Intelligent city planning management system and method based on big data

Abstract

The invention discloses an intelligent city planning management system and method based on big data, and relates to the technical field of big data, and the method comprises the steps: obtaining a plane layout diagram of a target intersection and a historical monitoring video, and obtaining a steering proportion vector corresponding to each lane; according to the monitoring video, extracting a target video clip in the monitoring video, and further calculating the current congestion degree of each lane group; obtaining an effective signal corresponding to each lane and allowing a vehicle on the lane to pass through the target intersection, and obtaining a timing coefficient of the effective signal corresponding to each lane; and obtaining historical timing data of the effective signal corresponding to each lane, and adjusting the timing data of the effective signal corresponding to each lane according to the timing coefficient. According to the invention, reasonable and targeted timing optimization is carried out on each signal on the signal lamp according to the actual situation of the intersection, a more convenient traffic environment is provided for driving residents, the traffic efficiency of the intersection is improved, and traffic jam is relieved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a big data-based intelligent city planning management system and method. Background Art

[0002] Urban planning and management play an important role in ensuring the orderly progress of urban construction, improving the overall image and quality of the city, and facilitating the transportation of residents with private cars. With the increase in the number of residents traveling by car, traffic lights have exposed some problems in actual operation. Since the timing schemes of various signals on many traffic lights are relatively fixed, they cannot be adjusted in time according to the actual traffic flow changes in different periods, resulting in road congestion in urban traffic. During peak hours in the morning and evening, the traffic volume increases greatly, but the timing of the signal lights may be the same as that during off-peak hours, resulting in increased congestion at intersections. In the off-peak stage, due to the failure to adjust the timing of the signal lights accordingly, vehicles may wait too long, and some intersections may also have empty waiting. Therefore, according to the actual situation of the intersection, the timing of each signal on the signal light is reasonably and targetedly optimized to provide a more convenient traffic environment for residents who travel by car, which helps to improve the traffic efficiency of the intersection, alleviate traffic congestion, and enhance the happiness of residents' travel. Summary of the invention

[0003] The purpose of the present invention is to provide a smart city planning management system and method based on big data to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions: A smart city planning and management method based on big data, comprising the following steps: Step S100: obtaining a plan layout diagram of the target intersection, the plan layout diagram including a number of lanes connected to the target intersection, obtaining a historical surveillance video of the target intersection, and obtaining a steering ratio vector corresponding to each lane according to a target steering behavior of vehicles on each lane after passing the target intersection; Step S200: combining a plurality of lanes into a lane group, extracting a target video segment from the surveillance video, and calculating the current congestion level of each lane group according to the length of time each vehicle stays at the target intersection; Step S300: Obtaining the effective signal corresponding to each lane, allowing vehicles in the lane to pass through the target intersection, obtaining the characteristic stay time corresponding to each lane according to the target turning behavior and turning ratio vector of the vehicles in each lane, and obtaining the timing coefficient of the effective signal corresponding to each lane according to the congestion level; For example, at an intersection, when the green light of the east-west through lane is on, this signal is the effective signal of the lane, and vehicles going straight in the east-west direction can pass through the intersection at this time; Step S400: Acquire historical timing data of the effective signal corresponding to each lane, and adjust the timing data of the effective signal corresponding to each lane according to the timing coefficient.

[0005] Furthermore, step S100 includes: Step S110: Obtain surveillance videos from the previous T days, and obtain the target intersection area TIR and each lane area in the surveillance video according to the floor plan; obtain the rectangular bounding box corresponding to a vehicle in the surveillance video as the vehicle area CR of the vehicle, and obtain the time period in which TIR∩CR is not empty, and take the minimum time in the time period as M1, and the maximum time as M2; take the position of the center point of the vehicle area CR as the midpoint position, set the time period TL0, and take the midpoint position of the time of the vehicle starting from the minimum time M1 and the time period TL0 before as PT1 , the midpoint position at the minimum moment M1 is taken as P1, and the direction from the midpoint position PT1 to the midpoint position P1 is taken as the moving direction D1; the midpoint position at the maximum moment M2 of a vehicle is taken as P2, and the midpoint position at the moment of the time period TL0 after the maximum moment M2 is taken as PT2, and the direction from the midpoint position P2 to the midpoint position PT2 is taken as the moving direction D2. The target turning behaviors include going straight, turning right, turning left, and turning around; according to the angle required to rotate clockwise from the moving direction D1 to the moving direction D2, the turning behavior to be determined of a vehicle is determined; Among them, the rectangular bounding box corresponding to a certain vehicle can be obtained through target detection algorithms such as Faster R-CNN and YOLO; these algorithm models are trained with a large amount of image data and can identify vehicles in images. When the model outputs the position of the vehicle in the image, it is expressed in the form of a rectangular bounding box. For surveillance videos, target detection can be performed continuously on each frame of the image, thereby tracking the position and movement of the vehicle in real time; Step S120: Determine the set of vehicle turning behaviors allowed for each lane according to traffic rules; obtain the vehicle region CR1 of a certain vehicle at the minimum time M1, obtain the intersection area between the vehicle region CR1 and a certain lane region, if the intersection area is greater than the lane intersection area threshold, obtain the lane Lan corresponding to the certain lane region, and use the certain vehicle as the target vehicle on the lane Lan, if the set of vehicle turning behaviors allowed for the corresponding lane Lan includes the to-be-determined turning behavior of the certain vehicle, use the to-be-determined turning behavior as the target turning behavior of the certain vehicle; When a vehicle turns, if most of the vehicle is in a certain lane, it can more accurately determine which lane the vehicle is turning from, thereby facilitating relevant calculations and analysis of vehicles in that lane; Step S130: Obtain the target vehicles corresponding to each lane in the monitoring video, take the total number of target vehicles corresponding to a lane as SUM0, and according to the target turning behavior of each target vehicle on a lane, collect the number of vehicles corresponding to the same target turning behavior to obtain the total number of vehicles corresponding to each target turning behavior, and according to the total number of target vehicles SUM0, obtain the steering ratio corresponding to each target turning behavior on a lane, and establish a steering ratio vector V0 corresponding to a lane.

[0006] Due to different road conditions at each intersection, when the left turn indicator is green, the vehicle may turn around or turn left. In this scheme, the steering ratio vector V0 corresponding to a lane is [R1, R2, R3, R4], where R1, R2, R3 and R4 represent the proportion of the straight, right turn, left turn and U-turn directions of the vehicle in a lane, respectively, and R1, R2, R3 and R4 are all between 0 and 1, R1+R2+R3+R4=1.

[0007] Further, step S200 includes: Step S210: All adjacent lanes with the same vehicle-allowed turning behavior are regarded as a lane group, and the lane group area in the monitoring video is obtained; the valid signal corresponding to a lane group that allows vehicles in the lane group to pass through the target intersection is obtained, and the total effective signal duration TP corresponding to the valid signal is obtained; the monitoring video segment in the valid signal is intercepted, and the target video segment with the closest distance to the current time and the duration of the monitoring video segment equal to the total effective signal duration TP is obtained; Step S220: Take the vehicle area corresponding to a certain vehicle in the target video clip at time m as CR0, obtain the intersection area of ​​the vehicle area CR0 and a certain lane group area, if the intersection area is greater than the preset lane group intersection area threshold and satisfies TIR∩CR0 is not empty at time m+1, where TIR is the target intersection area, then take the certain vehicle as the feature vehicle, and the lane group corresponding to the certain lane group area as Lag; then obtain the total number of feature vehicles corresponding to the lane group Lag in the target video clip, and sort the feature vehicles in chronological order from front to back according to the moment when each feature vehicle satisfies TIR∩CR1 for the first time; and take the total duration for which a certain feature vehicle satisfies TIR∩CR1 is not empty as the length of stay of the certain feature vehicle in the target intersection area; Step S230: Get any two feature vehicles a and b with adjacent serial numbers. Feature vehicles a and b are M and B respectively at the moment when TIR∩CR1 is not empty for the first time. a and M b , the time M a and M bThe absolute value of the difference is used as the time difference to obtain all the time differences corresponding to a lane group, and the current congestion level of a lane group is obtained according to the stay time corresponding to each characteristic vehicle. , and normalized, where K RT is the residence time coefficient, K MD is the time difference coefficient, G is the total number of characteristic vehicles corresponding to a lane group, H is the total number of time differences corresponding to a lane group, G=H+1, RT g is the dwell time corresponding to the g-th characteristic vehicle, MD h is the hth time difference.

[0008] If the dwell time is getting shorter and shorter, and the time difference between two characteristic vehicles with adjacent serial numbers is getting longer and longer, it is considered that there are fewer vehicles on the lane at this time, and it is not too crowded; the congestion level ranges from [0,1], and the larger the congestion level, the more vehicles there are on the lane; in this scheme, the congestion level is calculated based on the dwell time of characteristic vehicles within a period of time and the time difference between two characteristic vehicles with adjacent serial numbers, because the data changes of dynamic vehicles at the intersection can better reflect the congestion level of the lane; Furthermore, step S300 includes: Step S310: according to the target turning behavior of each vehicle on a certain lane in the target intersection area, the number of vehicles corresponding to the same target turning behavior is collected, and the total number of vehicles corresponding to a certain target turning behavior is obtained, and according to the stay time of each vehicle, the average stay time corresponding to the certain target turning behavior is obtained, and then the stay time vector is obtained, and the dot product of the turning ratio vector corresponding to the certain lane and the stay time vector is used as the characteristic stay time corresponding to the certain lane; The dwell time vector is obtained based on the dwell time of the vehicle at the target intersection. The dwell time vector S0 corresponding to a lane is [s1, s2, s3, s4]; for example, if a lane is only allowed to turn left or make a U-turn at the target intersection, and the corresponding steering ratio vector V0 of the lane is [0, 0, 0.6, 0.4], and the dwell time vector S0 is [0, 0, 8, 10], then the characteristic dwell time corresponding to a lane is the dot product of V0 and S0, which is 0*0+0*0+0.6*8+0.4*10=8.8, in seconds; Step S320: If a lane is included in a lane group, the congestion level of the lane group is taken as the congestion level of the lane, and according to the characteristic stay time corresponding to the lane, the timing coefficient of the effective signal corresponding to each lane is obtained as C=k*Y*Z, and normalized, where k is the timing correlation coefficient, Y is the congestion level corresponding to the lane, and Z is the characteristic stay time corresponding to the lane.

[0009] The timing coefficient indicates the correlation coefficient that the effective signal corresponding to the traffic light needs to be re-timing. The timing coefficient value range is [0,1]. When it is close to 0, it means that the traffic flow on the lane in that direction is relatively small, or the currently allocated green light time is too long, resulting in a waste of time. The current corresponding effective signal needs to be reduced in seconds. When it is close to 1, it means that the traffic flow on the lane in that direction is relatively large, or the currently allocated green light time is too short, resulting in traffic congestion, indicating that the corresponding effective signal needs to be increased in seconds.

[0010] Furthermore, step S400 includes: Step S410: Obtain the valid signal corresponding to each lane, and according to the total effective signal duration of each valid signal, intercept all monitoring video clips corresponding to each valid signal; take the total effective signal duration of a valid signal corresponding to a lane as SD, and according to step S200, obtain the congestion degree corresponding to a lane in each monitoring video clip; perform a first mark on the monitoring video clips whose congestion degree is less than the first congestion degree, and obtain the minimum signal duration T1=SD*(1- ), K1 is the first signal coefficient, K1>0; the surveillance video clips with a congestion level greater than the second congestion level are marked for the second time, and according to the minimum total number of characteristic vehicles W2 corresponding to the second marked surveillance video clips, and the characteristic stay time S of a lane, the maximum signal time T2=SD* , K2 is the second signal coefficient, K2>0; The value of the minimum signal duration T1 should be as large as possible while being less than the total effective signal duration SD. This is because the duration after re-timing should not differ greatly from the total effective signal duration SD. -x In the example, when the value range of x is x≥0, the value range of y is 1>y≥0, and y increases with the increase of x; therefore, in this scheme, when W1 is larger, the obtained T1 is larger, so it is necessary to obtain the maximum value W1 of the total number of characteristic vehicles corresponding to the first marked surveillance video segment, and the first signal coefficient K1 is determined according to the actual situation; the value of the maximum signal duration T2 should be as small as possible while being greater than the total effective signal duration SD, because the duration after re-timing should not differ greatly from the total effective signal duration SD; when y=e xAmong them, when the value range of x is x≥0, the value range of y is y≥1, and y decreases as x decreases; so in this solution, the smaller W2 is, the smaller T2 obtained is. Therefore, it is necessary to obtain the minimum value W2 of the total number of characteristic vehicles corresponding to the monitored video segment of the second tag, and the second signal coefficient K2 is determined according to the actual situation. In this embodiment, in order to make the obtained data more reasonable, the coefficients K1 and K2 should be adjusted so that the values of T1 and T2 are within a reasonable range; Step S420: According to the total duration SD of a certain effective signal and the timing coefficient C, the re-timed signal duration of a certain effective signal is obtained as T0 = SD(1 + K SD *(C - 0.5)), where K SD is the characteristic timing coefficient. When T0 < T1, let T0 = T1; when T0 > T2, let T0 = T2.

[0011] An intelligent urban planning and management system based on big data includes a steering ratio vector obtaining module, a congestion degree calculation module, a timing coefficient calculation module, and an effective signal adjustment module; Steering ratio vector obtaining module: used to obtain the planar layout diagram of the target intersection. The planar layout diagram includes several lanes connecting the target intersection. Obtain the historical monitored video of the target intersection, and according to the target steering behavior of the vehicles on each lane after passing through the target intersection, obtain the steering ratio vector corresponding to each lane; Congestion degree calculation module: used to combine several lanes into a lane group, extract the target video segment from the monitored video according to the monitored video, and calculate the current congestion degree of each lane group according to the staying time of each vehicle at the target intersection; Timing coefficient calculation module: used to obtain the effective signal that allows the vehicles on each lane to pass through the target intersection, obtain the characteristic staying time corresponding to each lane according to the target steering behavior and steering ratio vector of the vehicles on each lane, and obtain the timing coefficient of the effective signal corresponding to each lane according to the congestion degree; Effective signal adjustment module: used to obtain the historical timing data of the effective signal corresponding to each lane, and adjust the timing data of the effective signal corresponding to each lane according to the timing coefficient.

[0012] Furthermore, the steering ratio vector obtaining module includes a to-be-determined steering behavior determination unit, a target steering behavior obtaining unit, and a steering ratio vector calculation unit; To-be-determined steering behavior determination unit: used to obtain the monitored video within the previous T days, obtain the target intersection area and each lane area in the monitored video according to the planar layout diagram; the target steering behaviors include going straight, turning right, turning left, and making a U-turn, and determine the to-be-determined steering behavior of a certain vehicle; Obtaining target turning behavior unit: used to determine the set of vehicle turning behaviors allowed for each lane according to traffic rules, obtain the vehicle area of ​​a certain vehicle at the minimum time, and further obtain the target turning behavior of a certain vehicle; Steering ratio vector calculation unit: used to obtain the target vehicle corresponding to each lane in the monitoring video, and obtain the total number of target vehicles corresponding to a lane; and obtain the total number of vehicles corresponding to each target turning behavior, obtain the steering ratio corresponding to each target turning behavior on a lane, and establish the steering ratio vector corresponding to a lane.

[0013] Furthermore, the timing coefficient calculation module includes a characteristic stay time calculation unit and a timing coefficient calculation unit; Characteristic stay time calculation unit: used to obtain the average stay time corresponding to a certain target turning behavior according to the stay time of each vehicle, and then obtain the stay time vector, and take the dot product of the turning ratio vector corresponding to a lane and the stay time vector as the characteristic stay time corresponding to the lane; Timing coefficient calculation unit: used to take the congestion degree of a lane group as the congestion degree of a lane, and obtain the timing coefficient of the effective signal corresponding to each lane according to the characteristic stay time corresponding to the lane.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides an intelligent city planning management system and method based on big data, including: obtaining the plan layout diagram of the target intersection and the historical monitoring video, obtaining the steering ratio vector corresponding to each lane; extracting the target video clip according to the monitoring video, and then calculating the current congestion level of each lane group; obtaining the effective signal corresponding to each lane, allowing the vehicle on the lane to pass through the target intersection, and obtaining the timing coefficient of the effective signal corresponding to each lane; obtaining the historical timing data of the effective signal corresponding to each lane, and adjusting the timing data of the effective signal corresponding to each lane according to the timing coefficient. The present invention obtains the historical monitoring data of the target intersection, further calculates the current congestion level of the lane group according to the actual situation of the intersection, and optimizes the timing of each signal on the traffic light in a reasonable and targeted manner, providing a more convenient traffic environment for driving residents, improving the traffic efficiency of the intersection, alleviating traffic congestion, and enhancing the residents' sense of happiness when traveling. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a process of a smart city planning management method based on big data according to the present invention; Figure 2 This is a structural diagram of an intelligent city planning management system based on big data in the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example: Figure 1 As shown, the present invention provides a technical solution for a smart city planning management method based on big data, comprising the following steps: Step S100: Obtain a plan layout diagram of the target intersection, the plan layout diagram includes several lanes connected to the target intersection, obtain historical surveillance video of the target intersection, and obtain the steering ratio vector corresponding to each lane based on the target turning behavior of vehicles on each lane after passing the target intersection.

[0018] Step S110: Obtain surveillance videos from the previous T days, and obtain the target intersection area TIR and each lane area in the surveillance video according to the floor plan; obtain the rectangular bounding box corresponding to a vehicle in the surveillance video as the vehicle area CR of the vehicle, and obtain the time period in which TIR∩CR is not empty, and take the minimum time in the time period as M1, and the maximum time as M2; take the position of the center point of the vehicle area CR as the midpoint position, set the time period TL0, and take the midpoint position of the time of the vehicle starting from the minimum time M1 and the time period TL0 before as PT1 , the midpoint position at the minimum moment M1 is taken as P1, and the direction from the midpoint position PT1 to the midpoint position P1 is taken as the moving direction D1; the midpoint position of a vehicle at the maximum moment M2 is taken as P2, and the midpoint position at the moment of the maximum moment M2 in the subsequent time period TL0 is taken as PT2, and the direction from the midpoint position P2 to the midpoint position PT2 is taken as the moving direction D2. The target turning behaviors include going straight, turning right, turning left and turning around; according to the angle required to rotate clockwise from the moving direction D1 to the moving direction D2, the turning behavior to be determined of a vehicle is determined.

[0019] Among them, the rectangular bounding box corresponding to a certain vehicle can be obtained by target detection algorithms such as Faster R-CNN and YOLO; these algorithm models can identify vehicles in images after being trained with a large amount of image data, and the model outputs the position of the vehicle in the image in the form of a rectangular bounding box. For surveillance video, target detection can be performed continuously on each frame of the image, so as to track the position and movement of the vehicle in real time. According to the angle required to rotate clockwise from the moving direction D1 to the moving direction D2, the value range of this angle is [0,360]. In this embodiment, if the angle is 0-45 or 315-360, the vehicle's to-be-determined turning behavior is judged to be a U-turn; if the angle is 45-135, the vehicle's to-be-determined turning behavior is judged to be a right turn; if the angle is 135-225, the vehicle's to-be-determined turning behavior is judged to be straight; if the angle is 225-315, the vehicle's to-be-determined turning behavior is judged to be a left turn.

[0020] Step S120: Determine the set of allowed turning behaviors for vehicles corresponding to each lane according to traffic rules; obtain the vehicle area CR1 of a certain vehicle at the minimum time M1, obtain the intersection area between the vehicle area CR1 and a certain lane area, if the intersection area is greater than the lane intersection area threshold, obtain the lane Lan corresponding to the certain lane area, and use the certain vehicle as the target vehicle on the lane Lan, if the set of allowed turning behaviors for vehicles corresponding to the lane Lan includes the turning behavior to be determined of a certain vehicle, then use the turning behavior to be determined as the target turning behavior of the certain vehicle.

[0021] In this embodiment, the lane intersection area threshold is the vehicle area 0.8*CR1. When the vehicle turns, if most of the vehicle is in a lane, it can more accurately determine which lane the vehicle is turning from, thereby facilitating relevant calculations and analysis of vehicles in that lane.

[0022] Step S130: Obtain the target vehicles corresponding to each lane in the monitoring video, take the total number of target vehicles corresponding to a lane as SUM0, and according to the target turning behavior of each target vehicle on a lane, collect the number of vehicles corresponding to the same target turning behavior to obtain the total number of vehicles corresponding to each target turning behavior, and according to the total number of target vehicles SUM0, obtain the steering ratio corresponding to each target turning behavior on a lane, and establish a steering ratio vector V0 corresponding to a lane.

[0023] Due to different road conditions at each intersection, when the left turn indicator is green, the vehicle may turn around or turn left. In this solution, the steering ratio vector V0=[R1, R2, R3, R4] corresponding to a lane, where R1, R2, R3 and R4 represent the proportion of the straight, right turn, left turn and U-turn directions of the vehicle in a lane, respectively, and R1, R2, R3 and R4 are all between 0 and 1, R1+R2+R3+R4=1. For example, the steering ratios corresponding to the target steering behaviors on a lane are [0, 0, 0.6, 0.4], then the steering ratio vector V0=[0, 0, 0.6, 0.4].

[0024] Step S200: Combine several lanes into a lane group, extract the target video segment from the surveillance video, and calculate the current congestion level of each lane group based on the length of time each vehicle stays at the target intersection.

[0025] Step S210: All adjacent lanes with the same vehicle-allowed turning behavior are grouped as a lane group, and the lane group area in the monitoring video is obtained; a valid signal corresponding to a lane group that allows vehicles on the lane group to pass through the target intersection is obtained, and the total effective signal duration TP corresponding to the valid signal is obtained; a monitoring video segment within the valid signal is intercepted, and a target video segment that is closest to the current time and whose duration of the monitoring video segment is equal to the total effective signal duration TP is obtained.

[0026] Step S220: Take the vehicle area corresponding to a certain vehicle in the target video clip at time m as CR0, obtain the intersection area of ​​the vehicle area CR0 and a certain lane group area, if the intersection area is greater than the preset lane group intersection area threshold and satisfies TIR∩CR0 is not empty at time m+1, where TIR is the target intersection area, then take the certain vehicle as the feature vehicle, and the lane group corresponding to the certain lane group area as Lag; then obtain the total number of feature vehicles corresponding to the lane group Lag in the target video clip, and sort the feature vehicles in chronological order from front to back according to the moment when each feature vehicle satisfies TIR∩CR1 for the first time and is not empty; and take the total duration for which a certain feature vehicle satisfies TIR∩CR1 is not empty as the length of stay of the certain feature vehicle in the target intersection area.

[0027] Step S230: Get any two feature vehicles a and b with adjacent serial numbers. Feature vehicles a and b are M and B respectively at the moment when TIR∩CR1 is not empty for the first time. a and M b , the time M a and M b The absolute value of the difference is used as the time difference to obtain all the time differences corresponding to a lane group, and the current congestion level of a lane group is obtained according to the stay time corresponding to each characteristic vehicle. , and normalized, where K RT is the residence time coefficient, K MD is the time difference coefficient, G is the total number of characteristic vehicles corresponding to a lane group, H is the total number of time differences corresponding to a lane group, G=H+1, RT g is the dwell time corresponding to the g-th characteristic vehicle, MD h is the hth time difference.

[0028] If the dwell time becomes shorter and shorter, and the time difference between two characteristic vehicles with adjacent serial numbers becomes longer and longer, it is considered that there are fewer vehicles on the lane and it is not too crowded. The congestion level ranges from [0,1]. The larger the congestion level, the more vehicles there are on the lane. In this scheme, the congestion level is calculated based on the dwell time of the characteristic vehicle over a period of time and the time difference between two characteristic vehicles with adjacent serial numbers. This is because the data changes of dynamic vehicles at the intersection can better reflect the congestion level of the lane.

[0029] Step S300: Obtain the effective signal corresponding to each lane, allowing vehicles in the lane to pass the target intersection, obtain the characteristic stay time corresponding to each lane according to the target turning behavior and turning ratio vector of the vehicles in each lane, and obtain the timing coefficient of the effective signal corresponding to each lane according to the congestion level.

[0030] For example, at an intersection, when the green light for the east-west straight lane comes on, this signal is the effective signal for that lane, and vehicles going straight in the east-west direction can pass through the intersection.

[0031] Step S310: According to the target turning behavior of each vehicle on a certain lane in the target intersection area, the number of vehicles corresponding to the same target turning behavior is collected, and the total number of vehicles corresponding to a certain target turning behavior is obtained. According to the stay time of each vehicle, the average stay time corresponding to the certain target turning behavior is obtained, and then the stay time vector is obtained, and the dot product of the turning ratio vector corresponding to a certain lane and the stay time vector is used as the characteristic stay time corresponding to the certain lane.

[0032] The dwell time vector is obtained based on the vehicle's dwell time at the target intersection. The dwell time vector S0=[s1, s2, s3, s4] corresponding to a lane; for example, if on a certain lane, only the lane is allowed to turn left or make a U-turn at the target intersection, and the corresponding steering ratio vector V0=[0, 0, 0.6, 0.4] of the lane, the dwell time vector S0=[0, 0, 8, 10], then the characteristic dwell time corresponding to the lane is the dot product of V0 and S0, which is 0*0+0*0+0.6*8+0.4*10=8.8, in seconds.

[0033] Step S320: If a lane is included in a lane group, the congestion level of the lane group is taken as the congestion level of the lane, and according to the characteristic stay time corresponding to the lane, the timing coefficient of the effective signal corresponding to each lane is obtained as C=k*Y*Z, and normalized, where k is the timing correlation coefficient, Y is the congestion level corresponding to the lane, and Z is the characteristic stay time corresponding to the lane.

[0034] The timing coefficient indicates the correlation coefficient that the effective signal corresponding to the traffic light needs to be re-timing. The timing coefficient value range is [0,1]. When it is close to 0, it means that the traffic flow on the lane in that direction is relatively small, or the currently allocated green light time is too long, resulting in a waste of time. The current corresponding effective signal needs to be reduced in seconds. When it is close to 1, it means that the traffic flow on the lane in that direction is relatively large, or the currently allocated green light time is too short, resulting in traffic congestion, indicating that the corresponding effective signal needs to be increased in seconds.

[0035] Step S400: Acquire historical timing data of the effective signal corresponding to each lane, and adjust the timing data of the effective signal corresponding to each lane according to the timing coefficient.

[0036] Step S410: Obtain the valid signal corresponding to each lane, and according to the total effective signal duration of each valid signal, intercept all monitoring video clips corresponding to each valid signal; take the total effective signal duration of a valid signal corresponding to a lane as SD, and according to step S200, obtain the congestion degree corresponding to a lane in each monitoring video clip; perform a first mark on the monitoring video clips whose congestion degree is less than the first congestion degree, and obtain the minimum signal duration T1=SD*(1- ), K1 is the first signal coefficient, K1>0; the surveillance video clips with a congestion level greater than the second congestion level are marked for the second time, and according to the minimum total number of characteristic vehicles W2 corresponding to the second marked surveillance video clips, and the characteristic stay time S of a lane, the maximum signal time T2=SD* , K2 is the second signal coefficient, K2>0.

[0037] The value of the minimum signal duration T1 should be as large as possible while being less than the total effective signal duration SD. This is because the duration after re-timing should not differ greatly from the total effective signal duration SD. -xAmong them, when the value range of x is x≥0, the value range of y is 1>y≥0, and y increases as x increases; so in this solution, when W1 is larger, the obtained T1 is larger. Therefore, it is necessary to obtain the maximum value W1 of the total number of feature vehicles corresponding to the monitored video segment of the first marker. The first signal coefficient K1 is determined according to the actual situation. In this embodiment, K1 = 0.1; the value of the maximum signal duration T2 should be as small as possible while satisfying being greater than the total effective signal duration SD, because the duration after re-timing should not differ greatly from the total effective signal duration SD; at y = e x Among them, when the value range of x is x≥0, the value range of y is y≥1, and y decreases as x decreases; so in this solution, when W2 is smaller, the obtained T2 is smaller. Therefore, it is necessary to obtain the minimum value W2 of the total number of feature vehicles corresponding to the monitored video segment of the second marker. The second signal coefficient K2 is determined according to the actual situation. In this embodiment, K2 = 0.01. In this embodiment, in order to make the obtained data more reasonable, the coefficients K1 and K2 should be adjusted so that the values of T1 and T2 are within a reasonable range. Generally, the value of T1 is not easily less than 0.8*SD, and the value of T1 is not easily greater than 1.2*SD.

[0038] Step S420: According to the total effective signal duration SD of a certain effective signal and the timing coefficient C, the signal duration after re-timing of a certain effective signal is obtained as T0 = SD(1 + K SD *(C - 0.5)), where K SD is the feature timing coefficient. When T0 < T1, let T0 = T1; when T0 > T2, let T0 = T2.

[0039] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claims involved.

Claims

1. A smart city planning and management method based on big data, characterized in that: The following steps are involved: Step S100: obtaining a plan layout diagram of the target intersection, the plan layout diagram including a number of lanes connected to the target intersection, obtaining a historical surveillance video of the target intersection, and obtaining a steering ratio vector corresponding to each lane according to a target steering behavior of vehicles on each lane after passing the target intersection; Step S200: combining a plurality of lanes into a lane group, extracting a target video segment from the surveillance video, and calculating the current congestion level of each lane group according to the length of time each vehicle stays at the target intersection; Step S300: Obtaining the effective signal corresponding to each lane, allowing the vehicle in the lane to pass through the target intersection, obtaining the characteristic stay time corresponding to each lane according to the target turning behavior and turning ratio vector of the vehicle in each lane, and obtaining the timing coefficient of the effective signal corresponding to each lane according to the congestion degree; Step S400: Acquire historical timing data of the effective signal corresponding to each lane, and adjust the timing data of the effective signal corresponding to each lane according to the timing coefficient.

2. According to the big data-based smart city planning and management method of claim 1, it is characterized in that: Step S100 includes: Step S110: Obtain surveillance video within the previous T days, and obtain the target intersection area TIR and each lane area in the surveillance video according to the floor plan; obtain the rectangular bounding box corresponding to a certain vehicle in the surveillance video as the vehicle area CR of the certain vehicle, and obtain the time period in which TIR∩CR is not empty, and take the minimum moment in the time period as M1, and the maximum moment as M2; take the position of the center point of the vehicle area CR as the midpoint position, set the time period TL0, and take the midpoint position of the time of the certain vehicle starting from the minimum moment M1 and the time period TL0 before as PT1 , the midpoint position at the minimum moment M1 is taken as P1, and the direction from the midpoint position PT1 to the midpoint position P1 is taken as the moving direction D1; the midpoint position at the maximum moment M2 of the certain vehicle is taken as P2, and the midpoint position at the moment of the maximum moment M2 in the subsequent time period TL0 is taken as PT2, and the direction from the midpoint position P2 to the midpoint position PT2 is taken as the moving direction D2, and the target turning behaviors include going straight, turning right, turning left and turning around; according to the angle required to rotate clockwise from the moving direction D1 to the moving direction D2, the turning behavior to be determined of the certain vehicle is determined; Step S120: determining a set of vehicle turning behaviors allowed for each lane according to traffic rules; obtaining a vehicle region CR1 of the certain vehicle at the minimum time M1, obtaining an intersection area between the vehicle region CR1 and a certain lane region, and if the intersection area is greater than a lane intersection area threshold, obtaining a lane Lan corresponding to the certain lane region, and taking a certain vehicle as a target vehicle on the lane Lan, and if the set of vehicle turning behaviors allowed for the corresponding lane Lan includes the turning behavior to be determined of the certain vehicle, taking the turning behavior to be determined as the target turning behavior of the certain vehicle; Step S130: Obtain the target vehicles corresponding to each lane in the monitoring video, take the total number of target vehicles corresponding to a lane as SUM0, and according to the target turning behavior of each target vehicle on a lane, collect the number of vehicles corresponding to the same target turning behavior to obtain the total number of vehicles corresponding to each target turning behavior, and according to the total number of target vehicles SUM0, obtain the steering ratio corresponding to each target turning behavior on a lane, and establish a steering ratio vector V0 corresponding to a lane.

3. According to the big data-based smart city planning and management method of claim 2, it is characterized in that: Step S200 includes: Step S210: All adjacent lanes with the same vehicle-allowed turning behavior are regarded as a lane group, and the lane group area in the monitoring video is obtained; a valid signal corresponding to a lane group that allows vehicles in the lane group to pass through the target intersection is obtained, and the total effective signal duration TP corresponding to the valid signal is obtained; a monitoring video segment within the valid signal is intercepted, and a target video segment that is closest to the current time and whose duration of the monitoring video segment is equal to the total effective signal duration TP is obtained; Step S220: Take the vehicle area corresponding to a certain vehicle in the target video clip at time m as CR0, obtain the intersection area of ​​the vehicle area CR0 and a certain lane group area, if the intersection area is greater than the preset lane group intersection area threshold and satisfies TIR∩CR0 is not empty at time m+1, where TIR is the target intersection area, then take the certain vehicle as the feature vehicle, and the lane group corresponding to the certain lane group area as Lag; then obtain the total number of feature vehicles corresponding to the lane group Lag in the target video clip, and sort the feature vehicles in chronological order from front to back according to the moment when each feature vehicle satisfies TIR∩CR1 for the first time; and take the total duration when a certain feature vehicle satisfies TIR∩CR1 is not empty as the length of stay of the certain feature vehicle in the target intersection area; Step S230: Get any two feature vehicles a and b with adjacent serial numbers. Feature vehicles a and b are M and B respectively at the moment when TIR∩CR1 is not empty for the first time. a and M b , the time M a and M b The absolute value of the difference is used as the time difference to obtain all the time differences corresponding to the lane group, and the current congestion level of the lane group is obtained according to the stay time corresponding to each characteristic vehicle. , and normalized, where K RT is the residence time coefficient, K MD is the time difference coefficient, G is the total number of characteristic vehicles corresponding to a lane group, H is the total number of time differences corresponding to a lane group, G=H+1, RT g is the dwell time corresponding to the g-th characteristic vehicle, MD h is the hth time difference.

4. According to the big data-based smart city planning and management method of claim 3, it is characterized in that: Step S300 includes: Step S310: according to the target turning behavior of each vehicle on a certain lane in the target intersection area, the number of vehicles corresponding to the same target turning behavior is collected, and the total number of vehicles corresponding to a certain target turning behavior is obtained, and according to the stay time of each vehicle, the average stay time corresponding to the certain target turning behavior is obtained, and then the stay time vector is obtained, and the dot product of the turning ratio vector corresponding to the certain lane and the stay time vector is used as the characteristic stay time corresponding to the certain lane; Step S320: If a lane is included in a lane group, the congestion level of the lane group is taken as the congestion level of the lane, and according to the characteristic stay time corresponding to the lane, the timing coefficient of the effective signal corresponding to each lane is obtained as C=k*Y*Z, and normalized, wherein k is the timing correlation coefficient, Y is the congestion level corresponding to the lane, and Z is the characteristic stay time corresponding to the lane.

5. According to the big data-based smart city planning and management method of claim 4, it is characterized in that: Step S400 includes: Step S410: Obtain the valid signal corresponding to each lane, and according to the total effective signal duration of each valid signal, intercept all monitoring video clips corresponding to each valid signal; take the total effective signal duration of a valid signal corresponding to a lane as SD, and according to step S200, obtain the congestion degree corresponding to a lane in each monitoring video clip; perform a first mark on the monitoring video clips whose congestion degree is less than the first congestion degree, and obtain the minimum signal duration T1=SD*(1- ), K1 is the first signal coefficient, K1>0; the surveillance video clips with a congestion degree greater than the second congestion degree are marked for the second time, and according to the minimum total number of characteristic vehicles W2 corresponding to the second marked surveillance video clips, and the characteristic stay time S of the lane, the maximum signal time T2=SD* , K2 is the second signal coefficient, K2>0; Step S420: Based on the total duration SD of a certain valid signal and the timing coefficient C, the signal duration after re-timing of the certain valid signal is obtained as T0 = SD(1 + K SD *(C - 0.5)), where K SD is the characteristic timing coefficient. When T0 < T1, let T0 = T1; when T0 > T2, let T0 = T2.

6. A smart city planning management system, used to execute a smart city planning management method based on big data as described in any one of claims 1 to 5, characterized in that: The system includes a module for obtaining a steering ratio vector, a module for calculating a congestion level, a module for calculating a timing coefficient, and a module for adjusting an effective signal; Obtaining steering ratio vector module: used to obtain the plane layout diagram of the target intersection, which includes several lanes connected to the target intersection, obtain the historical monitoring video of the target intersection, and obtain the steering ratio vector corresponding to each lane according to the target steering behavior of the vehicles on each lane after passing the target intersection; Congestion calculation module: used to combine several lanes into a lane group, extract the target video clips from the monitoring video, and calculate the current congestion level of each lane group according to the length of time each vehicle stays at the target intersection; Timing coefficient calculation module: used to obtain the effective signal corresponding to each lane, allowing the vehicles in the lane to pass through the target intersection, obtain the characteristic stay time corresponding to each lane according to the target turning behavior and turning ratio vector of the vehicles in each lane, and obtain the timing coefficient of the effective signal corresponding to each lane according to the congestion level; The effective signal adjustment module is used to obtain the historical timing data of the effective signal corresponding to each lane, and adjust the timing data of the effective signal corresponding to each lane according to the timing coefficient.

7. The intelligent city planning and management system according to claim 6, characterized in that: The module for obtaining the steering ratio vector includes a unit for obtaining a steering behavior to be determined, a unit for obtaining a target steering behavior, and a unit for calculating a steering ratio vector; Obtaining the turning behavior unit to be determined: used to obtain the surveillance video within the previous T days, and obtain the target intersection area and each lane area in the surveillance video according to the plane layout diagram; The target turning behaviors include going straight, turning right, turning left and turning around, and determining the turning behavior to be determined of the vehicle; Obtaining a target turning behavior unit: used to determine a set of vehicle turning behaviors allowed for each lane according to traffic rules, obtain a vehicle area of ​​the certain vehicle at the minimum time, and further obtain a target turning behavior of the certain vehicle; Steering ratio vector calculation unit: used to obtain the target vehicle corresponding to each lane in the monitoring video and obtain the total number of target vehicles corresponding to a lane; The total number of vehicles corresponding to each target turning behavior is obtained, the turning ratio corresponding to each target turning behavior on a certain lane is obtained, and the turning ratio vector corresponding to a certain lane is established.

8. The intelligent city planning and management system according to claim 7, characterized in that: The timing coefficient calculation module includes a characteristic stay duration calculation unit and a timing coefficient calculation unit; Characteristic stay time calculation unit: used to obtain the average stay time corresponding to a certain target turning behavior according to the stay time of each vehicle, and then obtain the stay time vector, and take the dot product of the turning ratio vector corresponding to a lane and the stay time vector as the characteristic stay time corresponding to the lane; Timing coefficient calculation unit: used to take the congestion degree of a lane group as the congestion degree of a lane, and obtain the timing coefficient of the effective signal corresponding to each lane according to the characteristic stay time corresponding to the lane.

Images