A smart multi-lane detection system

Abstract

The present invention relates to the field of lane detection, and discloses an intelligent multi-lane detection system, comprising: a data acquisition module, which collects lane traffic data in real time by arranging multiple groups of detectors at intervals on multiple lanes of a current road section; a lane data processing module, which is used to process the collected lane traffic data, including data cleaning and feature extraction; a lane data analysis module, which is used to analyze the processed lane traffic data, calculate and obtain a subjective lane occupancy coefficient and an objective lane occupancy coefficient, and obtain a lane coefficient after processing the subjective lane occupancy coefficient and the objective lane occupancy coefficient according to a preset rule; compare the lane coefficient with a lane coefficient threshold, if the lane coefficient is greater than the lane coefficient threshold, it is judged that the road condition of the current road section is poor, otherwise, it is judged that the road condition of the current road section is good; a traffic road condition warning module, which generates warning information according to the judgment result of the lane data analysis module and sends it through wireless communication technology.

Description

Technical Field

[0001] The present invention relates to the field of lane detection, and in particular to an intelligent multi-lane detection system. Background Art

[0002] In the field of traffic control and management, with the continuous advancement of technology, the requirements for the intelligence, automation and real-time performance of traffic systems are increasing. The intelligent multi-lane detection system aims to improve road traffic efficiency, reduce traffic congestion and enhance traffic safety.

[0003] At present, although some intelligent transportation systems have achieved the collection and analysis of traffic data to a certain extent, they still have limitations in comprehensive monitoring of multi-lane traffic conditions, real-time data analysis, and decision support. For example, many systems are limited to monitoring a single lane; in addition, some systems lack efficiency and accuracy in data processing and analysis, resulting in insufficient basis for traffic management decisions.

[0004] In response to these challenges, the present invention proposes an intelligent multi-lane detection system. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent multi-lane detection system to solve the above technical problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An intelligent multi-lane detection system, comprising:

[0008] The data collection module collects lane traffic data in real time by arranging multiple sets of detectors at intervals on multiple lanes of the current road section;

[0009] Lane data processing module, used to process the collected lane traffic data, including data cleaning and feature extraction;

[0010] A lane data analysis module is used to analyze the processed lane traffic data, calculate the subjective lane occupancy coefficient and the objective lane occupancy coefficient, and obtain the lane coefficient after processing the subjective lane occupancy coefficient and the objective lane occupancy coefficient according to a preset rule;

[0011] The lane coefficient is compared with the lane coefficient threshold. If the lane coefficient is greater than the lane coefficient threshold, the road condition of the current road section is judged to be bad. Otherwise, the road condition of the current road section is judged to be good.

[0012] The traffic condition warning module generates warning information based on the judgment results of the lane data analysis module and sends it through wireless communication technology.

[0013] As a further solution, the detector includes a camera, a sensor and a radar. The camera is used to capture vehicle images to identify the vehicle type and license plate number; the radar and the sensor are used to monitor the vehicle speed, the number of vehicles on the lane, and the distance between vehicles in real time.

[0014] As a further solution, the process of calculating and obtaining the objective lane occupancy coefficient is:

[0015] Obtain information on whether an accident has occurred on multiple lanes on the current road section;

[0016] If an accident occurs, obtain the number of vehicles involved in the current accident , the length of time the lane is occupied after the accident , Number of occupied lanes And the corresponding length , substitute into the formula: Calculate the accident impact coefficient If no accident occurs, ;

[0017] The accident impact coefficient Substituting into the formula: Calculate the objective lane occupancy coefficient ;

[0018] In the formula is the number of lanes in the current road section, For the Lanes, is the number of vehicles on the current lane, is the maximum number of vehicles that the current lane can accommodate, is the average speed of vehicles in the current lane, is the designed maximum speed of the current lane, is the average distance between the front and rear vehicles in the current lane.

[0019] As a further solution, the process of calculating and obtaining the subjective lane occupancy coefficient is:

[0020] By formula:

[0021] Calculate the subjective lane occupancy coefficient ;

[0022] In the formula is the total number of detection sub-periods divided into a detection cycle, are the starting point and end point of a detection sub-period, respectively. is the weight coefficient corresponding to each detection sub-period, is the judgment function about the number of vehicles changing lanes illegally, is the curve of the average speed of vehicles on the current road section changing with time. is the reference curve, About time 's points.

[0023] As a further solution, the The expression is: ; In the formula is the impact factor, is the number of vehicles that change lanes illegally in each detection sub-period, The total number of vehicles entering the current road section in each detection sub-period.

[0024] As a further solution, the process of identifying vehicles that change lanes illegally on the current road section is as follows:

[0025] Obtain the number of vehicles entering the entrance of the current road section in each detection sub-period, and then draw the driving trajectory of each vehicle on multiple lanes on the current road section, using the boundaries on both sides of each lane as steps;

[0026] Identify the number of intersections between each vehicle and lane boundaries and the number of lanes traveled ;

[0027] By formula: Calculate the lane change coefficient of the current vehicle ;

[0028] Will Compared with the preset lane change warning value For comparison, if , it is judged that the current vehicle has illegal lane changing behavior, otherwise it is judged that the current vehicle has no illegal lane changing behavior.

[0029] As a further solution, the processing rule of the lane coefficient is:

[0030] Substitute the calculated objective lane occupancy coefficient and subjective lane occupancy coefficient into the following formula:

[0031] Calculate the lane coefficient ;

[0032] In the formula, , is the preset scale factor, For the The subjective lane occupancy coefficient of each lane, , is the exponential coefficient;

[0033] Will , The corresponding warning values , Make a comparison;

[0034] like ,but ,otherwise ;

[0035] like ,but ,otherwise .

[0036] As a further solution, the process of generating warning information based on the judgment result of the lane data analysis module is as follows:

[0037] like , an emergency warning of the current road condition is generated;

[0038] like ,but , then an accident warning for the current road section is generated; or , then a violation warning for the current road section is generated;

[0039] like and and , no traffic warning for the current road section will be generated.

[0040] Beneficial effects of the present invention:

[0041] (1) The present invention makes the judgment of road conditions more accurate by comprehensively considering multiple factors. At the same time, due to the real-time nature of data collection and processing, the system can quickly respond to changes in traffic conditions and provide timely road condition information. By judging the relationship between the lane coefficient and the lane coefficient threshold, it can automatically distinguish whether the road condition of the current section is good or bad. This judgment result not only provides an objective and scientific basis for decision-making for traffic management departments, but also helps them better allocate traffic resources, such as adjusting the timing of traffic lights, issuing traffic guidance information, etc., thereby optimizing traffic flow and alleviating traffic congestion.

[0042] (2) By real-time monitoring and analysis of traffic data, the present invention enables the system to promptly detect potential traffic safety hazards, such as vehicle accidents, congestion, and illegal driving, so as to take measures to intervene in advance, thereby helping to reduce the incidence of secondary traffic accidents and protect people's lives and property. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below in conjunction with the accompanying drawings.

[0044] Figure 1 It is a system structure block diagram of the present invention. DETAILED DESCRIPTION

[0045] 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.

[0046] See also Figure 1 As shown, the present invention is a smart multi-lane detection system, comprising:

[0047] The data collection module collects lane traffic data in real time by arranging multiple sets of detectors at intervals on multiple lanes of the current road section;

[0048] The lane data processing module is used to process the collected lane traffic data, including data cleaning and feature extraction. This module uses mature data processing tools and methods in the prior art, which will not be elaborated here.

[0049] A lane data analysis module is used to analyze the processed lane traffic data, calculate the subjective lane occupancy coefficient and the objective lane occupancy coefficient, and obtain the lane coefficient after processing the subjective lane occupancy coefficient and the objective lane occupancy coefficient according to a preset rule;

[0050] The lane coefficient is compared with the lane coefficient threshold. If the lane coefficient is greater than the lane coefficient threshold, the road condition of the current road section is judged to be bad. Otherwise, the road condition of the current road section is judged to be good.

[0051] The traffic condition warning module generates warning information based on the judgment results of the lane data analysis module and sends it through wireless communication technology. The detector includes a camera, a sensor and a radar. The camera is used to capture vehicle images to identify vehicle types and license plates; the radar and sensor are used to monitor vehicle speed, the number of vehicles on the lane, and the distance between vehicles in real time.

[0052] In order to solve the technical problems raised in the background technology, the present invention first collects lane traffic data in real time through a data acquisition module, and then analyzes it after processing. It analyzes whether the multi-lane driving process is caused by the subjective illegal lane change of the vehicle or the objective large traffic volume and slow driving speed of the vehicle, and calculates the subjective lane occupancy coefficient and the objective lane occupancy coefficient respectively according to the above classification. The method of comprehensively considering multiple factors makes the road condition judgment more accurate. At the same time, due to the real-time nature of data collection and processing, the system can quickly respond to changes in traffic conditions and provide timely road condition information;

[0053] The subjective lane occupancy coefficient and the objective lane occupancy coefficient are then processed to obtain the lane coefficient. By judging the relationship between the lane coefficient and the lane coefficient threshold, it is possible to automatically distinguish whether the road condition of the current section is good or bad. This judgment result not only provides an objective and scientific basis for decision-making for traffic management departments, but also helps them better allocate traffic resources, such as adjusting the timing of traffic lights, issuing traffic guidance information, etc., so as to optimize traffic flow and alleviate traffic congestion. The above technical solution monitors and analyzes traffic data in real time, and the system can promptly detect potential traffic safety hazards, such as vehicle accident congestion and illegal driving, so as to take measures to intervene in advance, which helps to reduce the incidence of secondary traffic accidents and protect people's lives and property.

[0054] The process of calculating and obtaining the objective lane occupancy coefficient is as follows:

[0055] Obtain information on whether an accident has occurred on multiple lanes on the current road section;

[0056] If an accident occurs, obtain the number of vehicles involved in the current accident , the length of time the lane is occupied after the accident , Number of occupied lanes And the corresponding length , substitute into the formula: Calculate the accident impact coefficient If no accident occurs, ; For the The length of the lane occupied by the accident vehicle, is the reference time of occupying the lane after an accident. To set the coefficient, it is formulated based on historical data and experimental data;

[0057] The accident impact coefficient Substituting into the formula: Calculate the objective lane occupancy coefficient ;

[0058] In the formula is the number of lanes in the current road section, For the Lanes, is the number of vehicles on the current lane, is the maximum number of vehicles that the current lane can accommodate, is the average speed of vehicles in the current lane, is the designed maximum speed of the current lane, is the average distance between the front and rear vehicles in the current lane.

[0059] The present invention provides a method for calculating and obtaining the objective lane occupancy coefficient. The objective lane occupancy is mainly divided into two situations: traffic congestion and accident congestion. Therefore, relevant lane traffic parameters are selected and substituted into the formula ,in ; It can be seen from the above formula that the greater the number of vehicles in the current lane detected in real time, that is, the greater the lane flow, the greater the traffic pressure, and the lower the average speed of vehicles in the current lane, the greater the traffic pressure and the higher the probability of vehicles being in congestion, and the smaller the average distance between the front and rear vehicles in the current lane, the smaller the distance between the front and rear vehicles, the more likely it is to be in a state of traffic congestion. By evaluating the traffic status of multiple lanes by accumulating and summing the various parameters detected in real time, the accuracy of subsequent road condition analysis can be effectively improved;

[0060] At the same time, if an accident occurs on the current road section, the accident impact coefficient The larger the value of The greater the impact, when no accident occurs, the overall objective lane occupancy coefficient remains unchanged; in order to accurately evaluate the impact of accident on the overall objective lane occupancy coefficient , so through the formula The calculation is based on the formula that takes into account the duration of the accident, the number of vehicles involved, and the number and length of lanes occupied. Obviously, the longer the accident takes place, the more vehicles involved, and the greater the number and length of lanes occupied, the greater the pressure on traffic and the greater the impact on the road conditions of the current section. Therefore, the accident impact coefficient The larger the value of .

[0061] The process of calculating the subjective lane occupancy coefficient is as follows:

[0062] By formula:

[0063] Calculate the subjective lane occupancy coefficient ;

[0064] In the formula is the total number of detection sub-periods divided into a detection cycle, are the starting point and end point of a detection sub-period, respectively. The weight coefficient corresponding to each detection sub-period is determined based on historical data analysis. is the judgment function about the number of vehicles changing lanes illegally, is the curve of the average speed of vehicles on the current road section changing with time. is the reference curve, About time 's points.

[0065] Said The expression is: ; In the formula is the impact factor, obtained based on historical data analysis. is the number of vehicles that change lanes illegally in each detection sub-period, The total number of vehicles entering the current road section in each detection sub-period.

[0066] The present invention provides a method for obtaining a subjective lane occupancy coefficient. In the process of subjective lane occupancy evaluation, illegal lane change has a greater impact on vehicle driving. Calculate the subjective lane occupancy coefficient ; obviously It can be seen that the greater the cumulative change in the average driving speed of vehicles on the current road section in each detection sub-period, the greater the impact of illegal lane changes on lane traffic during the passage process, and therefore the greater the subjective lane occupancy coefficient. By counting the number of vehicles that illegally change lanes in each detection sub-period and dynamically correcting the degree of impact in each detection sub-period, the subjective lane occupancy coefficient can be accurately calculated comprehensively, providing solid data support for subsequent road condition assessment and road condition warning.

[0067] The process of identifying vehicles that change lanes illegally on the current road section is as follows:

[0068] Obtain the number of vehicles entering the entrance of the current road section in each detection sub-period, and then draw the driving trajectory of each vehicle on multiple lanes on the current road section, using the boundaries on both sides of each lane as steps;

[0069] Identify the number of intersections between each vehicle and lane boundaries and the number of lanes traveled ;

[0070] By formula: Calculate the lane change coefficient of the current vehicle ;

[0071] Will Compared with the preset lane change warning value For comparison, if , it is judged that the current vehicle has illegal lane changing behavior, otherwise it is judged that the current vehicle has no illegal lane changing behavior.

[0072] The present invention provides a method for determining whether a vehicle has changed lanes illegally. By accurately obtaining the number of vehicles entering the entrance of the current road section in each detection sub-period and drawing the vehicle's driving trajectory, the dynamic behavior of the vehicle on the road can be carefully depicted, thereby accurately identifying the illegal lane change behavior. At the same time, the lane boundary is used as a ladder, combined with the number of intersections between the vehicle and the lane boundary and the number of lanes traveled, a reliable data basis is provided for the calculation of the lane change coefficient, and the accuracy of identification is further improved. In addition, real-time monitoring and analysis of the vehicle's driving trajectory are realized, providing a scientific and efficient supervision means for the traffic management department, which is helpful to timely discover and deal with illegal lane change behaviors and improve the intelligent level of traffic management.

[0073] Through the preset lane change warning value, the alarm mechanism can be automatically triggered to reduce manual intervention and improve the efficiency of traffic law enforcement. Illegal lane changing is one of the important causes of traffic accidents. Through effective identification and warning, the risk of traffic accidents caused by illegal lane changing can be significantly reduced, ensuring the safety of road users. At the same time, reducing illegal lane changing behavior will also help maintain good traffic order, improve road traffic efficiency and alleviate traffic congestion.

[0074] The processing rule of the lane coefficient is:

[0075] Substitute the calculated objective lane occupancy coefficient and subjective lane occupancy coefficient into the following formula:

[0076] Calculate the lane coefficient ;

[0077] In the formula, , is a preset proportionality factor, determined based on historical data analysis. For the The subjective lane occupancy coefficient of each lane, , is the exponential coefficient;

[0078] Will , The corresponding warning values , Make a comparison;

[0079] like ,but ,otherwise ;

[0080] like ,but ,otherwise .

[0081] The objective lane occupancy coefficient obtained by calculation is and subjective lane occupancy factor Substitute the following formula: Calculate the lane coefficient In order to improve the monitoring accuracy of the lane coefficient on the current road condition, the influence is adjusted through the exponential coefficient. Obviously, if the subjective lane occupancy coefficient and the objective lane occupancy coefficient exceed their respective warning values, the corresponding exponential coefficient will take a larger value to effectively improve the sensitivity of the overall lane coefficient.

[0082] The process of generating warning information based on the judgment results of the lane data analysis module is as follows:

[0083] like , an emergency warning of the current road condition is generated;

[0084] like ,but , then an accident warning for the current road section is generated; or , then a violation warning for the current road section is generated;

[0085] like and and , no traffic warning for the current road section will be generated.

[0086] In order to improve the accuracy of the road condition information warning of the current road section, the present invention first uses the comparison result between the lane coefficient and the lane coefficient threshold. When , it means that the overall road condition of the current section is poor, so an emergency warning is issued to inform other vehicles to avoid the current section and improve traffic flow; and in order to further control traffic, the subjective lane occupancy coefficient and the objective lane occupancy coefficient are compared with their respective warning values. Obviously, if the subjective lane occupancy coefficient is larger, it means that there are more illegal lane changes in the current section, so it affects the average driving speed of the entire section. Therefore, it is necessary to mark the illegal vehicle and send a warning message to the owner of the illegal vehicle in time to reduce the probability of illegal lane changes again in the next section; and if the objective lane occupancy coefficient is larger, it means that the probability of accident users in the current section is higher, so it is necessary to issue an accident warning for the current section and give specific accident vehicle occupying the road, so as to avoid the accident vehicle occupying the road in advance when entering the current section, so as to improve traffic efficiency.

[0087] It should be noted that the calculation formulas and various parameters involved in the calculation in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0088] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A smart multi-lane detection system, characterized in that: include: The data collection module collects lane traffic data in real time by arranging multiple sets of detectors at intervals on multiple lanes of the current road section; Lane data processing module, used to process the collected lane traffic data, including data cleaning and feature extraction; A lane data analysis module is used to analyze the processed lane traffic data, calculate the subjective lane occupancy coefficient and the objective lane occupancy coefficient, and obtain the lane coefficient after processing the subjective lane occupancy coefficient and the objective lane occupancy coefficient according to a preset rule; The lane coefficient is compared with the lane coefficient threshold. If the lane coefficient is greater than the lane coefficient threshold, the road condition of the current road section is judged to be bad. Otherwise, the road condition of the current road section is judged to be good. Traffic condition warning module, which generates warning information based on the judgment results of the lane data analysis module and sends it through wireless communication technology; The process of calculating and obtaining the objective lane occupancy coefficient is as follows: Obtain information on whether an accident has occurred on multiple lanes on the current road section; If an accident occurs, obtain the number of vehicles involved in the current accident , the length of time the lane is occupied after the accident , Number of occupied lanes And the corresponding length , substitute into the formula: Calculate the accident impact coefficient If no accident occurs, ; For the The length of the lane occupied by the accident vehicle, is the reference time of occupying the lane after an accident. is the setting coefficient; The accident impact coefficient Substituting into the formula: Calculate the objective lane occupancy coefficient ; In the formula is the number of lanes in the current road section, For the Lanes, is the number of vehicles on the current lane, is the maximum number of vehicles that the current lane can accommodate, is the average speed of vehicles in the current lane, is the designed maximum speed of the current lane, is the average distance between the front and rear vehicles in the current lane; The process of calculating the subjective lane occupancy coefficient is as follows: By formula: Calculate the subjective lane occupancy coefficient ; In the formula is the total number of detection sub-periods divided into a detection cycle, are the starting point and end point of a detection sub-period, respectively. is the weight coefficient corresponding to each detection sub-period, is the judgment function about the number of vehicles changing lanes illegally, is the curve of the average speed of vehicles on the current road section changing with time. is the reference curve, About time The integral of Said The expression is: ; In the formula is the impact factor, is the number of vehicles that change lanes illegally in each detection sub-period, The total number of vehicles entering the current road section in each detection sub-period; The processing rule of the lane coefficient is: Substitute the calculated objective lane occupancy coefficient and subjective lane occupancy coefficient into the following formula: Calculate the lane coefficient ; In the formula, , is the preset scale factor, For the The subjective lane occupancy coefficient of each lane, , is the exponential coefficient; Will , The corresponding warning values , Make a comparison; like ,but ,otherwise ; like ,but ,otherwise .

2. The intelligent multi-lane detection system according to claim 1, characterized in that: The detector includes a camera, a sensor and a radar. The camera is used to capture vehicle images to identify the vehicle type and license plate number; the radar and the sensor are used to monitor the vehicle speed, the number of vehicles on the lane, and the distance between vehicles in real time.

3. The intelligent multi-lane detection system according to claim 1, characterized in that: The process of identifying vehicles that change lanes illegally on the current road section is as follows: Obtain the number of vehicles entering the entrance of the current road section in each detection sub-period, and then draw the driving trajectory of each vehicle on multiple lanes on the current road section, using the boundaries on both sides of each lane as steps; Identify the number of intersections between each vehicle and lane boundaries and the number of lanes traveled ; By formula: Calculate the lane change coefficient of the current vehicle ; Will Compared with the preset lane change warning value For comparison, if , it is judged that the current vehicle has illegal lane changing behavior, otherwise it is judged that the current vehicle has no illegal lane changing behavior.

4. The intelligent multi-lane detection system according to claim 1, characterized in that: The process of generating warning information based on the judgment results of the lane data analysis module is as follows: like , an emergency warning of the current road condition is generated; like ,but , then an accident warning for the current road section is generated; or , then a violation warning for the current road section is generated; like and and , no traffic warning for the current road section will be generated.

Images