calculate the standard radius , is the preset correction factor.

2. A machine vision-based traffic monitoring system according to claim 1, characterized in that: In the processing module, the process of determining the crowding radius further includes the following steps: Set the maximum radius r max , in the process of adjusting the radius r, if the radius r=r max When the corresponding vehicle density is still greater than or equal to the vehicle density threshold Pys, an early warning message is sent to the management personnel, and the preset reduction steps are executed to determine the congestion radius.

3. A machine vision-based traffic monitoring system according to claim 2, characterized in that: The reduction steps specifically include: Let the radius r = r-Δr and redefine the initial area until the radius r < r min , r min Indicates the preset minimum radius and determines the density value H j , when the vehicle density P ≥ Pys after the jth radius adjustment, H j =1; when the vehicle density P < Pys after the jth radius adjustment, H j =0; Sort the density values ​​in the order of the time axis, starting from the first position in the sorting, determine the sorting position c where the last density value of 1 is located in the sorting, determine the target position c', and use the radius corresponding to the target position c' as the crowding radius. The target position c' satisfies the constraint that the density values ​​in the sorting position interval [c', c] are all 1; Among them, when there is no density value of 1 in the sorting, it is marked as a smooth state, and the congestion radius at this time is set to 0.

4. A machine vision-based traffic monitoring system according to claim 3, characterized in that: In the processing module, when the vehicle density P in the initial area is less than Pys, the reduction step is executed to determine the congestion radius.

5. The machine vision-based traffic monitoring system according to claim 3, characterized in that: When there is no sorting position that satisfies the constraint conditions, the radius corresponding to the sorting position c is used as the congestion radius.

6. A machine vision-based traffic monitoring system according to claim 1, characterized in that: In the processing module, the process of determining the vehicle density P specifically includes: , a represents the total number of vehicles in the initial area.

7. The machine vision-based traffic monitoring system according to claim 1, characterized in that: In the processing module, the position information of the vehicle is obtained based on the target detection algorithm.

Images