Intelligent traffic control system and method based on traffic flow prediction
By introducing an intelligent traffic control system based on traffic flow prediction into the traffic flow control system, the problem of inaccurate traffic arrangements during peak hours is solved, more precise traffic control is achieved, and traffic congestion and retention are reduced.
Patent Information
- Application Number
- CN202411974605.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-02-07
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing traffic flow control system cannot make precise traffic arrangements during peak hours, resulting in traffic jams and detention problems.
Adopt an intelligent traffic control system based on traffic flow prediction, which includes a historical unit for traffic flow prediction, a central unit for traffic control, a collection unit for road data, an analysis unit for judgment value, a control unit for road control, and a navigation unit for vehicle re-entry The navigation and processing units carry out image processing and feature calculations, and the on-site units arrange traffic management personnel to handle accidents.
Through accurate traffic flow prediction and real-time data analysis, the system can more accurately control traffic during peak periods, reduce congestion and retention, and improve the continuous flow of traffic flow.
Smart Images
Figure CN119399959A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of traffic control, and more specifically to an intelligent traffic control system and method based on traffic flow prediction. Background Art
[0002] Traffic flow refers to the flow of cars continuously driving on the road. In a broad sense, traffic flow also includes the flow of other vehicles and pedestrians. In a certain period of time, on a road section not affected by lateral crossing, traffic flow is in a continuous flow state; when encountering traffic light control at an intersection, it is in an intermittent flow state. The basic parameters of traffic flow include flow rate, speed and density, which are also called the three essentials of traffic flow.
[0003] Nowadays, the popularity of cars is gradually increasing. When traveling by car, it is greatly affected by traffic flow, especially during rush hour, when main sections of the city are prone to congestion. Therefore, it is necessary to control urban traffic through traffic flow control systems to reduce traffic congestion and detention problems. Through the macro-control of the control system, it not only promotes the continuous flow of traffic flow, but also provides more convenience for personal daily travel. However, the current traffic flow control system still has the following shortcomings;
[0004] Nowadays, when traffic control is performed through traffic flow, the traffic flow is generally calculated based on the queue length detected by the intersection sensor. However, the road conditions are very complicated. After using the traditional method to calculate the traffic flow, the calculated traffic flow has limited accuracy, and the same road section is divided into peak and trough periods at different times. Today's traffic control cannot accurately make reasonable arrangements during peak periods. Summary of the invention
[0005] In order to overcome the above-mentioned defects of the prior art, the implementation regulations of the present invention provide an intelligent traffic control system and method based on traffic flow prediction to solve the technical problems raised in the background technology.
[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent traffic control system based on traffic flow prediction, comprising a history unit, a central unit, a collection unit, an analysis unit, a control unit, a navigation unit, a processing unit, a feature unit and a field unit, wherein the history unit predicts the traffic flow of the controlled section, the central unit uses the traffic flow to perform traffic control, the collection unit collects data information of road vehicles, the analysis unit receives the data of the collection unit and calculates a judgment value P, the control unit performs road control of the controlled section, the navigation unit is used to re-navigate vehicles entering the controlled road, the processing unit receives the image data of the collection unit and performs grayscale processing and binarization processing, the feature unit calculates the proportional feature F of the binarized image, and the field unit arranges traffic management personnel to handle accidents at the controlled road site;
[0007] The historical unit uses the historical average model to predict the traffic flow of the controlled section. The algorithm formula of the historical average model is: , where V N is the predicted traffic flow of the controlled section, α is the smoothing coefficient, V J V is the traffic flow of the controlled road section in the latest hour. O is the traffic flow within one hour after the controlled road section was controlled on the previous day. The historical unit calculates the predicted traffic flow V N sent to the central unit, which uses the predicted traffic flow V N Carry out traffic control on controlled sections in advance.
[0008] In a preferred embodiment, the collection unit collects the number n of entry roads that can enter the controlled section and the number m of exit roads that can exit the controlled section, the collection unit collects the number of cars on each entry road that are within two hundred meters of the controlled section and the number of cars on each exit road that are within two hundred meters of the controlled section, counts the cars on the two-hundred-meter line between the entry road and the controlled section and the exit road, and collects the entry speed of the car when there are 50 meters left to enter the controlled section and the exit speed of the car when it is 50 meters away from the controlled section, and the analysis unit receives the data from the collection unit and calculates the judgment value P.
[0009] In a preferred embodiment, the calculation formula of the determination value P is: , where k1 and k2 are weights, i indicates that the current road is the i-th approach road, j indicates that the current road is the j-th exit road, Si indicates the number of cars within two hundred meters on the i-th approach road, Sj indicates the number of cars within two hundred meters on the j-th exit road, Vi indicates the current car approach speed of the i-th approach road, Vj indicates the current car approach speed of the j-th exit road, and the analysis unit sends the calculated judgment value P to the central unit.
[0010] In a preferred embodiment, the central unit receives the determination value P, and when the determination value P received by the central unit is zero, the central unit uses the predicted traffic flow V N When the judgment value received by the central unit is not zero, the central unit calculates the real-time traffic flow V S , real-time traffic flow V S The calculation formula is When the judgment value P received by the central unit is negative, the central unit adopts the real-time traffic flow V S When the judgment value received by the central unit is positive, the central unit calculates the real-time traffic flow V S Sent to the control unit.
[0011] In a preferred embodiment, the control unit receives the real-time traffic flow V sent by the central unit. S , and the control unit will real-time traffic flow V S Compared with its internal warning threshold Y, when the real-time traffic flow V S When the warning threshold Y is less than the warning threshold, the control unit sends a planning instruction to the navigation unit and uses the real-time traffic flow V S Carry out traffic control on the controlled road section, when real-time traffic flow V S ≥ warning threshold Y, the control unit uses real-time traffic flow V S Traffic control is performed on the controlled road section. The navigation unit receives the planning instruction and re-plans the route of the cars that have not entered the controlled road section and are 500 meters away from the controlled road section, and the planned route avoids the controlled road section.
[0012] In a preferred embodiment, the acquisition unit captures the image data information of the controlled road and sends it to the processing unit, and the processing unit grayscales the received image data information, and the grayscale processing formula is W=0.3R+0.58G+0.12B, wherein W is the grayscale value after processing, R is the red image, G is the green image, and B is the blue image, and R, G, and B are all within the grayscale value range of 0-255, and the processing unit binarizes the grayscale image data, and the binarization processing threshold is the grayscale value W1 after the controlled road surface is grayscaled, and the grayscale value W calculated by the processing unit is adjusted to 225 if the difference between the grayscale value W and the grayscale value W1 is within 10, and the grayscale value W is adjusted to 0 if the difference between the grayscale value W and the grayscale value W1 is more than 10.
[0013] In a preferred embodiment, the processing unit sends the binarized image data to the feature unit, and the feature unit receives the binarized image data and calculates the proportional feature F for the image area with continuous zeros. The calculation formula of the proportional feature F is: , where B is the perimeter of the image region with continuous zero values, and A is the area of the image region with continuous zero values.
[0014] In a preferred embodiment, a vehicle proportion feature database is provided in the feature unit, and the vehicle proportion feature database of the feature unit uses a standard proportion feature FB to calculate the existing vehicle proportion feature. The calculation formula of the standard proportion feature FB is: , where B1 is the perimeter of the vehicle contour, A1 is the area of the vehicle contour, and the feature unit matches the proportional feature F with the standard proportional feature FB. When the difference between the proportional feature F and the standard proportional feature FB is within 5%, the matching is successful, otherwise the matching fails, and the image area where the matching fails is determined to be non-vehicle.
[0015] In a preferred embodiment, the feature unit sends the image area where the proportion feature F successfully matches the standard proportion feature FB to the central unit, the central unit receives the image area sent by the feature unit and performs dynamic detection, when the central unit detects that the image area has not moved within ten minutes, the central unit marks the image area as an accident point, and the central unit sends the accident point to the on-site unit, the on-site unit receives the accident point and arranges traffic management personnel to handle it on-site.
[0016] Technical effects and advantages of the present invention:
[0017] 1. When the present invention performs traffic control on a controlled section based on traffic flow, the historical average model is first used to predict the traffic flow of the controlled section, so that preparation can be made in advance. When the control is performed, the real-time traffic flow V is finally calculated based on the car data and the bicycle data of different entering roads and different exiting roads. S More accurate, and therefore more precise, control based on the calculated traffic flow;
[0018] 2. The present invention takes into account all the entry and exit roads that can enter the controlled road, and collects the number of cars on each road and the number of cars entering and exiting. The calculated judgment value P can accurately reflect the situation of the current road section. The present invention is in a dynamic adjustment state and will be adjusted in real time according to the on-site traffic environment, and is always in a relatively accurate state;
[0019] 3. The present invention adopts different processing methods for different values of the judgment value P, which can more intelligently control the traffic on the controlled road section, collect images of the controlled road, grayscale and binarize the collected image data information, calculate the proportion feature F after binarization, match the proportion feature F with the standard proportion feature FB, and process according to the matching result to facilitate traffic control. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 It is a schematic diagram of the overall system composition of the present invention.
[0021] Figure 2 It is a schematic diagram of the traffic control method of the present invention. DETAILED DESCRIPTION
[0022] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are only examples. The intelligent traffic control system and method based on traffic flow prediction involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.
[0023] Reference Figure 1The present invention provides an intelligent traffic control system based on traffic flow prediction, including a history unit, a central unit, a collection unit, an analysis unit, a control unit, a navigation unit, a processing unit, a feature unit and a field unit, wherein the history unit predicts the traffic flow of the controlled section, the central unit uses the traffic flow to perform traffic control, the collection unit collects data information of road vehicles, the analysis unit receives the data of the collection unit and calculates a judgment value P, the control unit performs road control of the controlled section, the navigation unit is used to re-navigate vehicles entering the controlled road, the processing unit receives the image data of the collection unit and performs grayscale processing and binarization processing, the feature unit calculates the proportional feature F of the binarized image, and the field unit arranges traffic management personnel to handle accidents on the controlled road site.
[0024] In the embodiment of the present application, when the present application performs traffic control on the controlled road section based on traffic flow, the historical average model is first used to predict the traffic flow of the controlled road section, and preparation can be made in advance. When the control is performed, the real-time traffic flow V is finally calculated according to the car data and the bicycle data of different entering roads and different exiting roads. S More accurate, and therefore more precise, control based on the calculated traffic flow.
[0025] Furthermore, the historical unit uses a historical average model to predict the traffic flow of the controlled road section. The algorithm formula of the historical average model is: , where V N is the predicted traffic flow of the controlled section, α is the smoothing coefficient, V J V is the traffic flow of the controlled road section in the latest hour. O is the traffic flow within one hour after the controlled road section was controlled on the previous day. The historical unit calculates the predicted traffic flow V N sent to the central unit, which uses the predicted traffic flow V N Carry out traffic control on controlled sections in advance.
[0026] In the embodiment of the present application, a historical average model is used to predict the traffic flow of the controlled section. Therefore, when the controlled section has not reached the peak period, preparations can be made in advance, and various emergencies can be better responded to, thereby ensuring that the traffic situation of the controlled section is well resolved.
[0027] Furthermore, the collection unit collects the number n of entry roads that can enter the controlled section and the number m of exit roads that can exit the controlled section, the collection unit collects the number of cars on each entry road within two hundred meters of the controlled section and the number of cars on each exit road within two hundred meters of the controlled section, counts the cars on the two-hundred-meter line between the entry road and the controlled section and the exit road, and collects the entry speed of the car when it has 50 meters to enter the controlled section and the exit speed of the car when it leaves the controlled section at 50 meters, the analysis unit receives the data from the collection unit and calculates the judgment value P, the calculation formula of the judgment value P is: , where k1 and k2 are weights, i indicates that the current road is the i-th approach road, j indicates that the current road is the j-th exit road, Si indicates the number of cars within two hundred meters on the i-th approach road, Sj indicates the number of cars within two hundred meters on the j-th exit road, Vi indicates the current car approach speed of the i-th approach road, Vj indicates the current car approach speed of the j-th exit road, and the analysis unit sends the calculated judgment value P to the central unit.
[0028] In the embodiment of the present application, the road section that needs to be controlled has a relatively complicated road condition. Therefore, there are multiple entrances and multiple exits on the overall controlled road section. Therefore, when collecting data, the present application takes into account all the entry and exit roads that can enter the controlled roads, and collects the number of cars on each road and the number of cars entering and exiting. The calculated judgment value P can accurately reflect the situation of the current road section, avoiding the problem of inaccuracy in traditional traffic flow calculations using a single or a small number of traffic factors. The present application is in a dynamic adjustment state, and will be adjusted in real time according to the on-site traffic environment, and is always in a relatively accurate state.
[0029] Furthermore, the central unit receives the determination value P, and when the determination value P received by the central unit is zero, the central unit adopts the predicted traffic flow V N When the judgment value received by the central unit is not zero, the central unit calculates the real-time traffic flow V S , real-time traffic flow V S The calculation formula is When the judgment value P received by the central unit is negative, the central unit adopts the real-time traffic flow V S When the judgment value received by the central unit is positive, the central unit calculates the real-time traffic flow V S The control unit receives the real-time traffic flow V sent by the central unit. S , and the control unit will real-time traffic flow VS Compared with its internal warning threshold Y, when the real-time traffic flow V S When the warning threshold Y is less than the warning threshold, the control unit sends a planning instruction to the navigation unit and uses the real-time traffic flow V S Carry out traffic control on the controlled road section, when real-time traffic flow V S ≥ warning threshold Y, the control unit uses real-time traffic flow V S Traffic control is performed on the controlled road section. The navigation unit receives the planning instruction and re-plans the route of the cars that have not entered the controlled road section and are 500 meters away from the controlled road section, and the planned route avoids the controlled road section.
[0030] In the embodiment of the present application, on the basis of calculating the judgment value P accurately enough, when the judgment value P is zero, it means that the incoming vehicles and the outgoing vehicles are in a relatively balanced state at this time, so the previous predicted traffic flow V is used. N The problem can be solved by performing traffic control on the controlled road section. When the judgment value P is not zero and the judgment value P is less than zero, the number of vehicles entering is lower than that of vehicles leaving, and the controlled road is in a relatively good state. Therefore, the investment in control can be reduced. The new real-time traffic flow V S Carry out traffic control on the controlled section, and when the judgment value P is greater than zero, the new real-time traffic flow V S Traffic control on controlled roads requires more investment, and real-time traffic flow V S ≥ warning threshold Y, the controlled road section cannot accommodate more vehicles. Therefore, the cars that have not entered the controlled road section and are 500 meters away from the controlled road section will be re-routed to avoid the controlled road, reducing the number of vehicles entering and facilitating traffic restoration on the controlled road section.
[0031] Furthermore, the acquisition unit captures the image data information of the controlled road and sends it to the processing unit, and the processing unit performs grayscale processing on the received image data information. The grayscale processing formula is W=0.3R+0.58G+0.12B, where W is the grayscale value after processing, R is the red image, G is the green image, B is the blue image, and R, G, and B are all within the grayscale value range of 0-255. The processing unit performs binarization processing on the grayscale image data, and the binarization processing threshold is The grayscale value W1 after the grayscale processing of the road surface is controlled, and the grayscale value W calculated by the processing unit is adjusted to 225 if the difference between the grayscale value W and the grayscale value W1 is 10 or less, and the grayscale value W is adjusted to 0 if the difference between the grayscale value W and the grayscale value W1 is more than 10. The processing unit sends the binarized image data to the feature unit, and the feature unit receives the binarized image data and calculates the proportional feature F of the image area with continuous 0. The calculation formula of the proportional feature F is: , where B is the perimeter of the image region with continuous zero values, and A is the area of the image region with continuous zero values.
[0032] In an embodiment of the present application, after image acquisition, the acquired image is first gray-scaled. After the gray-scaled process, the surface color of the vehicle itself is different, but the surface of the road surface is a fixed color. Therefore, the gray-scaled value of the road surface after processing is at a relatively stable value. The gray-scaled value W1 of the controlled road surface after the gray-scaled process is within a range with a small variation amplitude, but the road surface will be affected by light. Therefore, when performing the binary process, the gray-scaled value W that is within 10 of the gray-scaled value W1 is adjusted to 225, and 225 is white. Therefore, the present application turns the road surface to white, and the vehicle or other objects on the road surface to 0, and turns it to black, separating the road surface from the vehicle to facilitate the detection of the vehicle. After the vehicle is separated, the image area ratio feature F that is continuously 0 is calculated to identify the vehicle.
[0033] Furthermore, a vehicle proportion feature database is provided in the feature unit, and the vehicle proportion feature database of the feature unit uses a standard proportion feature FB to calculate the existing vehicle proportion feature. The calculation formula of the standard proportion feature FB is: , where B1 is the perimeter of the vehicle contour, A1 is the area of the vehicle contour, the feature unit matches the proportional feature F with the standard proportional feature FB, when the difference between the proportional feature F and the standard proportional feature FB is within 5%, the matching is successful, otherwise the matching fails, and the image area where the matching fails is identified as a non-vehicle, the feature unit sends the image area where the proportional feature F and the standard proportional feature FB are successfully matched to the central unit, the central unit receives the image area sent by the feature unit and performs dynamic detection, when the central unit detects that the image area has not moved within ten minutes, the central unit marks the image area as an accident point, and the central unit sends the accident point to the on-site unit, the on-site unit receives the accident point and arranges traffic management personnel to the scene for processing.
[0034] In the embodiment of the present application, after calculating the proportion feature F of the vehicle, due to the complexity of the road surface, there may be other situations, such as if there is a puddle on the road surface, in which case it will also be identified as a vehicle. Therefore, the present application calculates the proportion feature F and stores the standard proportion feature FB of existing vehicles, and matches the two to exclude non-vehicles. After exclusion, if it is found that the vehicle has not moved for a long time, there is a possibility of an accident, which can be handled in a timely manner to facilitate traffic control.
[0035] Reference Figure 2 , an intelligent traffic control method based on traffic flow prediction, comprising the following steps:
[0036] Step S1, using the historical average model to predict the traffic flow of the controlled section, and using the predicted traffic flow to perform traffic control of the controlled section in advance;
[0037] Step S2, collecting data information of the input road and the exit road, and calculating the determination value P. When the determination value P is zero, continuing to use the predicted traffic flow to manage the traffic control of the road;
[0038] Step S3, when the determination value P is not zero, the real-time traffic flow is calculated, and when the determination value is negative, the real-time traffic flow is used for traffic control;
[0039] Step S4: when the determination value is a positive number, when the determination value is less than the warning threshold, the real-time traffic flow is still used for traffic control; when the determination value is greater than or equal to the warning threshold, the road planning for vehicles that have not entered the controlled road is re-performed;
[0040] Step S5, photographing image data information of the controlled road, graying and binarizing the collected image data information, and calculating the proportional feature F of the binarized image data;
[0041] Step S6: Match the scale feature F with the standard scale feature FB. When it is detected that the successfully matched image area has not moved within ten minutes, arrange traffic management personnel to the scene for processing.
[0042] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The units and algorithm steps of each example described in the embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0043] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0044] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0045] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. An intelligent traffic control system based on traffic flow prediction, characterized in that: It includes a history unit, a central unit, a collection unit, an analysis unit, a control unit, a navigation unit, a processing unit, a feature unit and a field unit, wherein the history unit predicts the traffic flow of the controlled road section, the central unit uses the traffic flow to perform traffic control, the collection unit collects data information of road vehicles, the analysis unit receives the data of the collection unit and calculates the judgment value P, the control unit performs road control of the controlled road section, the navigation unit is used to re-navigate vehicles entering the controlled road, the processing unit receives the image data of the collection unit and performs grayscale processing and binarization processing, the feature unit calculates the proportional feature F of the binarized image, and the field unit arranges traffic management personnel to handle accidents at the controlled road site; The historical unit uses the historical average model to predict the traffic flow of the controlled section. The algorithm formula of the historical average model is: , where V N is the predicted traffic flow of the controlled section, α is the smoothing coefficient, V J V is the traffic flow of the controlled road section in the latest hour. O is the traffic flow within one hour after the controlled road section was controlled on the previous day. The historical unit calculates the predicted traffic flow V N sent to the central unit, which uses the predicted traffic flow V N Carry out traffic control on controlled sections in advance.
2. The intelligent traffic control system based on traffic flow prediction according to claim 1 is characterized in that: The collection unit collects the number n of entry roads that can enter the controlled section and the number m of exit roads that can exit the controlled section, the collection unit collects the number of cars on each entry road that are within two hundred meters of the controlled section and the number of cars on each exit road that are within two hundred meters of the controlled section, counts the cars on the two-hundred-meter line between the entry road and the controlled section and the exit road, and collects the entry speed of the car when it has 50 meters left to enter the controlled section and the exit speed of the car when it is 50 meters away from the controlled section. The analysis unit receives the data from the collection unit and calculates the judgment value P.
3. The intelligent traffic control system based on traffic flow prediction according to claim 2 is characterized in that: The calculation formula of the judgment value P is: , where k1 and k2 are weights, i indicates that the current road is the i-th approach road, j indicates that the current road is the j-th exit road, Si indicates the number of cars within two hundred meters on the i-th approach road, Sj indicates the number of cars within two hundred meters on the j-th exit road, Vi indicates the current car approach speed of the i-th approach road, Vj indicates the current car approach speed of the j-th exit road, and the analysis unit sends the calculated judgment value P to the central unit.
4. The intelligent traffic control system based on traffic flow prediction according to claim 3 is characterized in that: The central unit receives the determination value P, and when the determination value P received by the central unit is zero, the central unit adopts the predicted traffic flow V N When the judgment value received by the central unit is not zero, the central unit calculates the real-time traffic flow V S , real-time traffic flow V S The calculation formula is When the judgment value P received by the central unit is negative, the central unit adopts the real-time traffic flow V S When the judgment value received by the central unit is positive, the central unit calculates the real-time traffic flow V S Sent to the control unit.
5. The intelligent traffic control system based on traffic flow prediction according to claim 4 is characterized in that: The control unit receives the real-time traffic flow V sent by the central unit. S , and the control unit will real-time traffic flow V S Compared with its internal warning threshold Y, when the real-time traffic flow V S When the warning threshold Y is less than the warning threshold, the control unit sends a planning instruction to the navigation unit and uses the real-time traffic flow V S Carry out traffic control on the controlled road section, when real-time traffic flow V S ≥ warning threshold Y, the control unit uses real-time traffic flow V S Traffic control is performed on the controlled road section. The navigation unit receives the planning instruction and re-plans the route of the cars that have not entered the controlled road section and are 500 meters away from the controlled road section, and the planned route avoids the controlled road section.
6. The intelligent traffic control system based on traffic flow prediction according to claim 1 is characterized in that: The acquisition unit captures the image data information of the controlled road and sends it to the processing unit, and the processing unit performs grayscale processing on the received image data information. The grayscale processing formula is W=0.3R+0.58G+0.12B, wherein W is the grayscale value after processing, R is the red image, G is the green image, and B is the blue image, and R, G, and B are all within the grayscale value range of 0-255. The processing unit performs binarization processing on the grayscale image data, and the binarization processing threshold is the grayscale value W1 after the grayscale processing of the controlled road surface, and the grayscale value W calculated by the processing unit is adjusted to 225 if the difference between the grayscale value W and the grayscale value W1 is 10 or less, and the grayscale value W is adjusted to 0 if the difference between the grayscale value W and the grayscale value W1 is more than 10.
7. The intelligent traffic control system based on traffic flow prediction according to claim 6 is characterized by: The processing unit sends the binarized image data to the feature unit, and the feature unit receives the binarized image data and calculates the proportional feature F for the image area with continuous zeros. The calculation formula of the proportional feature F is: , where B is the perimeter of the image region with continuous zero values, and A is the area of the image region with continuous zero values.
8. The intelligent traffic control system based on traffic flow prediction according to claim 7 is characterized in that: The feature unit is provided with a vehicle proportion feature database, and the vehicle proportion feature database of the feature unit uses a standard proportion feature FB to calculate the existing vehicle proportion feature. The calculation formula of the standard proportion feature FB is: , where B1 is the perimeter of the vehicle contour, A1 is the area of the vehicle contour, and the feature unit matches the proportional feature F with the standard proportional feature FB. When the difference between the proportional feature F and the standard proportional feature FB is within 5%, the matching is successful, otherwise the matching fails, and the image area where the matching fails is determined to be non-vehicle.
9. The intelligent traffic control system based on traffic flow prediction according to claim 8 is characterized in that: The feature unit sends the image area where the scale feature F successfully matches the standard scale feature FB to the central unit, and the central unit receives the image area sent by the feature unit and performs dynamic detection. When the central unit detects that the image area has not moved within ten minutes, the central unit marks the image area as an accident point, and the central unit sends the accident point to the on-site unit. The on-site unit receives the accident point and arranges traffic management personnel to handle it on-site.
10. An intelligent traffic control method based on traffic flow prediction, using an intelligent traffic control system based on traffic flow prediction as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step S1: Use the historical average model to predict the traffic flow of the controlled section, and use the predicted traffic flow to perform traffic control on the controlled section in advance; Step S2, collecting data information of the input road and the exit road, and calculating the determination value P. When the determination value P is zero, continuing to use the predicted traffic flow to manage the traffic control of the road; Step S3, when the determination value P is not zero, the real-time traffic flow is calculated, and when the determination value is negative, the real-time traffic flow is used for traffic control; Step S4: when the determination value is a positive number, when the determination value is less than the warning threshold, the real-time traffic flow is still used for traffic control; when the determination value is greater than or equal to the warning threshold, the road planning for vehicles that have not entered the controlled road is re-performed; Step S5, photographing image data information of the controlled road, graying and binarizing the collected image data information, and calculating the proportional feature F of the binarized image data; Step S6: Match the scale feature F with the standard scale feature FB. When it is detected that the successfully matched image area has not moved within ten minutes, arrange traffic management personnel to the scene for processing.