Real-time lane capacity calculation method and system based on radar and vision fusion

Abstract

The application discloses a real-time lane traffic capacity calculation method and system based on radar and video fusion. The method comprises the following steps: acquiring video image data and radar detection data; performing data fusion on the video image data and the radar detection data to obtain relative space-time information of each vehicle relative to a crossroad, and obtaining absolute space-time information of all vehicles at the crossroad according to the relative space-time information; acquiring traffic timing information and map information of the crossroad, and obtaining a saturation flow rate of a jth lane in a phase i and a stage green ratio of the jth lane in the phase i or a passable time proportion of the jth lane in the phase i according to the traffic timing information, the map information and the absolute space-time information; and obtaining a traffic capacity of the jth lane in the phase i according to the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation, in particular to a real-time lane capacity calculation method and system based on radar and vision fusion. BACKGROUND

[0002] Traffic congestion is a representative "urban disease" problem in the process of new urbanization construction in China, which causes great loss to social and economic development. The optimization of traffic conditions at intersections is the key to preventing and alleviating traffic congestion, and the estimation of traffic state parameters at intersections is an essential prerequisite for traffic optimization. The vehicle trajectory at the intersection can comprehensively and completely represent the traffic flow running state, containing rich traffic flow information. Among them, the lane capacity is one of the basic bases for road and traffic planning, design and traffic management, and also one of the basic bases for evaluating the traffic effect of various road and traffic facilities and management measures, which has important theoretical significance and practical value.

[0003] However, the traditional lane capacity calculation method fits the full sample data according to the sampling detection data to calculate the lane capacity, and the sampling detection data cannot accurately fit the full sample data, and errors are prone to occur in the fitting process, which leads to inaccurate calculation of the lane capacity and cannot be applied to the actual traffic environment.

[0004] CONTENT

[0005] The purpose of the present application is to solve the technical problem of inaccurate calculation of lane capacity caused by errors in the fitting process of the traditional lane capacity calculation method. To achieve the above purpose, the present application provides a real-time lane capacity calculation method and system based on radar and vision fusion.

[0006] The present application provides a real-time lane capacity calculation method based on radar and vision fusion, comprising:

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

[0008] Data fusion is performed on the video image data and the radar detection data to obtain the relative space-time information of each vehicle relative to the intersection, and the absolute space-time information of all vehicles at the intersection is obtained according to the relative space-time information;

[0009] Obtaining traffic timing information and map information of the intersection, and obtaining the saturation flow rate of the jth lane in phase i and the stage green ratio of the jth lane in phase i or the passable time proportion of the jth lane in phase i according to the traffic timing information, the map information and the absolute space-time information;

[0010] According to the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i, the traffic capacity of the jth lane in the phase i is obtained.

[0011] In one embodiment, the traffic timing information and the map information of the intersection are acquired, and according to the traffic timing information, the map information and the absolute space-time information, the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i are obtained, including:

[0012] According to the traffic timing information, the map information and the absolute space-time information, all the queuing vehicles of the jth lane in the phase i are obtained to form a queuing vehicle group of the jth lane in the phase i;

[0013] According to the headway corresponding to adjacent saturated through vehicles in the queuing vehicle group of the jth lane in the phase i, the saturated headway of the jth lane in the phase i is obtained;

[0014] According to the saturated headway of the jth lane in the phase i, the saturation flow rate of the jth lane in the phase i is obtained;

[0015] The saturation flow rate of the jth lane in the phase i is

[0016] h ij The saturated headway of the jth lane in the phase i is represented.

[0017] In one embodiment, the traffic timing information and the map information of the intersection are acquired, and according to the traffic timing information, the map information and the absolute space-time information, the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i are obtained, including:

[0018] According to the traffic timing information, the map information and the absolute space-time information, the stage effective green time of the jth lane in the phase i is obtained;

[0019] According to the traffic timing information and the map information, the cycle time of the cycle in which the jth lane in the phase i is located is obtained;

[0020] According to the ratio of the stage effective green time of the jth lane in the phase i to the cycle time of the cycle in which the jth lane in the phase i is located, the stage green ratio of the jth lane in the phase i is obtained.

[0021] In an embodiment, the phase effective green time of the jth lane in the phase i is obtained according to the traffic timing information, the map information and the absolute space-time information, including:

[0022] The green time of the jth lane in the phase i is obtained according to the traffic timing information and the map information.

[0023] The effective green extension time of the jth lane in the phase i in the clearance sub-phase is obtained according to the traffic timing information, the map information and the absolute space-time information.

[0024] The phase effective green time of the jth lane in the phase i is obtained according to the green time of the jth lane in the phase i and the effective green extension time of the jth lane in the phase i in the clearance phase.

[0025] In an embodiment, the queue vehicle set of the jth lane in the phase i is obtained according to the traffic timing information, the map information and the absolute space-time information, including:

[0026] The first queue vehicle set arriving at the jth lane in the phase i and waiting at a red signal light is obtained according to the traffic timing information, the map information and the absolute space-time information.

[0027] The second queue vehicle set arriving at the jth lane in the phase i and passing through at a green signal light is obtained according to the traffic timing information, the map information and the absolute space-time information.

[0028] The queue vehicle set of the jth lane in the phase i is obtained according to the first queue vehicle set and the second queue vehicle set.

[0029] In an embodiment, the application provides a real-time lane capacity calculation system based on radar and vision fusion, including:

[0030] A data acquisition module is configured to acquire video image data and radar detection data.

[0031] A space-time information acquisition module is configured to fuse the video image data and the radar detection data to obtain relative space-time information of each vehicle relative to an intersection, and obtain absolute space-time information of all vehicles at the intersection according to the relative space-time information.

[0032] a lane data acquisition module, configured to acquire traffic timing information and map information of the intersection, and obtain a saturation flow rate of a jth lane in a phase i and a stage green ratio of the jth lane in the phase i or a passable time proportion of the jth lane in the phase i according to the traffic timing information, the map information and absolute space-time information;

[0033] a capacity calculation module, configured to obtain a capacity of the jth lane in the phase i according to the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i.

[0034] In an embodiment, the lane data acquisition module comprises:

[0035] a queue formation module, configured to obtain all queuing vehicles of the jth lane in the phase i to form a queuing vehicle group of the jth lane in the phase i according to the traffic timing information, the map information and the absolute space-time information;

[0036] a saturation headway acquisition module, configured to obtain a saturation headway of the jth lane in the phase i according to a headway of adjacent vehicles corresponding to a saturation through the queuing vehicle group of the jth lane in the phase i;

[0037] a saturation flow rate calculation module, configured to obtain the saturation flow rate of the jth lane in the phase i according to the saturation headway of the jth lane in the phase i;

[0038] wherein the saturation flow rate of the jth lane in the phase i is

[0039] h ij represents the saturation headway of the jth lane in the phase i.

[0040] In an embodiment, the lane data acquisition module comprises:

[0041] a lane stage effective green time acquisition module, configured to obtain a stage effective green time of the jth lane in the phase i according to the traffic timing information, the map information and the absolute space-time information;

[0042] a lane cycle time acquisition module, configured to obtain a cycle time of a cycle in which the jth lane in the phase i is located according to the traffic timing information and the map information;

[0043] a lane stage green ratio acquisition module, configured to obtain the stage green ratio of the jth lane in the phase i according to a ratio of the stage effective green time of the jth lane in the phase i to the cycle time of the cycle in which the jth lane in the phase i is located.

[0044] In one embodiment, the lane phase effective green time obtaining module comprises:

[0045] a lane green time obtaining module, configured to obtain a green time of a jth lane in a phase i according to the traffic timing information and the map information;

[0046] a lane effective green extension time obtaining module, configured to obtain an effective green extension time of the jth lane in the phase i used by a vehicle in a clearance sub-phase according to the traffic timing information, the map information and the absolute space-time information;

[0047] a lane phase effective green time obtaining module, configured to obtain a phase effective green time of the jth lane in the phase i according to the green time of the jth lane in the phase i and the effective green extension time of the jth lane in the phase i used by the vehicle in the clearance sub-phase.

[0048] In one embodiment, the queue vehicle group forming module comprises:

[0049] a first queue vehicle group obtaining module, configured to obtain a first queue vehicle group which arrives at the jth lane in the phase i and stops waiting at a red signal light according to the traffic timing information, the map information and the absolute space-time information;

[0050] a second queue vehicle group obtaining module, configured to obtain a second queue vehicle group which arrives at the jth lane in the phase i and stops waiting at a green signal light according to the traffic timing information, the map information and the absolute space-time information;

[0051] a vehicle group obtaining module, configured to obtain the queue vehicle group of the jth lane in the phase i according to the first queue vehicle group and the second queue vehicle group.

[0052] In the real-time lane capacity calculation method and system based on radar and vision fusion, the absolute space-time information of the vehicle is obtained in combination with traffic timing information and map information, and the saturation flow rate of the jth lane in phase i and the stage green ratio of the jth lane in phase i or the passable time proportion of the jth lane in phase i are obtained. Then, the capacity of the jth lane in phase i is obtained based on the saturation flow rate of the jth lane in phase i and the stage green ratio of the jth lane in phase i or the passable time proportion of the jth lane in phase i. Through the real-time lane capacity calculation method based on radar and vision fusion, the traffic information of the intersection can be accurately and quickly obtained, the capacity of the jth lane in phase i can be calculated in real time, and the actual traffic conditions of each lane corresponding to each phase are fully considered. The traffic data can be completely obtained, the data collection speed is faster than that of the traditional method, the sample is wider, the timing scheme is provided for selection, the utilization rate of the intersection is improved, the saturation is reduced, and the traffic pressure is relieved.

[0053] The calculation process of the capacity of the jth lane in phase i in the real-time lane capacity calculation method based on radar and vision fusion provided by the application accurately calculates the capacity of each lane, improves the accuracy, and the precision is higher than that of the obtained fitting result. Therefore, through the real-time lane capacity calculation method based on radar and vision fusion provided by the application, the vehicle and road relationship in the real situation can be reflected, and the real capacity in each period can be obtained by analyzing and calculating in combination with the timing scheme information and lane information in the real situation. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 is a step flow schematic diagram of the real-time lane capacity calculation method based on radar and vision fusion provided by the application.

[0055] Figure 2 is a structural schematic diagram of the real-time lane capacity calculation system based on radar and vision fusion provided by the application. DETAILED DESCRIPTION

[0056] The technical scheme of the application will be further described in detail below with reference to the drawings and embodiments.

[0057] Please refer to Figure 1 The application provides a real-time lane capacity calculation method based on radar and vision fusion, which comprises the following steps:

[0058] S10, obtaining video image data and radar detection data;

[0059] S20, performing data fusion on the video image data and the radar detection data to obtain relative space-time information of each vehicle relative to the intersection, and obtaining absolute space-time information of all vehicles at the intersection according to the relative space-time information.

[0060] S30, obtain traffic timing information and map information of the intersection, and obtain the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i according to the traffic timing information, the map information and the absolute space-time information;

[0061] S40, obtain the traffic capacity of the jth lane in the phase i according to the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i.

[0062] In the embodiment, in S10, the video image data and the radar detection data can be obtained by a radar and video integrated machine. In S20, the video image is extracted frame by frame by a video processing software, and the frame-by-frame image is detected and recognized based on a deep learning method to obtain vehicle information based on a camera, such as a vehicle driving track, a vehicle head distance, a vehicle head time interval, a vehicle license plate number, a vehicle color, a vehicle license plate color and a vehicle model. The radar detection can obtain vehicle information based on radar, such as vehicle distance, vehicle direction, vehicle speed, vehicle acceleration and vehicle spatial position, in a bad detection environment and a bad environment.

[0063] According to the radar detection data, the relative distance of the vehicle relative to the intersection can be obtained. According to the video image data, the self attribute information of the vehicle (such as the license plate number, the license plate color, and the vehicle color, etc.) and the time information of each frame of image can be obtained. After data fusion of the video image data and the radar detection data, the relative space-time information of each vehicle relative to the intersection can be obtained. The relative space-time information is the space-time information relative to the intersection. The space-time information can be understood as the spatial position of the vehicle at different times, which specifically includes time information, vehicle position information, vehicle speed information, vehicle driving direction information, vehicle model information, and other multi-dimensional information. The relative space-time 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 space-time information can be mapped to the absolute space-time information. For example, in an embodiment, the high-precision map can provide the stop line contour position information of the intersection, the lane line contour position information, and the latitude and longitude information of the intersection, etc. The relative space-time information includes the relative spatial position of the vehicle relative to the intersection, and the relative spatial position can be converted into the absolute spatial position in the geographic coordinate system according to the distance of the vehicle relative to the intersection, so as to obtain the corresponding latitude and longitude information of the vehicle. Further, the vehicle can be marked on the map according to the corresponding latitude and longitude information of the vehicle, and the related geographic position information support can be provided. Therefore, by data fusion of the video image data and the radar detection data, the relative space-time information of each vehicle can be obtained, the relative space-time information of all vehicles passing through the intersection can be further obtained, and then the absolute space-time information of all vehicles passing through the intersection can be obtained.

[0064] In S30, the traffic timing information can be understood as providing the real twin information of the physical world signal control device, including but not limited to phase, stage, cycle, scheme, control mode, etc., and can also be understood as the urban traffic signal control information at the intersection, including the control time of red, green, and yellow light, etc.

[0065] The map information is obtained by actual surveying and mapping, and provides the real twin information of the physical world environment, including reference line, lane line, center line, curb, wavy guardrail, cement guardrail, overpass, traffic sign, contour sign, bridge pier, arrow, text, symbol, warning area, flow guide area, traffic light, stop position, pedestrian crossing, public transportation stop, speed reduction, in-intersection bicycle lane, no-parking area, manhole cover, parking space, traffic light pole, timing board, signal machine, flow guide island, overpass culvert, checkpoint, intersection center circle, tunnel wall, public transport harbor line, central separation belt, intersection surface, toll station elements, etc. The map information is high-precision map information, including but not limited to lane area, marking line position, channelization information, ground sign, etc.

[0066] The absolute space-time information of the vehicle obtained at the intersection includes time information and space information. According to the time information and the space information, and in comparison with the map information, the specific lane position information of the vehicle at a certain time can be obtained. According to the absolute space-time 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 known. According to the specific lane information of each vehicle, all vehicles corresponding to the jth lane in phase i can be known, and then the maximum flow number passing within a unit effective green time can be obtained, which can also be understood as the maximum traffic flow rate, and the saturation flow rate of the jth lane in phase i can be obtained. According to the traffic timing information and the map information, the stage green ratio of the jth lane in phase i can be known.

[0067] In S40, according to the traffic timing information of the intersection, the control mode of the signal lamp is known, and if the control mode has periodicity, the stage green ratio of the jth lane in phase i is obtained.

[0068] The traffic capacity of the jth lane in phase i is:

[0069] c ij =S ij ×λ ij

[0070] S ij represents the saturation flow rate of the jth lane in phase i, and λ ij represents the stage green ratio of the jth lane in phase i. Furthermore, according to the saturation flow rate of the jth lane in phase i and the stage green ratio of the jth lane in phase i, the traffic capacity of the jth lane in phase i can be accurately known.

[0071] If the signal control mode does not have periodicity, the lane passable time ratio of a time period corresponding to the jth lane in phase i is obtained.

[0072] The traffic capacity of the jth lane in phase i is:

[0073] c ij =S ij ×β ij

[0074] β ij represents the passable time ratio of the jth lane in phase i. Furthermore, according to the saturation flow rate of the jth lane in phase i and the passable time ratio of the jth lane in phase i, the traffic capacity of the jth lane in phase i can be accurately known.

[0075] In one embodiment, the lane passable time ratio in a time period can be obtained by sampling the time ratio for vehicle passing in a time period multiple times. Then, the passing capacity in a time period is obtained as the passing capacity of the jthlane in phase i in a time period based on the lane passable time ratio in a time period.

[0076] The real-time lane passing capacity calculation method based on radar and vision fusion provided in the application obtains the saturation flow rate of the jthlane in phase i and the stage green ratio of the jthlane in phase i or the passable time ratio of the jthlane in phase i by combining the absolute space-time information of the vehicle with the traffic timing information and the map information, and then obtains the passing capacity of the jthlane in phase i based on the saturation flow rate of the jthlane in phase i and the stage green ratio of the jthlane in phase i or the passable time ratio of the jthlane in phase i. Through the real-time lane passing capacity calculation method based on radar and vision fusion, the traffic information of the intersection can be accurately and quickly obtained in real time, the passing capacity of the jthlane in phase i can be calculated in real time, and the actual traffic conditions of each lane corresponding to each phase are fully considered, so that the traffic data can be completely obtained. Compared with the traditional method, the data collection speed is faster and the sample is wider, which provides a selection for the timing scheme, improves the utilization rate of the intersection, reduces the saturation, and relieves the traffic pressure.

[0077] The calculation process of the passing capacity of the jthlane in phase i in the real-time lane passing capacity calculation method based on radar and vision fusion provided in the application accurately calculates the passing capacity of each lane, thereby improving the accuracy and having higher precision than the fitting result. Therefore, through the real-time lane passing capacity calculation method based on radar and vision fusion provided in the application, the vehicle and road relationship in the real situation can be reflected, and the real passing capacity in each time period can be obtained by further analyzing and calculating the timing scheme information and the lane information in the real situation.

[0078] In one embodiment, S20, the video image data and the radar detection data are data fused to obtain the relative space-time information of each vehicle relative to the intersection, including:

[0079] S210, obtaining camera-based vehicle information according to the video image data;

[0080] S220, obtaining radar-based vehicle information according to the radar detection data;

[0081] S230, performing space-time fusion on the camera-based vehicle information and the radar-based vehicle information according to the radar-video fusion algorithm to obtain the relative space-time 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 space fusion process, conversion between the radar coordinate system and the camera coordinate system is needed. 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. By using the camera calibration method to calibrate the distance and angle of the vehicle detected by the radar, the internal parameters of the camera such as the focal length, the principal point coordinates and the distortion parameters can be obtained, the projection coordinates of the vehicle in the image can be obtained, the conversion from the radar coordinate system to the pixel coordinate system can be realized, and the space fusion of the video image data and the radar detection data can be completed.

[0083] In the time fusion process, the video image data and the radar detection data are synchronously collected in time to realize time fusion. When the sampling rate of the camera is different from the sampling rate of the radar, the sampling rate of the camera or the sampling rate of the radar can be used as the basis to perform sampling at the same sampling rate, one frame of image is collected by the camera each time, one frame of buffered data is selected from the radar, one frame of radar and camera fusion data is realized, and the time synchronization of the video image data and the radar detection data is ensured.

[0084] Through the time and space fusion of the camera-based vehicle information and the radar-based vehicle information, the relative space-time information of each vehicle relative to the intersection can be obtained. The relative space-time information can be understood as the relative space-time information of the vehicle relative to the intersection or the radar-camera integrated machine. The space-time information can be understood as the time information and the space information. The space-time information includes the time information, the vehicle position information, the vehicle speed information, the vehicle driving direction information, the vehicle model information, the vehicle license plate information and the vehicle color information of a vehicle at a certain time, and other multi-dimensional information. In this embodiment, through real-time observation and measurement by the radar-camera fusion technology, the influence of noise and delay acquisition is overcome, and the purposes of full space-time, high accuracy and low delay are achieved.

[0085] In one embodiment, S30, the traffic timing information and the map information of the intersection are obtained, and the saturation flow rate of the jth lane in phase i and the stage green ratio of the jth lane in phase i or the passable time ratio of the jth lane in phase i are obtained according to the traffic timing information, the map information and the absolute space-time information, including:

[0086] S310, all the queuing vehicles in the jth lane in phase i are obtained according to the traffic timing information, the map information and the absolute space-time information, to form a queuing vehicle fleet in the jth lane in phase i;

[0087] S320, the saturation headway of the jth lane in phase i is obtained according to the headway corresponding to the adjacent saturated passing vehicles in the queuing vehicle fleet of the jth lane in phase i;

[0088] S330, obtaining the saturated flow rate of the jth lane in phase i according to the saturated headway of the jth lane in phase i;

[0089] wherein the saturated flow rate of the jth lane in phase i is

[0090] h ij The saturated headway of the jth lane in phase i is represented.

[0091] In this embodiment, according to the absolute space-time information of all vehicles, combined with traffic timing information and map information, all vehicles queuing at the intersection can be obtained to form a queuing vehicle platoon in the jth lane in phase i. In this embodiment, the phase and lane are specifically limited, and the corresponding data information of the jth lane in phase i can be obtained through data screening, so that the lane traffic capacity calculation can be accurately to a specific phase and lane, and reliable data can be better provided for traffic management.

[0092] The queuing vehicles form a queuing vehicle platoon, the head and tail of the queuing vehicle platoon are confirmed, and the saturated through vehicles in the queuing vehicle platoon are screened. The headway of the adjacent two saturated through vehicles in the queuing vehicle platoon is obtained. The headway can be understood as the difference between the time experienced by the head of the nth vehicle and the head of the nth+1 vehicle to reach the observation line. The observation line can be understood as the vehicle stop line. The saturated through vehicle can be understood as a vehicle that does not have loss time such as reaction time and vehicle acceleration time during the corresponding green time of the jth lane in phase i. The unsaturated through vehicle can be understood as a vehicle that has loss time such as reaction time and vehicle acceleration time during the corresponding green time of the jth lane in phase i. By screening a plurality of vehicles in the queuing vehicle platoon, saturated through vehicles and unsaturated through vehicles can be screened.

[0093] According to the headway of the adjacent saturated through vehicles in the queuing vehicle platoon of the jth lane in phase i, the headway of all saturated through vehicles can be obtained, and then the saturated headway of the jth lane in phase i can be obtained. The saturated headway of the jth lane in phase i can be understood as the average of the headway of the nth vehicle and the subsequent vehicles after a period of time after the green light is on, without the influence of starting reaction and acceleration effect.

[0094] The saturated flow rate can be understood as the maximum flow number passed in unit effective green time. According to the calculation formula, the saturated headway of the jth lane in phase i is converted into the saturated flow rate of the jth lane in phase i per unit time.

[0095] In one embodiment, S310, according to the traffic timing information, the map information and the absolute space-time information, all the queuing vehicles in the jth lane in the phase i are obtained to form a queuing vehicle group in the jth lane in the phase i, including:

[0096] S311, according to the traffic timing information, the map information and the absolute space-time information, a first queuing vehicle set which arrives at the jth lane in the phase i at the red signal light and stops waiting is obtained;

[0097] S312, according to the traffic timing information, the map information and the absolute space-time information, a second queuing vehicle set which arrives at the jth lane in the phase i at the green signal light and stops queuing through is obtained;

[0098] S313, according to the first queuing vehicle set and the second queuing vehicle set, a queuing vehicle group in the jth lane in the phase i is obtained.

[0099] In this embodiment, the timing time of the red signal light and the green signal light can be known according to the traffic timing information. The vehicles which arrive at the jth lane in the phase i at the red signal light and stop waiting to form a first queuing vehicle set can be understood as the vehicles which arrive at the jth lane in the phase i at the red light and completely stop to queue. The vehicles which arrive at the jth lane in the phase i at the green signal light and stop queuing through to form a second queuing vehicle set can be understood as the vehicles which arrive at the jth lane in the phase i at the green light but stop queuing because the queuing vehicles have not completely dissipated. The first queuing vehicle set and the second queuing vehicle set are both the vehicles which queue in the jth lane in the phase i, and the continuous vehicle group with the parking delay time greater than 0. According to the first queuing vehicle set and the second queuing vehicle set, the queuing vehicle group in the jth lane in the phase i can be obtained. Through the method steps in this embodiment, the traffic timing information, the map information and the vehicle absolute space-time information are fully combined together to obtain the queuing vehicle group in a certain lane of a certain phase. The real-time fusion data based on radar and vision fully reflect the specific driving conditions of the vehicles in a certain lane of a certain phase, which is not limited to theoretical statistical sampling detection.

[0100] In one embodiment, S320, according to the headway corresponding to the adjacent vehicles in the queuing vehicle group in the jth lane in the phase i, a saturated headway in the jth lane in the phase i is obtained, including:

[0101] S321, the headway of all the queuing vehicles in the queuing vehicle group in the jth lane in the phase i, the head vehicle and the tail vehicle are obtained;

[0102] S322, according to the head vehicle and the tail vehicle, the average value of the headway of all the vehicles from the nth vehicle to the tail vehicle is calculated to obtain the saturated headway in the jth lane in the phase i.

[0103] In this embodiment, the headway of all the vehicles in the queue of the jthlane in the ithphase can be understood as the difference between the time taken by the nthvehicle and the nth+1vehicle in the jthlane in the ithphase to reach the observation line (vehicle stop line), i.e. n = t n+1 -t n .

[0104] The saturated headway of the jthlane in the ithphase The saturated headway h ij The formula represents the average of the headways of the m+1-n vehicles starting from the nthvehicle. The value of n can be a positive integer such as 4 or 5 or 6, or can be determined according to the actual driving situation, which can avoid the problem of inaccurate calculation caused by the influence of the start-up reaction and acceleration effect on the first 4 vehicles in the queue.

[0105] In one embodiment, the first vehicle in the queue is the first vehicle, and the average of the headways of all the saturated vehicles from the fifth vehicle to the end of the queue is calculated as the saturated headway h ij .

[0106] In one embodiment, when the number of queue vehicles in a corresponding phase of an intersection is small or there are no queue vehicles, the saturated flow rate calculated by the saturated headway in other different time situations can be obtained as the saturated flow rate of the jthlane in the ithphase, and the corresponding capacity of the jthlane in the ithphase can be obtained.

[0107] In one embodiment, S30, the traffic timing information and map information of the intersection are obtained, and the saturated flow rate of the jthlane in the ithphase and the stage green ratio of the jthlane in the ithphase or the passable time ratio of the jthlane in the ithphase are obtained according to the traffic timing information, the map information and the absolute space-time information, which further comprises:

[0108] S340, the stage effective green time of the jthlane in the ithphase is obtained according to the traffic timing information, the map information and the absolute space-time information;

[0109] S350, the cycle time of the cycle in which the jthlane in the ithphase is located is obtained according to the traffic timing information and the map information;

[0110] S360, the stage green ratio of the jthlane in the ithphase is obtained according to the ratio of the stage effective green time of the jthlane in the ithphase to the cycle time of the cycle in which the jthlane in the ithphase is located.

[0111] In this embodiment, one cycle can be understood as the time required for the signal light color to change according to the set signal phase sequence for one cycle. One cycle contains n stages or n phases, and the phase represents a momentary state, and the stage represents the duration of the phase state, and one phase corresponds to one stage. Phase i is a certain phase in a cycle, for example, it can be east-west straight, east-west left, north-south straight, north-south left, etc. The jth lane is a certain lane corresponding to the jth lane in the phase i momentary state. The cycle length can be understood as the time required for the signal light color to change according to the set signal phase sequence for one cycle. The cycle length is calculated as follows:

[0112] s i represents the ith stage duration, n represents the number of stages or phases contained in the cycle, and the cycle length is the sum of the stage durations of all n stages in the cycle.

[0113] The stage effective green light duration can be understood as the effective traffic time period of the vehicle in the jth lane in the phase i.

[0114] The stage green ratio of the jth lane in the phase i can be understood as the ratio of the effective green light duration corresponding to the jth lane in the phase i to the cycle length, and the calculation method is as follows:

[0115]

[0116] In one embodiment, S340, according to the traffic timing information, the map information and the absolute space-time information, the stage effective green light duration of the jth lane in the phase i is obtained, including:

[0117] S341, according to the traffic timing information and the map information, the green light time of the jth lane in the phase i is obtained;

[0118] S342, according to the traffic timing information, the map information and the absolute space-time information, the effective green light extension time used by the vehicle in the clearing sub-stage of the jth lane in the phase i is obtained;

[0119] S343, according to the green light time of the jth lane in the phase i and the effective green light extension time used by the vehicle in the clearing sub-stage of the jth lane in the phase i, the stage effective green light duration of the jth lane in the phase i is obtained.

[0120] In this embodiment, the green light time of the jth lane in the phase i can be understood as the time that the vehicle can pass in the jth lane in the phase i state, which is obtained by calculating the length of the green light lighting time.

[0121] The phase effective green light duration includes the green light time and the effective green light extension time of the clearance sub-phase in the phase used by the vehicle. The effective green light extension time used by the vehicle can be understood as the yellow light time and the all-red time effectively used by the vehicle, for example: the vehicle passes the stop line at the last moment of the yellow light, and passes the intersection at the last moment of the all-red time, which is the completely effective utilization time, and there is no loss of effective utilization of part of the yellow light and all-red time. The effective green light extension time can be obtained based on the absolute space-time information obtained by radar and vision fusion data, and the time and position of each vehicle in the jth lane are tracked, so that the effective green light extension time used by the vehicle in the clearance sub-phase in the phase can be accurately obtained. Then, the green light time in the phase and the effective green light extension time used by the vehicle are added to obtain the phase effective green light duration of the jth lane in the phase i.

[0122] See Figure 2 In one embodiment, the application provides a real-time lane capacity calculation system 100 based on radar and vision fusion. The real-time lane capacity calculation system 100 based on radar and vision fusion includes a data acquisition module 10, a space-time information acquisition module 20, a lane data acquisition module 30, and a capacity calculation module 40. The data acquisition module 10 is used to acquire video image data and radar detection data. The space-time information acquisition module 20 is used to fuse the video image data and the radar detection data, obtain the relative space-time information of each vehicle relative to the intersection, and obtain the absolute space-time information of all vehicles at the intersection according to the relative space-time information. The lane data acquisition module 30 is used to acquire traffic timing information and map information of the intersection, and according to the traffic timing information, the map information and the absolute space-time information, to obtain the saturation flow rate of the jth lane in the phase i and the phase green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i. The capacity calculation module 40 is used to obtain the capacity of the jth lane in the phase i according to the saturation flow rate of the jth lane in the phase i and the phase green ratio of the jth lane in the phase i or the passable time proportion of the jth lane in the phase i.

[0123] In this embodiment, the related description of the data acquisition module 10 can refer to the related description of S10 in the above embodiment. The related description of the space-time information acquisition module 20 can refer to the related description of S20 in the above embodiment. The related description of the lane data acquisition module 30 can refer to the related description of S30 in the above embodiment. The related description of the capacity calculation module 40 can refer to the related description of S40 in the above embodiment.

[0124] In one embodiment, the lane data obtaining module 30 comprises a queuing vehicle platoon forming module, a saturated headway obtaining module, and a saturated flow rate calculating module. The queuing vehicle platoon forming module is configured to obtain all queuing vehicles in the jthlane in phase i according to the traffic timing information, the map information, and the absolute space-time information, and form a queuing vehicle platoon in the jthlane in phase i. The saturated headway obtaining module is configured to obtain a saturated headway of the jthlane in phase i according to a headway corresponding to a saturated adjacent vehicle in the queuing vehicle platoon of the jthlane in phase i. The saturated flow rate calculating module is configured to obtain a saturated flow rate of the jthlane in phase i according to the saturated headway of the jthlane in phase i.

[0125] wherein the saturated flow rate of the jthlane in phase i is

[0126] h ij denotes the saturated headway of the jthlane in phase i.

[0127] In this embodiment, the related description of the queuing vehicle platoon forming module can refer to the related description of S310 in the above embodiment. The related description of the saturated headway obtaining module can refer to the related description of S320 in the above embodiment. The related description of the saturated flow rate calculating module can refer to the related description of S330 in the above embodiment.

[0128] In one embodiment, the lane data obtaining module 30 comprises a lane phase effective green time obtaining module, a lane cycle time obtaining module, and a lane phase green split obtaining module. The lane phase effective green time obtaining module is configured to obtain a phase effective green time of the jthlane in phase i according to the traffic timing information, the map information, and the absolute space-time information. The lane cycle time obtaining module is configured to obtain a cycle time of a cycle in which the jthlane in phase i is located according to the traffic timing information and the map information. The lane phase green split obtaining module is configured to obtain a phase green split of the jthlane in phase i according to a ratio of the phase effective green time of the jthlane in phase i to the cycle time of the cycle in which the jthlane in phase i is located.

[0129] In this embodiment, the related description of the lane phase effective green time obtaining module can refer to the related description of S340 in the above embodiment. The related description of the lane cycle time obtaining module can refer to the related description of S350 in the above embodiment. The related description of the lane phase green split obtaining module can refer to the related description of S360 in the above embodiment.

[0130] In one embodiment, the lane phase effective green time obtaining module comprises a lane green time obtaining module, a lane effective green extension time obtaining module, and a lane phase effective green time obtaining module. The lane green time obtaining module is configured to obtain the green time of the jthlane in phase i according to the traffic timing information and the map information. The lane effective green extension time obtaining module is configured to obtain the effective green extension time of the jthlane in phase i in the clearance sub-phase used by the vehicle according to the traffic timing information, the map information, and the absolute space-time information. The lane phase effective green time obtaining module is configured to obtain the phase effective green time of the jthlane in phase i according to the green time of the jthlane in phase i and the effective green extension time of the jthlane in phase i in the clearance sub-phase used by the vehicle.

[0131] In this embodiment, the related description of the lane green time obtaining module can refer to the related description of S341 in the above embodiment. The related description of the lane effective green extension time obtaining module can refer to the related description of S342 in the above embodiment. The related description of the lane phase effective green time obtaining module can refer to the related description of S343 in the above embodiment.

[0132] In one embodiment, the queuing vehicle set obtaining module comprises a first queuing vehicle set obtaining module, a second queuing vehicle set obtaining module, and a vehicle set obtaining module. The first queuing vehicle set obtaining module is configured to obtain a first queuing vehicle set that arrives at the jthlane in phase i and stops waiting during the red signal according to the traffic timing information, the map information, and the absolute space-time information. The second queuing vehicle set obtaining module is configured to obtain a second queuing vehicle set that arrives at the jthlane in phase i and stops queuing through during the green signal according to the traffic timing information, the map information, and the absolute space-time information. The vehicle set obtaining module is configured to obtain the queuing vehicle set of the jthlane in phase i according to the first queuing vehicle set and the second queuing vehicle set.

[0133] In this embodiment, the related description of the first queuing vehicle set obtaining module can refer to the related description of S311 in the above embodiment. The related description of the second queuing vehicle set obtaining module can refer to the related description of S312 in the above embodiment. The related description of the vehicle set obtaining module can refer to the related description of S313 in the above embodiment.

[0134] In each of the above embodiments, the specific order or hierarchy of steps in the processes disclosed is an example of an example order or hierarchy of steps. Based upon design preference, it is understood that the specific order or hierarchy of steps in the processes can be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in exemplary order and are not intended to be limited to the specific order or hierarchy presented.

[0135] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, and steps described in connection with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

[0136] The various illustrative logical blocks, modules, and steps described in connection with the embodiments disclosed herein can be implemented or performed by a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor can be a microprocessor, but in the alternative, the general purpose processor can be any conventional processor, controller, microcontroller, or state machine. A processor can also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0137] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium can be coupled to the processor, such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium can reside as discrete components in a user terminal. The previous description of the specific embodiments will be understood to be illustrative only of the principles of the present application. Numerous modifications of the methods and algorithms described herein, as well as other adaptive applications of the specific embodiments disclosed herein, will be apparent in light of this disclosure to those of ordinary skill in the art, and such modifications will be within the scope of the application as defined in the following claims. Accordingly, the application should not be limited to the above described embodiments.

[0138] The above detailed description has shown, described, and pointed out the aspects of the present application as applied to the preferred embodiments. Since the present application can be embodied in other forms, the foregoing description should be considered as merely illustrative of the principles of the application, and not in limitation of the scope of the application as set forth in the appended claims.

Claims

1. A real-time lane capacity calculation method based on radar and vision fusion, characterized in that, The method comprises: acquiring video image data and radar detection data; performing data fusion on the video image data and the radar detection data to obtain relative space-time information of each vehicle relative to the intersection, and obtaining absolute space-time information of all vehicles at the intersection according to the relative space-time information; acquire traffic timing information and map information of the intersection, and acquire phase i In the first j of the lane, and phase i In the first j of the lane, and phase i In the first j of the lane, and phase The method comprises: obtaining a phase according to the traffic timing information, the map information, and the absolute space-time information i In the method j The method comprises: obtaining a queue of all vehicles on the lane according to the traffic timing information, the map information, and the absolute space-time information i In the method j The method comprises: obtaining a queue of all vehicles on the lane according to the traffic timing information, the map information, and the absolute space-time information According to the traffic timing information, the map information, and the absolute spatio-temporal information, a first set of queuing vehicles that arrive at the phase i in the middle of the first lane and wait for a red signal light j ​ According to the traffic timing information, the map information, and the absolute space-time information, a second set of queuing vehicles that arrive at the phase i in the middle of the first lane and stop queuing through j the second lane obtaining the phase according to the first set of queued vehicles and the second set of queued vehicles i in the middle of the j lane According to the phase i In the phase j The headway of the adjacent saturated through vehicles in the queue of the lane of the first i In the phase j The headway of the saturated vehicles in the lane of the first According to the phase i In the phase j of the saturation headway of the lane, the phase i In the phase j of the saturation flow rate of the lane; Wherein the phase i In the middle of j The saturated flow rate of the lane is ; h ij representing the phase i in the first j saturated headway of the lane According to the phase i In the phase j The saturation flow rate of the lane in the phase i In the phase j The stage green ratio of the lane in the phase i In the phase j The passable time proportion of the lane in the phase i In the phase j The traffic capacity of the lane in the phase.

2. The real-time lane throughput calculation method according to claim 1, characterized in that, The method comprises: The traffic timing information and the map information of the intersection are acquired, and a phase i In the first j The saturation flow rate of the lane in the phase i In the first j The stage green ratio of the lane in the phase i In the first j The passable time proportion of the lane in the phase, comprising: According to the traffic timing information, the map information, and the absolute space-time information, a phase i In the middle of the j Lane phase effective green time According to the traffic timing information and the map information, a phase is obtained i In the middle of the j Article lane period length of the cycle in which the cycle is located; According to the phase i The Middle j The effective green light duration for each lane in a given phase i The Middle j The phase is obtained by comparing the cycle length of each lane with the cycle length of the current lane. i The Middle j The green light ratio of each lane.

3. The real-time lane capacity calculation method based on radar and vision fusion according to claim 2, characterized in that obtaining a phase according to the traffic timing information, the map information, and the absolute space-time information i In the first j The phase effective green time of the lane includes: According to the traffic timing information and the map information, a phase i In the middle of j The green light time of the lane According to the traffic timing information, the map information, and the absolute space-time information, a phase i In the first j The effective green light extension time used by the vehicle in the clear sub-stage of the lane According to the phase i In the phase j The effective green light extension time used by the vehicle in the clearance sub-phase of the first lane in the phase i In the phase j The stage effective green light duration of the first lane in the phase i In the phase j The stage effective green light duration of the first lane in the phase 4. A real-time lane capacity calculation system based on radar and vision fusion, characterized in that, The method comprises: a data acquisition module configured to acquire video image data and radar detection data; a space-time information acquisition module configured to perform data fusion on the video image data and the radar detection data to obtain relative space-time information of each vehicle relative to the intersection, and obtain absolute space-time information of all vehicles at the intersection according to the relative space-time information; a lane data acquisition module, configured to acquire traffic timing information and map information of the intersection, and obtain a phase of a lane according to the traffic timing information, the map information and the absolute space-time information i in the first j lane, a saturation flow rate of the lane and the phase i in the first j lane, a stage green ratio of the lane or the phase i in the first j lane, a passable time proportion of the lane a capacity calculation module configured to obtain the capacity of the phase according to the saturated flow rate of the first lane in the phase i the first lane in the phase j the stage green ratio of the first lane in the phase or the capacity of the phase i the first lane in the phase j the first lane in the phase i the first lane in the phase j the first lane in the phase i the first lane in the phase j the first lane in the phase The lane data acquisition module comprises: a queuing vehicle fleet forming module configured to obtain, according to the traffic timing information, the map information and the absolute space-time information, a phase i in the first j lane of all the queuing vehicles, form a phase i in the first j lane of the queuing vehicle fleet; a saturated headway acquisition module configured to acquire a headway of a saturated vehicle in the phase i in the phase j of the lane in the queue of the lane, and acquire a headway of a saturated vehicle in the phase i in the phase j of the lane a saturated flow rate calculation module for obtaining a saturated flow rate of the phase i in the first lane according to the phase j in the first lane according to the phase i in the first lane according to the phase j in the first lane according to the phase Wherein the phase i In the middle of the j The saturation flow rate of the lane is ; h ij representing the phase i in the first j saturated headway of the lane The queue formation module comprises: a first queuing vehicle set obtaining module, configured to obtain, according to the traffic timing information, the map information and the absolute space-time information, a first queuing vehicle set which arrives at a lane of the phase i in the middle of a red signal light and waits j ​ a second queuing vehicle set obtaining module, configured to obtain, according to the traffic timing information, the map information and the absolute space-time information, a second queuing vehicle set which arrives at the phase i in the green signal light time and stops queuing through the lane j in the first phase a fleet obtaining module, configured to obtain the phase according to the first queuing vehicle set and the second queuing vehicle set i in a middle j lane of the queuing fleet.

5. The real-time lane throughput calculation system of claim 4, wherein, The lane data acquisition module comprises:

6. The real-time lane capacity calculation system based on radar and vision fusion according to claim 5, The lane phase effective green light duration acquisition module is configured to acquire the phase effective green light duration of the lane according to the traffic timing information, the map information, and the absolute space-time information. i In the first j In the first The lane cycle length acquisition module is configured to acquire, according to the traffic timing information and the map information, a cycle length of a phase in which a lane belongs i In the first j Clause, the cycle length of the phase in which the lane belongs The lane phase green ratio acquisition module is configured to acquire the phase green ratio of the lane according to the phase i of the lane j in the phase i of the lane j in the cycle of the lane i of the lane j in the phase The lane phase effective green time acquisition module comprises: characterized in that ​ The lane green light time acquisition module is configured to acquire the green light time of a phase according to the traffic timing information and the map information. i In the first j Clause, the green light time of a lane. The lane effective green light extension time acquisition module is configured to acquire a phase i In the first j The lane effective green light extension time is used by a vehicle in a clear sub-stage of the lane. The lane phase effective green time obtaining module is configured to obtain the phase i The lane phase effective green time obtaining module is configured to obtain the phase j The lane phase effective green time obtaining module is configured to obtain the phase i The lane phase effective green time obtaining module is configured to obtain the phase j The lane phase effective green time obtaining module is configured to obtain the phase i The lane phase effective green time obtaining module is configured to obtain the phase j The lane phase effective green time obtaining module is configured to obtain the phase

Images