Periodic loss time calculation method and system based on radar and vision fusion

Abstract

The present application discloses a method and system for calculating periodic loss time based on radar-visual fusion. The method includes: fusing video image data with radar detection data to obtain absolute time-space information of all vehicles; based on the phase and traffic lane corresponding to each stage, and according to the absolute time-space information, obtaining the additional headway of each vehicle corresponding to the startup sub-stage in each stage; superimposing the additional headway of each vehicle corresponding to the startup sub-stage to obtain the startup sub-stage loss time; based on the phase and traffic lane corresponding to each stage, and according to the absolute time-space information, obtaining the effective green light extension time used by vehicles in the clearing sub-stage; obtaining the clearing sub-stage loss time according to the effective green light extension time used by vehicles in the clearing sub-stage; obtaining the stage loss time according to the startup sub-stage loss time and the clearing sub-stage loss time, and obtaining the loss time of a cycle according to the stage loss time corresponding to each stage.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method and system for calculating periodic loss time based on radar and vision fusion. Background Art

[0002] Optimizing traffic conditions at intersections is the key to preventing and alleviating traffic congestion, and estimating traffic state parameters at intersections is an essential prerequisite for traffic optimization. The vehicle trajectories at intersections can fully characterize the traffic flow operation state and contain rich traffic flow information. The vehicle trajectories at intersections can reflect the characteristics of vehicle speed and acceleration over time and space, and accurately reproduce the operation rules of vehicles passing through intersections, thereby improving the accuracy of estimation and prediction of traffic state parameters (such as travel speed, travel time, queue length, delay, etc.) and the efficiency of traffic signal control, which has important theoretical significance and practical value.

[0003] However, the traditional method of calculating periodic loss time uses manual observation to conduct sampling inspection on samples, which results in unstable sampling data due to the influence of environmental or human factors at different times and spaces, and does not fully consider the driving conditions of various vehicles, which makes the traditional calculation method have large errors and low accuracy.

[0004] Application Contents

[0005] The purpose of this application is to solve the technical problems of large errors and low accuracy of traditional calculation methods. To achieve the above purpose, this application provides a method and system for calculating periodic loss time based on radar-visual fusion.

[0006] The present application provides a method for calculating periodic loss time based on radar-visual fusion, including:

[0007] Acquire video image data and radar detection data;

[0008] Fusing the video image data with the radar detection data to obtain relative spatiotemporal information of each vehicle relative to the intersection, and obtaining absolute spatiotemporal information of all vehicles at the intersection based on the relative spatiotemporal information;

[0009] Acquire traffic timing information and map information of the intersection, and obtain multiple stages included in a cycle, phases corresponding to each stage, and traffic lanes according to the traffic timing information and the map information;

[0010] Based on the phase and the traffic lane corresponding to each of the stages and according to the absolute time-space information, obtaining the additional headway time of each vehicle corresponding to the starting sub-stage in each of the stages;

[0011] Superimposing the additional headway of each vehicle corresponding to the startup sub-stage in each stage to obtain the startup loss time corresponding to the startup stage;

[0012] Based on the phase and the traffic lane corresponding to each of the stages and according to the absolute time-space information, obtaining the effective green light extension time used by the vehicle in the clearing sub-stage in each of the stages;

[0013] According to the effective green light extension time used by vehicles in the clearing sub-stage in each stage, obtaining the clearing sub-loss time corresponding to the clearing sub-stage;

[0014] According to the promoter loss time and the clearer loss time, the stage loss time corresponding to each stage is obtained, and according to the stage loss time corresponding to each stage, the loss time of one cycle is obtained.

[0015] In one embodiment, based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information, obtaining the additional headway of each vehicle corresponding to the starting sub-stage in each stage includes:

[0016] According to the phase corresponding to each stage and the absolute spatiotemporal information of all vehicles in the traffic lane, the headway of each vehicle and the saturated headway of the queuing vehicle fleet are obtained;

[0017] The additional headway of each vehicle is obtained according to the headway of each vehicle and the saturated headway.

[0018] In one embodiment, based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information, obtaining the effective green light extension time used by the vehicle in the clearing sub-stage in each stage includes:

[0019] According to the phase corresponding to each stage and the absolute spatiotemporal information of all vehicles in the traffic lane, obtaining the effective extended travel time of each vehicle that passes through the stop line during the yellow signal light and passes through the intersection during the full red time in the clearing sub-stage;

[0020] The effective extended passage time of each vehicle is added up to obtain the effective green light extension time used by the vehicle in the clearing sub-stage in each stage.

[0021] In one embodiment, obtaining the clearing sub-loss time corresponding to the clearing sub-stage according to the effective green light extension time used by the vehicle in the clearing sub-stage in each stage includes:

[0022] Obtaining the full red time corresponding to the red signal light and the yellow light time corresponding to the yellow signal light in each stage;

[0023] The clearing sub-loss time corresponding to the clearing sub-stage is calculated according to the all-red time, the yellow light time and the effective green light extension time.

[0024] In one embodiment, obtaining the headway of each vehicle and the saturated headway of the queuing vehicle fleet according to the phase corresponding to each stage and the absolute spatiotemporal information of all vehicles in the traffic lane includes:

[0025] According to the phase corresponding to each stage and the absolute spatiotemporal information of all vehicles in the traffic lane, the head vehicle and the tail vehicle of the queue are obtained;

[0026] According to the first vehicle and the last vehicle of the team, the average headway time of all vehicles from the nth vehicle of the first vehicle to the last vehicle of the team is calculated to obtain the saturated headway time;

[0027] Wherein, n is a positive integer greater than 4.

[0028] In one embodiment, the present application provides a periodic loss time calculation system based on radar and vision fusion, comprising:

[0029] A data acquisition module, used to acquire video image data and radar detection data;

[0030] an absolute space-time information acquisition module, used to fuse the video image data with the radar detection data to obtain relative space-time information of each vehicle relative to the intersection, and to obtain absolute space-time information of all vehicles at the intersection based on the relative space-time information;

[0031] A phase information acquisition module, used to acquire traffic timing information and map information of the intersection, and obtain multiple phases included in a cycle, the phase corresponding to each phase, and the traffic lane according to the traffic timing information and the map information;

[0032] An additional headway acquisition module is used to acquire the additional headway of each vehicle corresponding to the start sub-phase in each of the phases based on the phase and the traffic lane corresponding to each of the phases and according to the absolute time-space information;

[0033] A promoter loss time acquisition module, used for superimposing the additional headway of each vehicle corresponding to the promoter sub-stage in each stage to obtain the promoter loss time corresponding to the promoter sub-stage;

[0034] An effective green light extension time acquisition module is used to acquire the effective green light extension time used by vehicles in the clearing sub-stage in each stage based on the phase and the traffic lane corresponding to each stage and according to the absolute time and space information;

[0035] A clearing sub-loss time acquisition module, used for acquiring the clearing sub-loss time corresponding to the clearing sub-stage according to the effective green light extension time used by vehicles in the clearing sub-stage in each stage;

[0036] The cycle loss time acquisition module is used to obtain the stage loss time corresponding to each stage according to the promoter loss time and the clearing sub-loss time, and to obtain the loss time of a cycle according to the stage loss time corresponding to each stage.

[0037] In one embodiment, the additional headway acquisition module includes:

[0038] A first time headway acquisition module is used to obtain the headway of each vehicle and the saturated headway of the queuing team according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane;

[0039] The second time headway acquisition module is used to obtain the additional headway of each vehicle according to the headway of each vehicle and the saturated headway.

[0040] In one embodiment, the effective green light extension time acquisition module includes:

[0041] A first extended time acquisition module is used to obtain the effective extended travel time of each vehicle that passes through the stop line during the yellow traffic light and passes through the intersection during the full red time in the clearing sub-stage according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane;

[0042] The second extended time acquisition module is used to add up the effective extended passage time of each vehicle to obtain the effective green light extended time used by the vehicle in the clearing sub-stage in each stage.

[0043] In one embodiment, the clearing sub-loss time acquisition module includes:

[0044] A signal light time acquisition module, used for acquiring the full red time corresponding to the red signal light and the yellow light time corresponding to the yellow signal light in each stage;

[0045] A calculation module is used to calculate the clearing sub-loss time corresponding to the clearing sub-stage according to the all-red time, the yellow light time and the effective green light extension time.

[0046] In one embodiment, the first time distance acquisition module includes:

[0047] A head and tail vehicle acquisition module, used for acquiring the head vehicle and the tail vehicle of the queue according to the phase corresponding to each stage and the absolute time and space information of all vehicles in the traffic lane;

[0048] A saturated headway time calculation module is used to calculate the average headway time of all vehicles from the nth vehicle from the head vehicle to the tail vehicle according to the head vehicle and the tail vehicle, so as to obtain the saturated headway time;

[0049] Wherein, n is a positive integer greater than 4.

[0050] In the above-mentioned periodic loss time calculation method and system based on radar-visual fusion, the video image data and radar detection data are fused in real time, the absolute spatiotemporal information of all vehicles can be accurately obtained, and the traffic timing information and map information are combined to obtain each stage in a cycle and the corresponding phase and traffic lane, so as to achieve the fusion of multiple information of video image data, radar detection data, traffic timing information and map information, and obtain the promoter loss time corresponding to the promoter stage and the clearing sub-loss time corresponding to the clearing sub-stage in each stage from multiple dimensions, so as to obtain the stage loss time, and further obtain the cycle loss time. In addition, in the periodic loss time calculation method based on radar-visual fusion provided by the present application, the loss of each time period such as the promoter loss time, the effective green light extension time used by the vehicle in the clearing sub-stage, and the clearing sub-loss time are fully considered, so that the obtained cycle loss time is more accurate, the utilization rate of the intersection is improved, the saturation is reduced, the traffic pressure is relieved, and the timing plan is provided with a basis for selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This application provides a method for calculating periodic loss time based on radar-vision fusion.

[0052] Figure 2 This application provides a periodic loss time calculation system based on radar and vision fusion. DETAILED DESCRIPTION

[0053] The technical solution of the present application is further described in detail below through the accompanying drawings and embodiments.

[0054] See also Figure 1 The present application provides a method for calculating periodic loss time based on radar-visual fusion, including:

[0055] S10, acquiring video image data and radar detection data;

[0056] S20, fusing the video image data with the radar detection data to obtain relative spatiotemporal information of each vehicle relative to the intersection, and obtaining absolute spatiotemporal information of all vehicles at the intersection based on the relative spatiotemporal information;

[0057] S30, obtaining traffic timing information and map information of the intersection, and obtaining multiple stages included in a cycle, the phase corresponding to each stage, and the traffic lane according to the traffic timing information and the map information;

[0058] S40, based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information, obtaining the additional headway time of each vehicle corresponding to the start sub-stage in each stage;

[0059] S50, superimposing the additional headway time of each vehicle corresponding to the starter stage in each stage to obtain the starter loss time corresponding to the starter stage;

[0060] S60, based on the phase and the traffic lane corresponding to each stage and according to the absolute time and space information, obtaining the effective green light extension time used by the vehicle in the clearing sub-stage in each stage;

[0061] S70, obtaining a clearing sub-stage loss time corresponding to the clearing sub-stage according to the effective green light extension time used by vehicles in the clearing sub-stage in each stage;

[0062] S80, obtaining the stage loss time corresponding to each stage according to the initiator loss time and the clearer loss time, and obtaining the loss time of one cycle according to the stage loss time corresponding to each stage.

[0063] In S10, video image data and radar detection data can be obtained through the radar vision integrated device. In S20, the video image is extracted frame by frame through video processing software, and the frame by frame image is detected and recognized based on the deep learning method to obtain the vehicle driving trajectory, headway, headway, vehicle license plate number, vehicle color, vehicle license plate color and vehicle model and other camera-based vehicle information. Radar detection can obtain radar-based vehicle information such as vehicle distance, vehicle orientation, vehicle speed, vehicle acceleration and vehicle spatial position in harsh detection environments and harsh environments.

[0064] The relative distance of the vehicle relative to the intersection can be obtained according to the radar detection data. According to the video image data, the vehicle's own attribute information (such as license plate number, license plate color, vehicle color, etc.) and the time information of each frame of the image can be obtained. After the video image data and the radar detection data are fused, the relative spatiotemporal information of each vehicle relative to the intersection can be obtained. Relative spatiotemporal information is spatiotemporal information with the intersection as a reference. Spatiotemporal information can be understood as the spatial position of the vehicle at different times, specifically including multi-dimensional information such as time information, vehicle position information, vehicle speed information, vehicle driving direction information, and vehicle model information. The relative spatiotemporal information of each vehicle relative to the intersection includes the spatial position of each vehicle relative to the intersection at different times. According to the conversion relationship between the coordinate systems, the relative spatiotemporal information can be mapped to the absolute spatiotemporal information. For example: In one embodiment, the high-precision map can provide the stop line contour position information, lane line contour position information, and longitude and latitude information of the intersection. Relative spatiotemporal information includes the relative spatial position of the vehicle relative to the intersection. According to the distance of the vehicle relative to the intersection, the relative spatial position can be converted into an absolute spatial position in the geographic coordinate system, and the longitude and latitude information corresponding to the vehicle can be obtained. Furthermore, the vehicle can be marked on the map according to the longitude and latitude information corresponding to the vehicle, providing relevant geographic location information support. Therefore, by fusing the video image data with the radar detection data to obtain the relative spatiotemporal information of each vehicle, the relative spatiotemporal information of all vehicles passing through the intersection can be further obtained, and then the absolute spatiotemporal information of all vehicles passing through the intersection can be obtained.

[0065] In S30, traffic timing information can be understood as providing real twin information of signal control devices in the physical world, including but not limited to phase, stage, cycle, plan, control method, etc. It can also be understood as urban traffic signal control information at intersections, including red, green, yellow and other light color control time, etc.

[0066] Map information is obtained from actual surveying and mapping, providing real twin information of the physical world environment, including reference lines, lane lines, center lines, curbs, corrugated guardrails, concrete guardrails, overpasses, traffic signs, delineators, bridge piers, arrows, text, symbols, warning areas, diversion areas, traffic lights, stop positions, pedestrian crossings, public transportation stops, speed reduction, bicycle lanes at intersections, no-parking zones, manhole covers, parking spaces, traffic light poles, timers, signal machines, diversion islands, interchange culverts, checkpoints, intersection center circles, tunnel walls, bus bay lines, central isolation belts, intersection surfaces, toll station elements, etc. Map information is high-precision map information, including but not limited to lane areas, marking positions, channelization information, ground signs, etc.

[0067] The absolute spatiotemporal information of the vehicle obtained at the intersection includes time information and space information. By comparing the time information and space information with the map information, the specific lane position information of the vehicle at a certain moment can be obtained. According to the absolute spatiotemporal information of all vehicles at the intersection, the position information of the vehicle within a period of time can be obtained, and then the lane information of the vehicle can be obtained. A cycle can be understood as the time required for the color of the signal light to change one circle according to the set signal phase sequence. A cycle contains n stages or phases. The stages and phases contained in the cycle are obtained by timing. The traffic light indicates the flow direction allowed to pass, and then the flow direction is used to match the lane to obtain the passable lane. For example: the phases allowed to pass are north straight, north right, south value, and south right. The right turn lane and the straight + right turn lane in the north-south straight lane are all passable, that is, the passable lane is formed. The corresponding time is assigned to each phase to form a stage. The phase represents a moment state, and the stage represents the state duration.

[0068] In S40, one stage corresponds to one phase, and each stage includes multiple sub-stages, such as the start-up sub-stage and the clearing sub-stage. Based on the absolute time-space information, the driving trajectory, headway, headway time and other information of each vehicle can be obtained. The start-up sub-stage represents a period of time starting from the start of the vehicle and thereafter, including the time period of the start-up reaction and the acceleration reaction. The additional headway time can be understood as the extra green light time occupied by each vehicle due to the start-up reaction and acceleration effect, which can be calculated by the difference between the headway time of each vehicle and the saturated headway time.

[0069] In S50, the additional headway time of each vehicle corresponding to the start-up sub-stage in each stage is summed up to obtain the extra green light time occupied by all vehicles in the start-up sub-stage due to the start-up reaction and acceleration effect, and then obtain the start-up loss time corresponding to the start-up sub-stage.

[0070] In S60, the clearing sub-stage is opposite to the starting sub-stage, which can be understood as the time period when the green light turns to yellow and red after the green light ends, or as the stage corresponding to the time difference between the moment when the front wheel of the last vehicle passing through the stop line during the yellow light period and the moment when the green light turns on in the next phase. It can also be understood as the stage corresponding to the loss time caused by some vehicles behind the stop line during the yellow light period after the green light time ends. For example, in the extreme case, no vehicle passes through the entire stage, then the green light period is the empty time period, and the yellow light and all red time are the clearing loss time.

[0071] The clearing sub-stage includes two types of clearing losses. In one case, some vehicles actively slow down and stop because they cannot pass through the intersection, and do not pass the stop line. The stop time is yellow and has not turned red. At this time, the yellow light during the stop time is equivalent to the function of stopping at the red light (some vehicles have stopped at the yellow light moment and waited for the red light to come), resulting in a clearing loss. In another case, there are red lights in all four directions (which can be understood as full red time), so that vehicles or pedestrians who have passed the stop line but not through the intersection pass through the intersection. Before the full red time ends, the intersection has been cleared in advance and no extra time is needed for clearing. The extra time is considered to be lost, resulting in another type of clearing loss.

[0072] The effective green light extension time used by the vehicle can be understood as the yellow light and full red time effectively used by the vehicle. For example, in one embodiment, the vehicle passes the stop line at the last moment of the yellow light and passes the intersection at the last moment of the full red time. This period of time is the completely effective utilization time and is not lost, and part of the yellow light and full red time are effectively utilized.

[0073] In S70, the sum of the yellow light time and the full red time is subtracted from the effective green light extension time to calculate the clearing sub-stage loss time. The effective green light extension time can be obtained by using the absolute time-space information obtained based on the radar-visual fusion data. By tracking the time and position of the vehicle, the effective green light extension time used by the vehicle in the clearing sub-stage can be accurately obtained, and the clearing sub-stage loss time can be further calculated.

[0074] In S80, the stage loss time of each stage can be understood as the time that vehicles are not allowed to pass or is wasted due to the change of the signal light color. The stage loss time is equal to the sum of the starter loss time and the clearing sub-loss time. The stage loss time of each stage in a cycle is added together to obtain the loss time of a cycle.

[0075] The periodic loss time calculation method based on radar-visual fusion provided by the present application fuses the video image data with the radar detection data in real time, and can accurately obtain the absolute spatiotemporal information of all vehicles, and combine the traffic timing information with the map information to obtain each stage in a cycle and the corresponding phase and traffic lane, realizing the fusion of multiple information of video image data, radar detection data, traffic timing information and map information, and obtaining the promoter loss time corresponding to the promoter stage and the clearing sub-loss time corresponding to the clearing sub-stage in each stage from multiple dimensions, thereby obtaining the stage loss time, and further obtaining the cycle loss time. In addition, the periodic loss time calculation method based on radar-visual fusion provided by the present application fully considers the losses of each time period such as the promoter loss time, the effective green light extension time used by vehicles in the clearing sub-stage, and the clearing sub-loss time, so that the obtained cycle loss time is more accurate, the intersection utilization rate is improved, the saturation is reduced, the traffic pressure is relieved, and the timing plan is provided with a basis for selection.

[0076] By calculating the clearing sub-loss time in the periodic loss time calculation method based on radar and vision fusion provided in the present application, it is possible to give suggestions for adjusting the duration of yellow and red lights in induction control. By calculating the starting sub-loss time in the periodic loss time calculation method based on radar and vision fusion provided in the present application, it is possible to give suggestions for reducing the starting loss time in road and signal construction. By calculating the stage loss time in the periodic loss time calculation method based on radar and vision fusion provided in the present application, it is possible to give reference suggestions on the selection and design of signal timing schemes.

[0077] In one embodiment, S20, fusing the video image data with the radar detection data to obtain the relative spatiotemporal information of each vehicle relative to the intersection includes:

[0078] S210, obtaining camera-based vehicle information according to the video image data;

[0079] S220, obtaining radar-based vehicle information according to the radar detection data;

[0080] S230 combines the camera-based vehicle information with the radar-based vehicle information according to the radar video fusion algorithm.

[0081] The received vehicle information is fused in time and space to obtain the relative time and space information of each vehicle relative to the intersection.

[0082] In this embodiment, the radar video fusion algorithm includes time fusion and space fusion. In the process of spatial fusion, it is necessary to convert between the radar coordinate system and the camera coordinate system. The radar and the camera are relatively fixed, and the conversion relationship between the radar coordinate system and the camera coordinate system can be obtained. According to the camera coordinate system and the image coordinate system, distortion correction can be performed to obtain the distorted image coordinates. The camera calibration method is used to calibrate the distance and angle of the vehicle detected by the radar, and the internal parameters of the camera such as focal length, principal point coordinates, distortion parameters, etc. can be obtained, and the projection coordinates of the vehicle in the image can be obtained, and the conversion of the radar coordinate system to the pixel coordinate system is realized, and the spatial fusion of the video image data and the radar detection data is completed.

[0083] In the process of time fusion, video image data and radar detection data are collected synchronously in time to achieve time fusion. When the sampling rate of the camera is different from the sampling rate of the radar, the same sampling rate can be used for sampling based on the sampling rate of the camera or the sampling rate of the radar. The camera collects one frame of image each time, selects the radar, and one frame of cached data is sampled together to achieve a frame of radar and camera fusion data, ensuring the time synchronization of video image data and radar detection data.

[0084] By fusing camera-based vehicle information with radar-based vehicle information in time and space, the relative time and space information of each vehicle relative to the intersection can be obtained. Relative time and space information can be understood as the relative time and space information of the vehicle relative to the intersection or the radar-vision integrated device. Time and space information can be understood as time information and space information. Time and space information includes multi-dimensional information such as time information of a vehicle at a certain moment, vehicle position information, vehicle speed information, vehicle driving direction information, vehicle model information, vehicle license plate information, and vehicle color information. In this embodiment, real-time observation and measurement are performed through radar-vision fusion technology, which overcomes the influence of noise and delayed acquisition, and achieves the purpose of full time and space, high accuracy, and low latency.

[0085] In one embodiment, S40, based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information, obtaining the additional headway of each vehicle corresponding to the start sub-stage in each stage includes:

[0086] S410, obtaining the headway of each vehicle and the saturated headway of the queuing team according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane;

[0087] S420, obtaining an additional headway of each vehicle according to the headway of each vehicle and the saturated headway.

[0088] In this embodiment, the queueing fleet is a continuous fleet of vehicles that are queued and have a parking delay time greater than 0. The queueing fleet includes vehicles that arrive at the intersection at a red signal light and stop to wait and vehicles that arrive at the intersection at a green signal light and stop to queue to pass. The timing of the red signal light and the green signal light can be known based on the traffic timing information. Arriving at the intersection at a red signal light and stopping to wait can be understood as vehicles that arrive at a red light and stop completely to queue. Arriving at the intersection at a green signal light and stopping to queue to pass can be understood as vehicles that arrive at a green light but stop to queue because the queued vehicles have not completely dissipated. Based on the radar-based fusion data, the vehicle driving conditions at each stage are fully reflected in real time.

[0089] In one embodiment, S410, according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane, the headway of each vehicle and the saturated headway of the queue are obtained, including:

[0090] S411, obtaining the head vehicle and the tail vehicle of the queuing vehicle team according to the phase corresponding to each stage and the absolute time and space information of all vehicles in the traffic lane;

[0091] S412, calculating the average headway time of all vehicles from the nth vehicle at the head of the team to the last vehicle at the end of the team according to the head vehicle and the last vehicle at the end of the team, and obtaining the saturated headway time;

[0092] Wherein, n is a positive integer greater than 4.

[0093] In this embodiment, the headway time of all vehicles in the queue, the head vehicle and the tail vehicle in the queue are obtained. According to the head vehicle and the tail vehicle in the queue, the average headway time of all vehicles from the nth vehicle in the queue to the tail vehicle is calculated to obtain the saturated headway time. Where n is a positive integer greater than 4. The queue includes two situations: vehicles that arrive at the intersection at a red traffic light and stop to wait, and vehicles that arrive at the intersection at a green traffic light and stop to queue to pass.

[0094] The headway time can be understood as the time difference between the headways of the nth vehicle and the n+1th vehicle reaching the observation line (vehicle stop line). n =t n+1 -t n The saturated headway can be understood as the headway between the nth and subsequent vehicles after a period of time after the green light comes on, when the vehicles in the lane are moving at a constant speed without the influence of the starting reaction and acceleration effect. Saturated headway h sThe formula is expressed as the average of the headway time of m+1-n vehicles starting from the nth vehicle. If n is greater than 4, the problem of inaccurate calculation caused by the first 4 vehicles in the queue being greatly affected by the starting reaction and acceleration effect can be avoided. Under normal vehicle traffic conditions, the head and tail of the queue are identified and confirmed, and the headway time of the nth vehicle and subsequent vehicles is calculated. The headway time of multiple vehicles is averaged to obtain the saturated headway time. The saturated headway time calculation process is sampled multiple times and then the average is taken, which can be applied to the morning rush hour on rainy weekdays or the idle time on sunny non-working days.

[0095] The difference between the headway of each vehicle and the saturated headway is the additional headway of each vehicle. By calculating the difference between the headway and the saturated headway, the additional headway of each vehicle can be obtained. In this embodiment, the headway and the saturated headway are both accurately calculated by the absolute time and space information obtained by the radar-visual fusion data, which improves the accuracy of the calculation method and can quickly and accurately obtain data for the calculation of cycle loss time.

[0096] In one embodiment, S60, based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information, obtaining the effective green light extension time used by the vehicle in the clearing sub-stage in each stage includes:

[0097] S610, obtaining the effective extended travel time of each vehicle that passes through the stop line during the yellow traffic light period and passes through the intersection during the full red time in the clearing sub-phase according to the phase corresponding to each phase and the absolute spatiotemporal information of all vehicles in the traffic lane;

[0098] S620, the effective extended travel time of each vehicle is added up to obtain the effective green light extension time used by the vehicle in the clearing sub-stage in each stage.

[0099] In this embodiment, the trajectory of the vehicle can be tracked based on the absolute spatiotemporal information, and multi-dimensional information such as time information, vehicle location information, vehicle speed information, vehicle driving direction information, and vehicle model information can be obtained. At the same time, combined with traffic timing information and map information, each vehicle that passes through the stop line during the yellow signal light and passes through the intersection during the full red time in the clearing sub-stage can be captured. The full red time can be understood as the duration during which no vehicle at any entrance is allowed to cross the stop line and enter the intersection, or it can be understood as the time interval after the end of the yellow light of one phase and before the start of the green light of the next phase.

[0100] Passing the stop line during the yellow signal light and passing the intersection during the all-red time can be understood as when the green signal light turns to the yellow signal light, some vehicles pass the stop line, and the vehicles pass the intersection during the time period when the yellow signal light turns to the red signal light and the red signal light does not turn to the green signal light. In the clearing sub-stage, the yellow signal light and the all-red time are effectively utilized by the vehicles to pass the intersection, thereby forming an effective extension of the passage time. By superimposing the effective green light extension time corresponding to each vehicle, the total effective extension of the passage time utilized by multiple vehicles in the clearing sub-stage can be obtained, forming an effective green light extension time. The calculation accuracy of the effective green light extension time in this embodiment is greater than the calculation method obtained by rough definition and fitting, and the effective green light extension time can be quickly and accurately obtained.

[0101] In one embodiment, S70, according to the effective green light extension time used by vehicles in the clearing sub-stage in each stage, obtaining the clearing sub-loss time corresponding to the clearing sub-stage includes:

[0102] S710, obtaining the full red time corresponding to the red traffic light and the yellow light time corresponding to the yellow traffic light in each stage;

[0103] S720, calculating the clearing sub-stage loss time corresponding to the clearing sub-stage according to the all-red light time, the yellow light time, and the effective green light extension time.

[0104] In this embodiment, the clearing sub-loss time can be calculated by the full red time, the yellow light time and the effective green light extension time. The clearing sub-loss time is equal to the sum of the full red time and the yellow light time, minus the effective green light extension time. The effective green light extension time can be accurately calculated based on the absolute spatiotemporal information, and then the clearing sub-loss time corresponding to the clearing sub-stage can be accurately known based on the effective green light extension time, so that the calculation accuracy of the clearing sub-loss time is greater than the calculation method obtained by rough definition and fitting, and the clearing sub-loss time can be quickly, accurately and fully obtained.

[0105] See also Figure 2In one embodiment, the present application provides a periodic loss time calculation system based on radar-visual fusion. The periodic loss time calculation system 100 based on radar-visual fusion includes a data acquisition module 10, an absolute time-space information acquisition module 20, a stage information acquisition module 30, an additional headway time acquisition module 40, a starter sub-loss time acquisition module 50, an effective green light extension time acquisition module 60, a clearing sub-loss time acquisition module 70, and a periodic loss time acquisition module 80. The data acquisition module 10 is used to acquire video image data and radar detection data. The absolute time-space information acquisition module 20 is used to fuse the video image data with the radar detection data to obtain the relative time-space information of each vehicle relative to the intersection, and obtain the absolute time-space information of all vehicles at the intersection based on the relative time-space information. The stage information acquisition module 30 is used to acquire the traffic timing information and map information of the intersection, and obtain multiple stages contained in a cycle, the phase corresponding to each stage, and the traffic lanes based on the traffic timing information and the map information.

[0106] The additional headway acquisition module 40 is used to acquire the additional headway of each vehicle corresponding to the startup sub-stage in each stage based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information. The startup loss time acquisition module 50 is used to superimpose the additional headway of each vehicle corresponding to the startup sub-stage in each stage to obtain the startup loss time corresponding to the startup sub-stage. The effective green light extension time acquisition module 60 is used to acquire the effective green light extension time used by vehicles in the clearing sub-stage in each stage based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information.

[0107] The clearing sub-loss time acquisition module 70 is used to obtain the clearing sub-loss time corresponding to the clearing sub-stage according to the effective green light extension time used by vehicles in the clearing sub-stage in each stage. The cycle loss time acquisition module 80 is used to obtain the stage loss time corresponding to each stage according to the starter loss time and the clearing sub-loss time, and obtain the loss time of a cycle according to the stage loss time corresponding to each stage.

[0108] In this embodiment, the relevant description of the data acquisition module 10 may refer to the relevant description of S10 in the above embodiment. The relevant description of the absolute spatiotemporal information acquisition module 20 may refer to the relevant description of S20 in the above embodiment. The relevant description of the stage information acquisition module 30 may refer to the relevant description of S30 in the above embodiment. The relevant description of the additional headway acquisition module 40 may refer to the relevant description of S40 in the above embodiment. The relevant description of the promoter loss time acquisition module 50 may refer to the relevant description of S50 in the above embodiment. The relevant description of the effective green light extension time acquisition module 60 may refer to the relevant description of S60 in the above embodiment. The relevant description of the clearing sub-loss time acquisition module 70 may refer to the relevant description of S70 in the above embodiment. The relevant description of the cycle loss time acquisition module 80 may refer to the relevant description of S80 in the above embodiment.

[0109] In one embodiment, the additional headway acquisition module 40 includes a first headway acquisition module and a second headway acquisition module. The first headway acquisition module is used to obtain the headway of each vehicle and the saturated headway of the queue according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane. The second headway acquisition module is used to obtain the additional headway of each vehicle according to the headway of each vehicle and the saturated headway.

[0110] In this embodiment, the description of the first time distance acquisition module can refer to the description of S410 in the above embodiment. The description of the second time distance acquisition module can refer to the description of S420 in the above embodiment.

[0111] In one embodiment, the effective green light extension time acquisition module 60 includes a first extension time acquisition module and a second extension time acquisition module. The first extension time acquisition module is used to obtain the effective extended passage time of each vehicle that passes through the stop line during the yellow signal light and passes through the intersection during the full red time in the clearing sub-stage according to the phase corresponding to each stage and the absolute time and space information of all vehicles in the traffic lane. The second extension time acquisition module is used to superimpose the effective extended passage time of each vehicle to obtain the effective green light extension time used by the vehicle in the clearing sub-stage in each stage.

[0112] In this embodiment, the description of the first extended time acquisition module can refer to the description of S610 in the above embodiment. The description of the second extended time acquisition module can refer to the description of S620 in the above embodiment.

[0113] In one embodiment, the clearing sub-loss time acquisition module 70 includes a signal light time acquisition module and a calculation module. The signal light time acquisition module is used to acquire the full red time corresponding to the red signal light and the yellow light time corresponding to the yellow signal light in each stage. The calculation module is used to calculate the clearing sub-loss time corresponding to the clearing sub-stage according to the full red time, the yellow light time and the effective green light extension time.

[0114] In this embodiment, the relevant description of the signal light time acquisition module can refer to the relevant description of S710 in the above embodiment. The relevant description of the calculation module can refer to the relevant description of S720 in the above embodiment.

[0115] In one embodiment, the first time distance acquisition module includes a head and tail vehicle acquisition module and a saturated headway time distance calculation module. The head and tail vehicle acquisition module is used to obtain the head vehicle and the tail vehicle of the queue according to the phase corresponding to each stage and the absolute time and space information of all vehicles in the traffic lane. The saturated headway time distance calculation module is used to calculate the average headway time distance of all vehicles from the nth vehicle from the head vehicle to the tail vehicle according to the head vehicle and the tail vehicle, and obtain the saturated headway time distance. Wherein, n is a positive integer greater than 4.

[0116] In this embodiment, the description of the leading and trailing vehicle acquisition module can refer to the description of S411 in the above embodiment. The description of the saturated headway calculation module can refer to the description of S412 in the above embodiment.

[0117] In the above-mentioned various embodiments, the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims provide the elements of various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0118] Those skilled in the art may also understand that the various illustrative logical blocks, modules and steps listed in the embodiments of the present application may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, modules and steps described above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present application.

[0119] The various illustrative logic blocks or modules described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or the design of any combination of the above functions. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any traditional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.

[0120] The steps of the method or algorithm described in the embodiments of the present application can be directly embedded in the software module executed by the hardware, the processor, or a combination of the two. The software module can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM or other storage media of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Alternatively, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a user terminal. Optionally, the processor and the storage medium can also be arranged in different components in the user terminal.

[0121] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for calculating periodic loss time based on radar-visual fusion, characterized in that: include: Acquire video image data and radar detection data; Fusing the video image data with the radar detection data to obtain relative spatiotemporal information of each vehicle relative to the intersection, and obtaining absolute spatiotemporal information of all vehicles at the intersection based on the relative spatiotemporal information; Acquire traffic timing information and map information of the intersection, and obtain multiple stages included in a cycle, phases corresponding to each stage, and traffic lanes according to the traffic timing information and the map information; Based on the phase and the traffic lane corresponding to each of the stages and according to the absolute time-space information, obtaining the additional headway time of each vehicle corresponding to the starting sub-stage in each of the stages; Superimposing the additional headway of each vehicle corresponding to the startup sub-stage in each stage to obtain the startup loss time corresponding to the startup stage; Based on the phase and the traffic lane corresponding to each of the stages and according to the absolute time-space information, obtaining the effective green light extension time used by the vehicle in the clearing sub-stage in each of the stages; According to the effective green light extension time used by vehicles in the clearing sub-stage in each stage, obtaining the clearing sub-loss time corresponding to the clearing sub-stage; According to the promoter loss time and the clearer loss time, the stage loss time corresponding to each stage is obtained, and according to the stage loss time corresponding to each stage, the loss time of one cycle is obtained.

2. The method for calculating periodic loss time based on radar-visual fusion according to claim 1, characterized in that: The step of obtaining the additional headway time of each vehicle corresponding to the start sub-phase in each stage based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information includes: According to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane, the headway of each vehicle and the saturated headway of the queue are obtained; The additional headway of each vehicle is obtained according to the headway of each vehicle and the saturated headway.

3. The method for calculating periodic loss time based on radar-visual fusion according to claim 1, characterized in that: The obtaining of the effective green light extension time used by vehicles in the clearing sub-stage in each stage based on the phase and the traffic lane corresponding to each stage and according to the absolute time-space information includes: obtaining the effective extended passage time of each vehicle that passes through the stop line during the yellow signal light and passes through the intersection during the full red time in the clearing sub-stage according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane; The effective extended passage time of each vehicle is added up to obtain the effective green light extension time used by the vehicle in the clearing sub-stage in each stage.

4. The method for calculating periodic loss time based on radar-visual fusion according to claim 3 is characterized in that: The obtaining, according to the effective green light extension time used by the vehicle in the clearing sub-stage in each stage, the clearing sub-loss time corresponding to the clearing sub-stage comprises: Obtaining the full red time corresponding to the red signal light and the yellow light time corresponding to the yellow signal light in each of the stages; The clearing sub-loss time corresponding to the clearing sub-stage is calculated according to the all-red time, the yellow light time and the effective green light extension time.

5. The method for calculating periodic loss time based on radar-visual fusion according to claim 2, characterized in that: The step of obtaining the headway of each vehicle and the saturated headway of the queueing vehicle fleet according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane comprises: According to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane, the head vehicle and the tail vehicle of the queue are obtained; According to the first vehicle and the last vehicle of the team, the average headway time of all vehicles from the nth vehicle of the first vehicle to the last vehicle of the team is calculated to obtain the saturated headway time; Wherein, n is a positive integer greater than 4.

6. A periodic loss time calculation system based on radar and vision fusion, characterized in that: include: A data acquisition module, used to acquire video image data and radar detection data; an absolute space-time information acquisition module, used to fuse the video image data with the radar detection data to obtain relative space-time information of each vehicle relative to the intersection, and to obtain absolute space-time information of all vehicles at the intersection based on the relative space-time information; A phase information acquisition module, used to acquire traffic timing information and map information of the intersection, and obtain multiple phases included in a cycle, the phase corresponding to each phase, and the traffic lane according to the traffic timing information and the map information; An additional headway acquisition module is used to acquire the additional headway of each vehicle corresponding to the start sub-phase in each of the phases based on the phase and the traffic lane corresponding to each of the phases and according to the absolute time-space information; A promoter loss time acquisition module, used for superimposing the additional headway of each vehicle corresponding to the promoter sub-stage in each stage to obtain the promoter loss time corresponding to the promoter sub-stage; An effective green light extension time acquisition module is used to acquire the effective green light extension time used by vehicles in the clearing sub-stage of each stage based on the phase and the traffic lane corresponding to each stage and according to the absolute time and space information; A clearing sub-loss time acquisition module, used for acquiring the clearing sub-loss time corresponding to the clearing sub-stage according to the effective green light extension time used by vehicles in the clearing sub-stage in each stage; The cycle loss time acquisition module is used to obtain the stage loss time corresponding to each stage according to the promoter loss time and the clearing sub-loss time, and to obtain the loss time of a cycle according to the stage loss time corresponding to each stage.

7. The periodic loss time calculation system based on radar and visual fusion according to claim 6 is characterized in that: The additional headway acquisition module comprises: A first time distance acquisition module is used to obtain the headway time of each vehicle and the saturated headway time of the queuing team according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane; The second time headway acquisition module is used to obtain the additional headway of each vehicle according to the headway of each vehicle and the saturated headway.

8. The periodic loss time calculation system based on radar and visual fusion according to claim 6 is characterized in that: The effective green light extension time acquisition module includes: A first extended time acquisition module is used to obtain the effective extended travel time of each vehicle that passes through the stop line during the yellow traffic light and passes through the intersection during the full red time in the clearing sub-stage according to the phase corresponding to each stage and the absolute time-space information of all vehicles in the traffic lane; The second extended time acquisition module is used to add up the effective extended passage time of each vehicle to obtain the effective green light extended time used by the vehicle in the clearing sub-stage in each stage.

9. The periodic loss time calculation system based on radar and visual fusion according to claim 8 is characterized in that: The clearing sub-loss time acquisition module includes: A signal light time acquisition module, used for acquiring the full red time corresponding to the red signal light and the yellow light time corresponding to the yellow signal light in each stage; A calculation module is used to calculate the clearing sub-loss time corresponding to the clearing sub-stage according to the all-red time, the yellow light time and the effective green light extension time.

10. The periodic loss time calculation system based on radar and visual fusion according to claim 7, characterized in that: The first time distance acquisition module includes: A head and tail vehicle acquisition module, used to acquire the head vehicle and the tail vehicle of the queuing team according to the phase corresponding to each stage and the absolute time and space information of all vehicles in the traffic lane; A saturated headway time calculation module is used to calculate the average headway time of all vehicles from the nth vehicle from the head vehicle to the tail vehicle according to the head vehicle and the tail vehicle, so as to obtain the saturated headway time; Wherein, n is a positive integer greater than 4.

Images