CN113129595A - Traffic signal control method, equipment and medium for road intersection - Google Patents

Traffic signal control method, equipment and medium for road intersection Download PDF

Info

Publication number
CN113129595A
CN113129595A CN202110440444.7A CN202110440444A CN113129595A CN 113129595 A CN113129595 A CN 113129595A CN 202110440444 A CN202110440444 A CN 202110440444A CN 113129595 A CN113129595 A CN 113129595A
Authority
CN
China
Prior art keywords
vehicle
phase
image
road
lane
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110440444.7A
Other languages
Chinese (zh)
Other versions
CN113129595B (en
Inventor
李玉宝
齐杰
孙庆文
王素军
乔学军
陈翠娇
王以龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinan Jinyu Highway Industry Development Co ltd
Original Assignee
Jinan Jinyu Highway Industry Development Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinan Jinyu Highway Industry Development Co ltd filed Critical Jinan Jinyu Highway Industry Development Co ltd
Priority to CN202110440444.7A priority Critical patent/CN113129595B/en
Publication of CN113129595A publication Critical patent/CN113129595A/en
Application granted granted Critical
Publication of CN113129595B publication Critical patent/CN113129595B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/08—Controlling traffic signals according to detected number or speed of vehicles

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application discloses a traffic signal control method, equipment and medium for a road intersection. And determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase. And acquiring the number of the passed vehicles of each lane corresponding to each phase. And calculating the average value of the vehicle queue lengths of the lanes corresponding to the phases as the average vehicle queue length of the phases. And calculating the average number of passed vehicles for each phase. And determining the green light adjustment value of the phase according to the average vehicle queuing length, the average number of the vehicles passing through and the current green light duration of the phase. And determining the green light time of the next time period of the phase based on the green light adjustment value and the current green light duration. And adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.

Description

Traffic signal control method, equipment and medium for road intersection
Technical Field
The present disclosure relates to the field of traffic signal control technologies, and in particular, to a method, a device, and a medium for controlling a traffic signal at a road intersection.
Background
With the increasing of the automobile holding capacity, the traffic demand of the urban road network conflicts with the automobile holding capacity, and the original road facilities can not meet the existing demand, so that the traffic jam situation is frequent. Because the traffic flow of the urban road intersection is complex and changeable and the intersection traffic speed is low, traffic jam often occurs at the urban road intersection.
Most of the existing traffic signal control strategies of urban road intersections are limited to the requirements of controlling the passing time and sequence of multi-directional conflict traffic flows, and a fixed signal timing scheme is provided under the condition of meeting the two requirements. By controlling the traffic signals according to the mode, the complex and changeable conditions of the traffic flow of the urban road intersection cannot be met, the problem of traffic jam at the road intersection cannot be effectively solved, and the space-time resources of the road intersection cannot be fully utilized.
Based on the technical scheme, the technical scheme is extremely important, which can be suitable for complex and variable conditions of the road intersection, fully utilize the space-time resources of the road intersection and effectively avoid traffic jam of the road intersection.
Disclosure of Invention
The embodiment of the application provides a traffic signal control method, equipment and a medium for a road intersection, which are used for avoiding traffic jam at the road intersection.
In one aspect, an embodiment of the present application provides a traffic signal control method for a road intersection, where the method includes:
and acquiring a corresponding historical road image set in each phase preset time period of the road intersection. The historical road images in the historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when the traffic lane corresponding to each phase is switched from a traffic state to a no-traffic state. The road intersection is a cross intersection. And carrying out image recognition on each historical road image, and determining the vehicle queue length and the vehicle queue number of each lane corresponding to each phase. And acquiring the number of the passed vehicles of each lane corresponding to each phase. And determining whether the maximum vehicle queuing number in the set of vehicle queuing numbers is larger than a first preset threshold value. And under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, calculating the average value of the vehicle queuing lengths of the lanes corresponding to the phases as the average vehicle queuing length of the phases. And calculating the average value of the number of the passed vehicles of each lane corresponding to each phase as the average number of the passed vehicles of the phase. And determining the green light adjustment value of the phase according to the average vehicle queuing length, the average number of the vehicles passing through and the current green light duration of the phase. And determining the green light time of the next time period of the phase based on the green light adjustment value and the current green light duration. Wherein the next time period corresponds to the preset time period. And adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
In the embodiment of the application, the vehicle queue length, the vehicle queue number and the number of vehicles passing through a lane are determined according to the historical road image corresponding to each phase of the road intersection, and then the green light adjustment value of each phase is determined. The traffic signal timing scheme of the road intersection can be changed in time by analyzing and sorting historical data. Meanwhile, the complex and variable road intersection signal lamp timing scheme is adjusted, the traffic flow of the road intersection can be increased, the congestion of the road intersection is reduced to a certain extent, and the traffic accident phenomenon is avoided.
In one implementation of the present application, image recognition is performed on each historical road image, and a vehicle contour of a vehicle located in each lane in the historical road image is determined. And calculating the spacing distance between the adjacent vehicle profiles in each lane, and generating a spacing distance sequence corresponding to the spacing distance. And sequentially determining whether the spacing distance in the spacing distance sequence is greater than a second preset threshold value. And in the case that the spacing distance is larger than a second preset threshold value, taking the corresponding vehicle profile close to the stop line as the termination vehicle. And determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase according to the vehicle stopping.
In one implementation of the present application, a vehicle contour with a minimum distance to a corresponding stop line is determined from a historical road image. It is determined whether the distance of the vehicle contour with the smallest distance from the stop line is smaller than a third preset threshold. And in the case that the distance between the vehicle profile with the minimum distance and the stop line is less than a third preset threshold value, taking the vehicle profile with the minimum distance as the corresponding starting vehicle. And determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase according to the ending vehicle and the starting vehicle.
In one implementation of the application, each historical road image is processed according to the road lane information to obtain a vehicle queuing image corresponding to at least one lane image corresponding to the historical road image. And setting corresponding movable areas for the lane images according to a sliding window algorithm, and determining whether vehicles exist in a preset starting point area of the vehicle queuing image or not according to the movable areas. And under the condition that the vehicle image exists in the preset starting point area, setting an approaching straight line in the preset starting point area, moving the approaching straight line according to a preset direction until the pixel value on the approaching straight line at the current position is greater than a third preset threshold value and the difference value between the pixel value and the pixel value at the previous position is greater than a fourth preset threshold value, and determining a queuing vehicle starting line. And sliding the preset movable area from the queuing vehicle start line according to a preset direction and a preset step length to determine a queuing vehicle finish line. And determining the vehicle queuing length in each historical road image corresponding to each phase based on the queuing vehicle start line and the queuing vehicle finish line.
In one implementation manner of the application, the road background image corresponding to the historical road image is determined by performing image recognition on the historical road image. And determining the historical road image after removing the pixel points of the road background image based on the road background image and the historical road image. And corroding the historical road image after the pixel points of the road background image are removed by the structural element SE to obtain the de-noised historical road image. And determining vehicle queuing images corresponding to all lanes in all the historical road images based on the de-noised historical road images.
In one implementation of the present application, lane region information in a historical road image is determined. The lane area information includes a lane area length and a lane area width. And determining an image of the lane area of the historical road image of each lane of each phase according to the lane area information. And carrying out binarization processing on the images of the lane areas to obtain vehicle queue images corresponding to all lanes in all historical road images.
In one implementation manner of the application, a distance fitting equation is established according to actual measurement data of a lane corresponding to a vehicle queuing image, so as to determine a corresponding relation between a pixel distance in the vehicle queuing image and an actual distance. And determining the vehicle queuing length in each historical road image based on the distance fitting equation and the pixel distance of the queuing vehicle start line and the queuing vehicle finish line.
In one implementation of the present application, a preset priority value of a road intersection is determined based on position information of the road intersection. And determining a preset correlation coefficient between the road intersection and the adjacent road intersection according to the vehicle queue number. And determining a signal period coordination parameter of the phase based on the preset priority value of the road intersection and the preset correlation coefficient between the road intersection and the adjacent road intersection so as to determine a green light adjustment value of the corresponding phase. Wherein, the signal period coordination parameter of the phase is determined according to the following formula:
Figure BDA0003034803050000041
Figure BDA0003034803050000042
wherein, theta1A phase of the kth signal period, alpha is a preset priority value of the intersection, and m1Is the average vehicle queue length, beta is a preset correlation coefficient between the intersection and the adjacent intersection,
Figure BDA0003034803050000043
the coordination parameter for the other road crossings for the kth signal period of the phase,
Figure BDA0003034803050000044
the coordination parameters of other road intersections in the k-1 signal period of the signal lamp of the corresponding phase are n, and the n is the number of the other road intersections.
In another method, an embodiment of the present application provides a traffic signal control apparatus for a road intersection, the apparatus including: at least one processor. And a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to: and acquiring a corresponding historical road image set in each phase preset time period of the road intersection. The historical road images in the historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when the traffic lane corresponding to each phase is switched from a traffic state to a no-traffic state. The road intersection is a cross intersection. And carrying out image recognition on each historical road image, and determining the vehicle queue length and the vehicle queue number of each lane corresponding to each phase. And acquiring the number of the passed vehicles of each lane corresponding to each phase. And determining whether the maximum vehicle queuing number in the set of vehicle queuing numbers is larger than a first preset threshold value. And under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, calculating the average value of the vehicle queuing lengths of the lanes corresponding to the phases as the average vehicle queuing length of the phases. And calculating the average value of the number of the passed vehicles of each lane corresponding to each phase as the average number of the passed vehicles of the phase. And determining the green light adjustment value of the phase according to the average vehicle queuing length, the average number of the vehicles passing through and the current green light duration of the phase. And determining the green light time of the next time period of the phase based on the green light adjustment value and the current green light duration. Wherein the next time period corresponds to the preset time period. And adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
On the other hand, the embodiment of the present application further provides a traffic signal control medium for a road intersection, which stores computer-executable instructions for executing: and acquiring a corresponding historical road image set in each phase preset time period of the road intersection. The historical road images in the historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when the traffic lane corresponding to each phase is switched from a traffic state to a no-traffic state. The road intersection is a cross intersection. And carrying out image recognition on each historical road image, and determining the vehicle queue length and the vehicle queue number of each lane corresponding to each phase. And acquiring the number of the passed vehicles of each lane corresponding to each phase. And determining whether the maximum vehicle queuing number in the set of vehicle queuing numbers is larger than a first preset threshold value. And under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, calculating the average value of the vehicle queuing lengths of the lanes corresponding to the phases as the average vehicle queuing length of the phases. And calculating the average value of the number of the passed vehicles of each lane corresponding to each phase as the average number of the passed vehicles of the phase. And determining the green light adjustment value of the phase according to the average vehicle queuing length, the average number of the vehicles passing through and the current green light duration of the phase. And determining the green light time of the next time period of the phase based on the green light adjustment value and the current green light duration. Wherein the next time period corresponds to the preset time period. And adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 2 is another flowchart of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 3 is another flowchart of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 4 is another flowchart of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 5 is another flowchart of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 6 is another flowchart of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a traffic signal control method for a road intersection according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a traffic signal control device for a road intersection according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without any creative effort belong to the protection scope of the present application.
With the increasing of the automobile holding capacity, the traffic demand of the urban road network conflicts with the automobile holding capacity, and the original road facilities can not meet the existing demand, so that the traffic jam situation is frequent. Because the traffic flow of the urban road intersection is complex and changeable and the intersection traffic speed is low, traffic jam often occurs at the urban road intersection.
The existing urban road intersection traffic timing scheme needs to be updated in time to adapt to complex and variable traffic environments.
Based on the above, the embodiment of the application provides a traffic signal control method, equipment and medium for a road intersection. The traffic signal control method for the intersection provided by the embodiment of the application comprises S101-S107, and as shown in FIG. 1:
s101, the server acquires a corresponding historical road image set in each phase preset time period of the road intersection.
The historical road images in the historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when the traffic lane corresponding to each phase is switched from a traffic state to a no-traffic state. The road intersection is a cross intersection.
In the embodiment of the application, the server acquires the historical road image of the image acquisition device in a certain phase, for example, the image acquisition device in an east-west phase at the time when the green light changes into the red light. Here, the phase is a road traveling in a certain direction and a road traveling in the opposite direction, such as a road traveling straight to the east and a road traveling straight to the west. The historical road image may be a road image of a corresponding work day in the previous month. For example, the current working day is wednesday, and the server acquires historical road images of four wednesdays in the previous month of the east-west straight-going phase.
Further, the history road image is an image captured by an image capturing device such as an electronic eye, a camera, or the like provided with each lane of each phase, and for a road intersection having a plurality of lanes, each lane has a corresponding image capturing device. The image acquisition equipment acquires historical road images at the moment when the green light is changed into the red light, and can accurately determine queued vehicles which do not pass through the road intersection.
It should be noted that the server exists as an exemplary execution subject of the traffic signal control method for the intersection, and the execution subject is not limited to the server, and this application is not particularly limited thereto.
S102, the server carries out image recognition on each historical road image, and determines the vehicle queue length and the vehicle queue number of each lane corresponding to each phase. And acquiring the number of the passed vehicles of each lane corresponding to each phase.
In the embodiment of the application, the server performs image recognition on the historical road image, and determines the vehicle queue length and the vehicle queue number of each lane corresponding to each phase in the historical road image, wherein the vehicle queue length can be calculated according to the historical road image, and the vehicle queue number can be obtained according to the vehicle queue length and the vehicle profile in the historical road image. The server can determine the number of vehicles passing through each lane corresponding to each phase in the green light process through the geomagnetic detection equipment.
In an embodiment of the present application, the image recognition of the historical road image and the determination of the vehicle queue length and the vehicle queue number of each lane corresponding to each phase further include the following steps, as shown in fig. 2:
s201, the server carries out image recognition on each historical road image and determines the vehicle outline of the vehicle positioned in each lane in each historical road image.
In the embodiment of the application, the server performs image recognition and processing on the historical road image, so as to determine the vehicle contour image in the historical road image. The vehicle contour image corresponds to a vehicle contour image in a single lane.
S202, the server calculates the spacing distance between the adjacent vehicle profiles in each lane and generates a spacing distance sequence corresponding to the spacing distance.
In the embodiment of the application, the distance of the vehicle contour interval of the single lane corresponding to each phase is determined according to the historical road image. The separation distance is the distance between the rear of the vehicle relatively close to the stop-line and the front of the vehicle relatively far from the stop-line. And generating a spacing distance sequence according to the queuing sequence of the vehicles in each lane.
S203, the server sequentially determines whether the spacing distance in the spacing distance sequence is larger than a second preset threshold value.
And S204, under the condition that the spacing distance is larger than a second preset threshold value, the server takes the corresponding vehicle contour close to the stop line as a stop vehicle.
The stop line is a white solid line arranged at the road intersection and used for warning the vehicle, and the closer the vehicle contour is to the stop line, the closer the vehicle contour is to the road intersection. In the embodiment of the application, the separation distance is a pixel distance, the server sets a second preset threshold value A, when the separation distance is greater than A, the distance between adjacent vehicles is too far, the vehicle profile close to the stop line is taken as a stop vehicle of the vehicle queue number, and the tail part of the vehicle profile is taken as a stop line of the vehicle queue length.
S205, the server determines the vehicle queue length and the vehicle queue number of each lane corresponding to each phase according to the vehicle stopping.
In an embodiment of the present application, determining the vehicle queue length and the vehicle queue number of each lane corresponding to each phase according to the terminating vehicle further includes the following steps, as shown in fig. 3:
s301, the server determines the vehicle outline with the minimum distance to the corresponding stop line according to the historical road image.
In the embodiment of the application, the server determines whether a vehicle in line exists according to the distance between the vehicle and the stop line, and the vehicle is in a driving state under a green light state in general. The historical road image collected by the image collecting device is an image collected when a green light is converted into a red light, and the vehicle closest to the stop line at the moment is the vehicle which does not pass through in time in the green light state.
S302, the server determines whether the distance between the vehicle outline with the minimum distance and the stop line is smaller than a third preset threshold value.
In the embodiment of the present application, whether there is a vehicle in line is determined by the distance between the vehicle outline and the stop line. The method and the device aim to solve the problem that traffic at road intersections is too congested due to the fact that the vehicle queuing length and the green light are not appropriate. Therefore, in an actual vehicle queuing scenario, when the green light of the east-west phase of the intersection is just finished, the queued vehicle should be close to the stop line, that is, whether the distance between the minimum vehicle profile and the stop line is smaller than a third preset threshold, where the third preset threshold may be set to 0.5 meter, or may be other values. That is, when the vehicle profile at the minimum distance from the stop line exceeds 0.5 m, the server determines that there is no vehicle in line.
And S303, under the condition that the distance between the vehicle contour with the minimum distance and the stop line is smaller than a third preset threshold value, the server takes the vehicle contour with the minimum distance as a corresponding starting vehicle.
In the embodiment of the present application, when the profile of the vehicle behind the stop line is smaller than the third preset threshold, that is, the front of the first vehicle behind the stop line is close enough to the stop line, the first vehicle is taken as the starting vehicle, and conversely, no starting vehicle behind the stop line, that is, no vehicle in line, exists.
S304, the server determines the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase according to the ending vehicle and the starting vehicle.
In the embodiment of the application, the server determines the queuing length of the vehicles according to the distance from the front of the starting vehicle to the tail of the ending vehicle in the lane. The server determines the number of vehicle queues in the queued vehicles according to the vehicle profiles and the vehicle queue lengths, wherein large buses, small cars and the like may exist in the queued vehicles. The server can identify the vehicle type according to the vehicle outline, and the vehicle queuing number can be accurately determined by combining the vehicle queuing length.
S103, the server determines whether the maximum vehicle queuing number in the set of the vehicle queuing number combinations is larger than a first preset threshold value.
In the embodiment of the application, the server determines the vehicle queue number of each lane corresponding to each phase in a preset time period, for example, 6 to 7 points, generates a set corresponding to the vehicle queue number, and compares each element value in the set with a first preset threshold (for example, 10 vehicles) to determine the maximum vehicle queue number of the vehicle queue number of each phase.
And S104, under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, the server calculates the average value of the vehicle queuing lengths of the lanes corresponding to the phases to serve as the average vehicle queuing length of the phases. And calculating the average value of the number of the passed vehicles of each lane corresponding to the phase as the average number of the passed vehicles of the phase.
In the embodiment of the application, the server compares the maximum vehicle queuing number corresponding to each phase with a first preset threshold, when the maximum vehicle queuing number exceeds the first preset threshold, the server determines that the signal lamp of the corresponding phase can be adjusted, and the server determines the average value of the vehicle queuing lengths of each lane of the corresponding phase according to historical road images in a preset time period and uses the average value as the average vehicle queuing length of the corresponding phase.
And S105, the server determines the green light adjustment value of the phase according to the average vehicle queuing length, the average number of the vehicles passing through and the current green light duration of the phase.
In the embodiment of the present application, the green light adjustment value may be a negative number or a positive number, the vehicle queue length at a certain phase is 0, and vehicles in all lanes can pass through within the current green light duration, and the green light time is left, then the green light adjustment value is a negative number. And when the queuing length of the vehicles is not 0, and all the vehicles cannot pass through the intersection within the green light duration, the green light adjustment value is positive.
The server can determine the vehicle passing speed of the intersection at the phase according to the average number of the passed vehicles and the current green light duration of the phase, so that the green light time can be determined according to the following formula:
g′n＝hn·vn+gn
wherein, g'nDenotes the green time, h, of the n phases after increasing the green durationnAverage vehicle representing phaseLength of queue, vnIndicating the vehicle speed of passage, h, of n phasesn·vnI.e. the green light adjustment value, gnRepresenting the original green time of the n-phase.
In one embodiment of the application, when the maximum vehicle queue length in the vehicle queue number of a phase is 0, each lane indicating the phase can pass through the intersection in the current green duration. The server determines the vehicle passing speed according to the average number of the passed vehicles in the phase, and if the vehicle passing speed is greater than the preset normal passing speed of the server, such as A, the current green light duration of the phase is in a saturated state, and the green light duration does not need to be modified; when the vehicle passing speed is lower than the normal passing speed A preset by the server, the current green light duration of the phase is too long, and the green light duration needs to be reduced.
The manner in which the green light duration is reduced can be determined according to the following equation:
g′n＝sn/v0
wherein, g'nIndicating the time of green light, s, after a reduction in the duration of green lightnIndicating the average number of vehicles passed, v, of the phase0Indicating a preset normal traffic speed.
S106, the server determines the green light time of the next time period of the phase based on the green light adjustment value and the current green light duration.
Wherein the next time period corresponds to a preset time period.
In the embodiment of the application, the server adjusts the green light time of the next time period according to the determined green light adjustment value, the server determines a green light adjustment value according to a preset time period, such as historical road images of 6-7 points of every wednesday in the previous month, and the server adjusts the green light duration time before 6 points of the wednesday. For example, if the green duration of phase a at 5 o 'clock on wednesday 50 is 30 seconds, and the server determines that the green adjustment value is 5 seconds by processing the historical road image, the server adjusts the green duration of phase a to 35 seconds at 6 o' clock.
S107, the server adjusts the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
In the embodiment of the application, the green light adjustment value of each phase is determined by processing the historical road image of each phase, so as to adjust the timing scheme of the traffic signal in the next time period. According to the method and the device, the timing scheme of the road intersection is adjusted in real time through the research on the vehicle queuing length and the vehicle queuing number, so that the traffic environment of the complicated and changeable road intersection is not complicated any more, and the traffic tension is relieved.
In the embodiment of the present application, as for the above solution S102, the following embodiment may also be adopted to determine the vehicle queue length of each lane corresponding to each phase, as shown in fig. 4:
s401, the server processes each historical road image according to the road lane information to obtain a vehicle queue image corresponding to at least one lane image corresponding to the historical road image.
The vehicle queue image is used for representing the vehicle image after the binarization processing of the single lane. In the embodiment of the application, the server needs to perform the following processing on the historical road image so as to obtain a corresponding vehicle queue image. As shown in fig. 5:
s501, the server identifies the historical road image to determine a road background image corresponding to the historical road image.
In the embodiment of the application, the installation positions of the image acquisition devices are different, so that lanes corresponding to the acquired historical road images are different, in order to extract the vehicle images only in the corresponding lanes from the historical road images, the vehicle images can be extracted in a mode of removing the background of the historical road images, and the vehicle images can be acquired in a specific mode by adopting a background difference method. The server can determine a road background image corresponding to the historical road image according to the image acquisition device corresponding to the historical road image, wherein the road background image does not contain a vehicle image.
S502, the server determines the historical road image after the pixel points of the road background image are removed based on the road background image and the historical road image.
In the embodiment of the application, the server removes the pixel points containing the road background image in the historical road image, so that the vehicle image in the lane can be more accurately acquired, and the influence of irrelevant factors on the calculation of the vehicle queue length is avoided.
S503, corroding the historical road image with the pixel points of the road background image removed by the server through the structural element SE to obtain the de-noised historical road image.
In the embodiment of the application, fine white noise points exist in the historical road image after the pixel points of the road background image are removed, the server corrodes the image by using the structural element SE, and the fine white noise points are eliminated, so that the de-noised historical road image is obtained.
In one embodiment of the application, the corroded historical road image may be too large and easy to break, so that the corroded historical road image can be further processed to obtain a clear vehicle queue image. The server obtains a vehicle edge image by performing CANNY edge detection on the vehicle image that is not binarized and acquired in S501. And the server supplements the vehicle edge image to the de-noising historical road image, so that a clearer vehicle queuing image can be obtained.
S504, the server determines vehicle queuing images corresponding to all lanes in all historical road images based on the de-noised historical road images.
The server can obtain the de-noised historical road image of each lane of each phase through the scheme, and the vehicle queue image corresponding to each lane can be obtained through a lane region segmentation mode. The lane area segmentation can be realized by the following embodiments, as shown in fig. 6, specifically including S601-S603:
s601, the server determines lane area information in the historical road image.
The lane area information includes a lane area length and a lane area width.
In the embodiment of the application, because the setting positions of the image acquisition devices are different, and the lane areas in the historical road image are different in shape, the server can determine the length and the width of the lane area corresponding to the historical road image in advance so as to determine the shape of the vehicle queuing image in the historical road image. Taking the image acquisition device as an electronic eye arranged above a stop line of a road intersection as an example, the electronic eye a acquires an image of a first lane in a straight-going phase, and the server can establish a space coordinate system according to the arrangement position of the electronic eye a, so that lane area information of the first lane image acquired by the electronic eye a can be determined.
S602, the server determines the lane area images of the historical road images of the lanes of each phase according to the lane area information.
In the embodiment of the application, the historical road image may include more than one lane, and also include vehicles in other lanes and other lanes, so that the server may determine the image only including the corresponding lane area according to the lane area information.
S603, the server carries out binarization processing on the images of the lane areas to obtain vehicle queue images corresponding to all lanes in all historical road images.
In the embodiment of the application, in order to reduce unnecessary influence factors and highlight the contour of a vehicle image, image binarization processing is performed on the image of a lane area, that is, the gray value of a pixel point in the image is set to be 0 or 255, so that the image has a black-and-white effect, and the contour of the vehicle after binarization processing is white. And the server performs the processing on the historical road images of the lanes in each phase to obtain vehicle queue images corresponding to the lanes.
By the scheme, the vehicle outline is displayed more clearly on the vehicle queuing image, noise points and redundant images in the image are reduced, and convenience is provided for a subsequent server to determine the vehicle queuing length.
S402, the server sets corresponding movable areas for the lane images according to a sliding window algorithm, and determines whether vehicles exist in the preset starting point area of the vehicle queuing images according to the movable areas.
The preset movable area is used for judging whether a vehicle image exists in the vehicle queuing images or not. As shown in fig. 7, 1 is a preset movable area, 2 is a stop line, 3 is a vehicle pixel point, and 4 is a preset start area. In the embodiment of the application, whether the vehicle image exists in the preset movable area is determined by presetting the proportion of all the pixel points in the area occupied by the vehicle pixel points 3 in the movable area 1. According to the method and the device, the green light adjustment value needs to be determined according to the vehicle queuing length, and the vehicle queuing starting point needs to be determined. Therefore, a preset starting point region 4 is set in the vehicle queuing image, the preset starting point region is a distance preset after the stop line 2, and if vehicle pixel points exist in the preset starting point region, it is indicated that the vehicle queuing exists in the preset starting point region 4.
S403, under the condition that the vehicle image exists in the preset starting point area, the server sets an approaching straight line in the preset starting point area, moves the approaching straight line according to the preset direction until the pixel value of the approaching straight line at the current position is larger than a third preset threshold value and the difference value between the pixel value and the pixel value at the previous position is larger than a fourth preset threshold value, and determines a queuing vehicle starting line.
The start line of the queued vehicle is the position of the image of the vehicle closest to the stop line of the preset start area. In the embodiment of the application, when the vehicle image exists in the preset starting point area, the approaching straight line moves towards the preset direction and moves towards the upper part of the image far away from the stop line according to the preset moving pixel distance. And in the process of approaching linear movement, determining whether the pixel value on the approaching linear is greater than a third preset threshold value or not, and whether the difference value between the pixel value and the pixel value at the previous position is greater than a fourth preset threshold value or not, and taking the first position of the approaching linear meeting the conditions as a starting line of the queued vehicles.
S404, the server slides the preset movable area from the starting line of the queued vehicles according to the preset direction and the preset step length to determine the finishing line of the queued vehicles.
In the embodiment of the application, after the server determines the starting line of the queued vehicles, the preset movable area slides from the position of the starting line of the queued vehicles according to the preset direction and the preset step length, and the preset step length can be set as the width of the preset movable area. And determining vehicle pixel points in the preset movable area of each sliding position in the sliding process of the preset movable area.
In this embodiment of the application, when the preset movable area is at a certain position, and under the condition that the number of vehicle pixels in the preset movable area is smaller than the fifth preset threshold, that is, under the condition that there are very few vehicle pixels, it is indicated that there is no vehicle in line at the position. The server takes the position immediately above that position as the in-line vehicle ending area and determines the in-line vehicle ending line in the in-line vehicle ending area in a manner that determines the in-line vehicle starting line.
S405, the server determines the vehicle queuing length in each historical road image corresponding to each phase based on the queuing vehicle start line and the queuing vehicle finish line.
According to the embodiment of the application, the queuing vehicle starting line and the queuing vehicle finishing line are determined in the vehicle queuing image, namely the vehicle queuing length can be determined according to the moving times of the preset movable area between the queuing vehicle starting line and the queuing vehicle finishing line. If the moving times are 4 times and the moving step length is 4 pixel points each time, it is indicated that 4 x 4+4 pixel points are formed between the queuing vehicle start line and the queuing vehicle finish line, and the vehicle queuing length can be determined by converting the distance of 4 x 4+4 pixel points and the actual measurement data.
In an embodiment of the application, the conversion between the pixel distance and the actual measurement data may be performed by establishing a distance fitting equation according to the actual measurement data of the lane corresponding to the vehicle queuing image, so as to determine the corresponding relationship between the pixel distance and the actual distance in the vehicle queuing image. And determining the vehicle queuing length in each historical road image according to a distance fitting equation, the pixel distance of the starting line of the queued vehicles and the pixel distance of the finishing line of the queued vehicles.
According to the scheme, a new traffic signal timing scheme is formulated through the research on the vehicle queuing length of the road intersection, and the influence of the position factor of the road intersection on the traffic signal timing is not considered. In an actual traffic road, a previous intersection often affects the traffic condition of a next intersection, and therefore, the green duration is further adjusted by the following embodiment.
In one embodiment of the application, the server determines position information of the intersection, and the priority value of the intersection can be determined according to the position information. The position information of the road intersection comprises the types of lanes of the road intersection, such as a main road, an express way and the like. The higher the grade of the lane type of the road intersection is, the larger the priority value of the road intersection is, for example, the priority value of the express way is 1, and the priority value of the main road is 0.8.
The server is stored with the vehicle queue number and the preset correlation coefficient between the road intersection and the adjacent road intersection in advance. Because the traffic conditions of adjacent road intersections influence each other, the related influence factor of the road intersection can be obtained according to actual experimental data, and the related influence factor is used as a preset correlation coefficient between the road intersection and the adjacent road intersection.
Taking the east-west straight-going phase as an example, according to the priority value of the road intersection and the preset correlation coefficient between the road intersection and the adjacent road intersection, the signal period coordination parameter of the phase can be obtained through the following formula, so as to determine the green light adjustment value of the corresponding phase. Wherein, the signal period coordination parameter of the phase is determined according to the following formula:
Figure BDA0003034803050000161
Figure BDA0003034803050000162
wherein, theta1The kth signal period coordination parameter for the phase, alpha is the priority value of the intersection, m1Is the average vehicle queue length, beta is the correlation coefficient with other road intersections,
Figure BDA0003034803050000163
the coordination parameter for the other road crossings for the kth signal period of the phase,
Figure BDA0003034803050000164
the coordination parameters of other road intersections in the k-1 signal period of the signal lamp of the corresponding phase are n, and the n is the number of the other road intersections.
And the k signal period coordination parameter of the phase obtained through the above shows that in a preset time period, the k signal period coordination parameter of the traffic signal lamp, and one signal period is a period in which the traffic signal lamp is changed from a passing state to a no-passing state and then to a passing state. According to the time of a single vehicle passing through the intersection in an ideal state and the kth signal period coordination parameter of the phase, the green light time of the east-west straight-going phase, which needs to be adjusted, can be obtained, and the time of the single vehicle passing through the intersection in the ideal state can be calculated according to historical data. The formula is as follows:
tg＝A·θ1
wherein, tgThe duration of the green light representing the phase, and a represents the time taken for a single vehicle to pass through the intersection under ideal conditions. The server can adjust the duration time of the green light of each phase through the scheme, and further adjust the current traffic signal timing scheme.
Based on the same inventive concept, the embodiment of the application also provides equipment corresponding to the method.
Fig. 8 is a schematic structural diagram of a traffic signal control device for a road intersection according to an embodiment of the present application, where as shown in fig. 8, the device includes:
at least one processor; and a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to: and acquiring a corresponding historical road image set in each phase preset time period of the road intersection. The historical road images in the historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when the traffic lane corresponding to each phase is switched from a traffic state to a no-traffic state. The road intersection is a cross intersection. And carrying out image recognition on each historical road image, and determining the vehicle queue length and the vehicle queue number of each lane corresponding to each phase. And acquiring the number of the passed vehicles of each lane corresponding to each phase. And determining whether the maximum vehicle queuing number in the set of vehicle queuing numbers is larger than a first preset threshold value. And under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, calculating the average value of the vehicle queuing lengths of the lanes corresponding to the phases as the average vehicle queuing length of the phases. And calculating the average value of the number of the passed vehicles of each lane corresponding to each phase as the average number of the passed vehicles of the phase. And determining the green light adjustment value of the phase according to the average vehicle queuing length, the average number of the vehicles passing through and the current green light duration of the phase. And determining the green light time of the next time period of the phase based on the green light adjustment value and the current green light duration. Wherein the next time period corresponds to the preset time period. And adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. A method of traffic signal control for a pathway intersection, the method comprising:
acquiring a historical road image set corresponding to each phase of the road intersection within a preset time period; the method comprises the steps that historical road images in a historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when lanes corresponding to phases are switched from a passing state to a no-passing state; the road intersection is a cross intersection;
carrying out image recognition on each historical road image, and determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase; acquiring the number of passed vehicles of each lane corresponding to each phase;
determining whether the maximum vehicle queuing number in a set consisting of the vehicle queuing numbers is greater than a first preset threshold value;
under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, calculating the average value of the vehicle queuing lengths of the lanes corresponding to the phases as the average vehicle queuing length of the phases; calculating the average value of the number of the passed vehicles of each lane corresponding to each phase, and taking the average value as the average number of the passed vehicles of the phase;
determining a green light adjustment value of the phase according to the average vehicle queuing length, the average number of vehicles passing through and the current green light duration of the phase;
determining a green light time for the next time period of the phase based on the green light adjustment value and the current green light duration; wherein the next time period corresponds to the preset time period;
and adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
2. The method according to claim 1, wherein the image recognition of each of the historical road images to determine the vehicle queue length and the vehicle queue number of each lane corresponding to each phase specifically comprises:
performing image recognition on each historical road image, and determining the vehicle contour of the vehicle positioned in each lane in each historical road image;
calculating the spacing distance between adjacent vehicle profiles in each lane, and generating a spacing distance sequence corresponding to the spacing distance;
sequentially determining whether the spacing distance in the spacing distance sequence is greater than a second preset threshold value;
taking the corresponding vehicle profile close to the stop line as a stop vehicle under the condition that the spacing distance is greater than a second preset threshold value;
and determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase according to the stop vehicle.
3. The method according to claim 2, wherein the determining the vehicle queue length and the vehicle queue number of each lane corresponding to each phase according to the end vehicle specifically comprises:
determining a vehicle contour with the minimum distance from the corresponding stop line according to the historical road image;
determining whether the distance between the vehicle contour with the minimum distance and the stop line is smaller than a third preset threshold value;
taking the vehicle contour with the minimum distance as a corresponding starting vehicle under the condition that the distance between the vehicle contour with the minimum distance and the stop line is smaller than a third preset threshold value;
and determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase according to the ending vehicle and the starting vehicle.
4. The method according to claim 1, wherein the image recognition of the historical road image to determine the vehicle queue length and the vehicle queue number of each lane corresponding to each phase specifically comprises:
processing each historical road image according to road lane information to obtain a vehicle queuing image corresponding to at least one lane image corresponding to the historical road image;
setting corresponding movable areas for the lane images according to a sliding window algorithm, and determining whether vehicles exist in a preset starting point area of the vehicle queuing images or not according to the movable areas;
under the condition that the vehicle image exists in the preset starting point area, setting an approaching straight line in the preset starting point area, moving the approaching straight line according to a preset direction until the pixel value of the approaching straight line at the current position is larger than a third preset threshold value and the difference value between the pixel value and the pixel value at the previous position is larger than a fourth preset threshold value, and determining a queuing vehicle starting line;
sliding the preset movable area from the queuing vehicle start line according to the preset direction and the preset step length to determine a queuing vehicle finish line;
and determining the vehicle queuing length in each historical road image corresponding to each phase based on the queuing vehicle start line and the queuing vehicle finish line.
5. The method according to claim 4, wherein the image recognition of the historical road image to obtain the vehicle queue image corresponding to each lane in each historical road image specifically comprises:
determining a road background image corresponding to the historical road image by carrying out image recognition on the historical road image;
determining the historical road image after removing the pixel points of the road background image based on the road background image and the historical road image;
corroding the historical road image with the pixel points of the road background image removed by using a structural element SE to obtain a de-noised historical road image;
and determining vehicle queuing images corresponding to all lanes in all the historical road images based on the de-noised historical road images.
6. The method according to claim 5, wherein the image recognition is performed on the historical road image to obtain a vehicle queue image corresponding to each lane in each historical road image, and specifically, the method further comprises:
determining lane area information in the historical road image; wherein the lane area information includes a lane area length and a lane area width;
determining an image of a lane area of the historical road image of each lane of each phase according to the lane area information;
and carrying out binarization processing on the images of the lane areas to obtain vehicle queue images corresponding to all lanes in all historical road images.
7. The method according to claim 4, wherein the determining the vehicle queue length in each historical road image corresponding to each phase based on the queued vehicle start line and the queued vehicle finish line specifically comprises:
establishing a distance fitting equation according to actual measurement data of the lanes corresponding to the vehicle queuing image so as to determine the corresponding relation between the pixel distance in the vehicle queuing image and the actual distance;
and determining the vehicle queuing length in each historical road image based on the distance fitting equation and the pixel distance of the queuing vehicle start line and the queuing vehicle finish line.
8. The method of claim 1, further comprising:
determining a preset priority value of the road intersection based on the position information of the road intersection;
determining preset correlation coefficients of the road intersection and the adjacent road intersection according to the vehicle queue number;
determining a signal period coordination parameter of the phase based on the preset priority value of the road intersection and a preset correlation coefficient between the road intersection and an adjacent road intersection so as to determine a green light adjustment value of the corresponding phase;
wherein the signal period coordination parameter of the phase is determined according to the following formula:
Figure FDA0003034803040000041
Figure FDA0003034803040000042
wherein, theta1A is the kth signal period coordination parameter of the phase, a is the preset priority value of the intersection, m1Beta is the preset correlation coefficient between the intersection and the adjacent intersection,
Figure FDA0003034803040000043
the coordination parameters of the other road crossings for the kth signal period of the phase,
Figure FDA0003034803040000044
and the coordination parameters are coordination parameters of other road intersections in the k-1 signal period of the corresponding phase signal lamp, and n is the number of the other road intersections.
9. A traffic information control apparatus for a road intersection, characterized by comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring a historical road image set corresponding to each phase of the road intersection within a preset time period; the method comprises the steps that historical road images in a historical road image set are acquired by corresponding image acquisition equipment at a preset acquisition time, and the preset acquisition time is the time when lanes corresponding to phases are switched from a passing state to a no-passing state; the road intersection is a cross intersection;
carrying out image recognition on each historical road image, and determining the vehicle queuing length and the vehicle queuing number of each lane corresponding to each phase; acquiring the number of passed vehicles of each lane corresponding to each phase;
determining whether the maximum vehicle queuing number in a set consisting of the vehicle queuing numbers is greater than a first preset threshold value;
under the condition that the maximum vehicle queuing number is larger than a first preset threshold value, calculating the average value of the vehicle queuing lengths of the lanes corresponding to the phases as the average vehicle queuing length of the phases; calculating the average value of the number of the passed vehicles of each lane corresponding to each phase, and taking the average value as the average number of the passed vehicles of the phase;
determining a green light adjustment value of the phase according to the average vehicle queuing length, the average number of vehicles passing through and the current green light duration of the phase;
determining a green light time for the next time period of the phase based on the green light adjustment value and the current green light duration; wherein the next time period corresponds to the preset time period;
and adjusting the current traffic signal timing scheme based on the green light time of the next time period of each phase to control the traffic signal of the next time period of the intersection.
10. A traffic signal control medium for a pathway intersection having stored thereon computer executable instructions for performing a method of traffic signal control for a pathway intersection as claimed in any one of claims 1 to 8.
CN202110440444.7A 2021-04-23 2021-04-23 Traffic signal control method, equipment and medium for road intersection Active CN113129595B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110440444.7A CN113129595B (en) 2021-04-23 2021-04-23 Traffic signal control method, equipment and medium for road intersection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110440444.7A CN113129595B (en) 2021-04-23 2021-04-23 Traffic signal control method, equipment and medium for road intersection

Publications (2)

Publication Number Publication Date
CN113129595A true CN113129595A (en) 2021-07-16
CN113129595B CN113129595B (en) 2022-06-10

Family

ID=76779471

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110440444.7A Active CN113129595B (en) 2021-04-23 2021-04-23 Traffic signal control method, equipment and medium for road intersection

Country Status (1)

Country Link
CN (1) CN113129595B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706873A (en) * 2021-09-28 2021-11-26 长沙智能驾驶研究院有限公司 Vehicle arrival time prediction method, device, equipment and computer storage medium
CN113851008A (en) * 2021-10-25 2021-12-28 深圳技术大学 Traffic signal lamp control method, device, equipment and storage medium
CN114093179A (en) * 2021-12-02 2022-02-25 智道网联科技(北京)有限公司 Vehicle scheduling method, cloud server, equipment and storage medium for cross intersection
CN114202916A (en) * 2021-12-01 2022-03-18 辽宁警察学院 Single-point intersection traffic signal control method
CN114446066A (en) * 2021-12-30 2022-05-06 银江技术股份有限公司 Road signal control method and device
CN115083160A (en) * 2022-06-15 2022-09-20 国汽智控(北京)科技有限公司 Signal lamp control method and device and signal lamp controller
CN116092297A (en) * 2023-04-07 2023-05-09 南京航空航天大学 Edge calculation method and system for low-permeability distributed differential signal control
CN116912779A (en) * 2023-09-12 2023-10-20 四川弘和数智集团有限公司 Queuing detection method and device, electronic equipment and readable storage medium

Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005182308A (en) * 2003-12-17 2005-07-07 Denso Corp Vehicle driving support device
CN101469985A (en) * 2007-12-26 2009-07-01 河海大学常州校区 Single-frame image detection apparatus for vehicle queue length at road junction and its working method
CN102360531A (en) * 2011-09-30 2012-02-22 哈尔滨工业大学 Intelligent traffic light control method and system based on wireless sensor network
JP2013036932A (en) * 2011-08-10 2013-02-21 Fujitsu Ltd Vehicle line length measurement device, vehicle line length measurement method, and computer program for measuring vehicle line length
JP2013045242A (en) * 2011-08-23 2013-03-04 Yazaki Energy System Corp On-vehicle device for monitoring events
CN103258425A (en) * 2013-01-29 2013-08-21 中山大学 Method for detecting vehicle queuing length at road crossing
DE102012204123A1 (en) * 2012-03-15 2013-09-19 Deutsches Zentrum für Luft- und Raumfahrt e.V. Method for determining queue length of traffic objects and/or vehicle groups, involves determining numerically identified traffic density by interpolation and core approximations at specific order, with extreme and/or turning points
CN103903445A (en) * 2014-04-22 2014-07-02 北京邮电大学 Vehicle queuing length detection method and system based on video
CN104021670A (en) * 2014-03-27 2014-09-03 湖南工业大学 Method for extracting vehicle queue state information in urban road network based on high-resolution remote-sensing image
CN105513342A (en) * 2015-11-25 2016-04-20 南京莱斯信息技术股份有限公司 Video-tracking-based vehicle queuing length calculating method
CN105632196A (en) * 2014-09-16 2016-06-01 赵菲菲 Method and system for controlling traffic signal lamp in real time and intelligently
CN106997673A (en) * 2017-06-05 2017-08-01 南通大学 Determine the method and system of the traffic lights redundancy duration in track
CN107644528A (en) * 2017-08-02 2018-01-30 浙江工业大学 A kind of vehicle queue length detection method based on vehicle tracking
CN107644529A (en) * 2017-08-03 2018-01-30 浙江浩腾电子科技股份有限公司 A kind of vehicle queue length detection method based on motion detection
CN108109380A (en) * 2018-01-31 2018-06-01 迈锐数据（北京）有限公司 A kind of detecting system of vehicle queue length, method and device
CN108765981A (en) * 2018-06-20 2018-11-06 昆明理工大学 A kind of real-time queue length prediction technique of divided lane
CN109426788A (en) * 2017-08-31 2019-03-05 浙江宇视科技有限公司 Queue length detection method, device and server
CN109961639A (en) * 2019-01-29 2019-07-02 中电海康集团有限公司 Queue length estimation method in lane under a kind of hypersaturated state
CN110111590A (en) * 2019-06-04 2019-08-09 南京慧尔视智能科技有限公司 A kind of vehicle dynamic queue length detection method
CN110379180A (en) * 2019-07-05 2019-10-25 平安国际智慧城市科技股份有限公司 A kind of traffic signal control method, traffic-control unit and terminal device
CN110632917A (en) * 2018-06-21 2019-12-31 株式会社斯巴鲁 Automatic driving assistance system
CN112489456A (en) * 2020-12-01 2021-03-12 山东交通学院 Signal lamp regulation and control method and system based on urban trunk line vehicle queuing length

Patent Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005182308A (en) * 2003-12-17 2005-07-07 Denso Corp Vehicle driving support device
CN101469985A (en) * 2007-12-26 2009-07-01 河海大学常州校区 Single-frame image detection apparatus for vehicle queue length at road junction and its working method
JP2013036932A (en) * 2011-08-10 2013-02-21 Fujitsu Ltd Vehicle line length measurement device, vehicle line length measurement method, and computer program for measuring vehicle line length
JP2013045242A (en) * 2011-08-23 2013-03-04 Yazaki Energy System Corp On-vehicle device for monitoring events
CN102360531A (en) * 2011-09-30 2012-02-22 哈尔滨工业大学 Intelligent traffic light control method and system based on wireless sensor network
DE102012204123A1 (en) * 2012-03-15 2013-09-19 Deutsches Zentrum für Luft- und Raumfahrt e.V. Method for determining queue length of traffic objects and/or vehicle groups, involves determining numerically identified traffic density by interpolation and core approximations at specific order, with extreme and/or turning points
CN103258425A (en) * 2013-01-29 2013-08-21 中山大学 Method for detecting vehicle queuing length at road crossing
CN104021670A (en) * 2014-03-27 2014-09-03 湖南工业大学 Method for extracting vehicle queue state information in urban road network based on high-resolution remote-sensing image
CN103903445A (en) * 2014-04-22 2014-07-02 北京邮电大学 Vehicle queuing length detection method and system based on video
CN105632196A (en) * 2014-09-16 2016-06-01 赵菲菲 Method and system for controlling traffic signal lamp in real time and intelligently
CN105513342A (en) * 2015-11-25 2016-04-20 南京莱斯信息技术股份有限公司 Video-tracking-based vehicle queuing length calculating method
CN106997673A (en) * 2017-06-05 2017-08-01 南通大学 Determine the method and system of the traffic lights redundancy duration in track
CN107644528A (en) * 2017-08-02 2018-01-30 浙江工业大学 A kind of vehicle queue length detection method based on vehicle tracking
CN107644529A (en) * 2017-08-03 2018-01-30 浙江浩腾电子科技股份有限公司 A kind of vehicle queue length detection method based on motion detection
CN109426788A (en) * 2017-08-31 2019-03-05 浙江宇视科技有限公司 Queue length detection method, device and server
CN108109380A (en) * 2018-01-31 2018-06-01 迈锐数据（北京）有限公司 A kind of detecting system of vehicle queue length, method and device
CN108765981A (en) * 2018-06-20 2018-11-06 昆明理工大学 A kind of real-time queue length prediction technique of divided lane
CN110632917A (en) * 2018-06-21 2019-12-31 株式会社斯巴鲁 Automatic driving assistance system
CN109961639A (en) * 2019-01-29 2019-07-02 中电海康集团有限公司 Queue length estimation method in lane under a kind of hypersaturated state
CN110111590A (en) * 2019-06-04 2019-08-09 南京慧尔视智能科技有限公司 A kind of vehicle dynamic queue length detection method
CN110379180A (en) * 2019-07-05 2019-10-25 平安国际智慧城市科技股份有限公司 A kind of traffic signal control method, traffic-control unit and terminal device
CN112489456A (en) * 2020-12-01 2021-03-12 山东交通学院 Signal lamp regulation and control method and system based on urban trunk line vehicle queuing length

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706873A (en) * 2021-09-28 2021-11-26 长沙智能驾驶研究院有限公司 Vehicle arrival time prediction method, device, equipment and computer storage medium
CN113706873B (en) * 2021-09-28 2022-11-29 长沙智能驾驶研究院有限公司 Vehicle arrival time prediction method, device, equipment and computer storage medium
CN113851008A (en) * 2021-10-25 2021-12-28 深圳技术大学 Traffic signal lamp control method, device, equipment and storage medium
CN114202916A (en) * 2021-12-01 2022-03-18 辽宁警察学院 Single-point intersection traffic signal control method
CN114093179A (en) * 2021-12-02 2022-02-25 智道网联科技(北京)有限公司 Vehicle scheduling method, cloud server, equipment and storage medium for cross intersection
CN114446066A (en) * 2021-12-30 2022-05-06 银江技术股份有限公司 Road signal control method and device
CN114446066B (en) * 2021-12-30 2023-05-16 银江技术股份有限公司 Road signal control method and device
CN115083160A (en) * 2022-06-15 2022-09-20 国汽智控(北京)科技有限公司 Signal lamp control method and device and signal lamp controller
CN116092297A (en) * 2023-04-07 2023-05-09 南京航空航天大学 Edge calculation method and system for low-permeability distributed differential signal control
CN116912779A (en) * 2023-09-12 2023-10-20 四川弘和数智集团有限公司 Queuing detection method and device, electronic equipment and readable storage medium
CN116912779B (en) * 2023-09-12 2023-12-22 四川弘和数智集团有限公司 Queuing detection method and device, electronic equipment and readable storage medium

Also Published As

Publication number Publication date
CN113129595B (en) 2022-06-10

Similar Documents

Publication Publication Date Title
CN113129595B (en) Traffic signal control method, equipment and medium for road intersection
US11314973B2 (en) Lane line-based intelligent driving control method and apparatus, and electronic device
JP7106664B2 (en) Intelligent driving control method and device, electronic device, program and medium
CN108986465B (en) Method, system and terminal equipment for detecting traffic flow
CN113674527B (en) Traffic monitoring system and method based on intelligent traffic Internet of things
EP2546602B1 (en) Stereo camera apparatus
CN108509907B (en) Car light detection method, device, medium and equipment for realizing intelligent driving
CN106647776B (en) Method and device for judging lane changing trend of vehicle and computer storage medium
CN102231236B (en) Method and device for counting vehicles
CN111613070B (en) Traffic signal lamp control method, traffic signal lamp control device, electronic equipment and computer storage medium
EP3979196A1 (en) Image processing method and apparatus for target detection
US20190026923A1 (en) Image recognition system
CN107924568B (en) Image processing apparatus, image processing method, and storage medium
EP3955218A2 (en) Lane line detection method and apparatus, electronic device, computer storage medium, and computer program product
Odeh Management of an intelligent traffic light system by using genetic algorithm
CN109063630B (en) Rapid vehicle detection method based on separable convolution technology and frame difference compensation strategy
CN110718076A (en) Timing method and device of traffic signal lamp, electronic equipment and readable storage medium
CN103729828A (en) Video rain removing method
WO2021093335A1 (en) Method for automatically labeling lane changing intention based on high-noise trajectory data of vehicle
CN112149471B (en) Loop detection method and device based on semantic point cloud
US7747041B2 (en) Automated estimation of average stopped delay at signalized intersections
EP2975591A1 (en) Image pickup device, vehicle number image pickup device, and image pickup method
CN102163328B (en) Method for detecting and eliminating glare in traffic video image
CN109829935B (en) Scene sequence tracking processing method and device of vehicle and vehicle
CN116935631A (en) Abnormal traffic situation detection method, device and system based on radar fusion

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 250101 no.1188 Tianchen street, high tech Zone, Jinan City, Shandong Province

Applicant after: Shandong Jinyu Information Technology Group Co.,Ltd.

Address before: 250101 no.1188 Tianchen street, high tech Zone, Jinan City, Shandong Province

Applicant before: JINAN JINYU HIGHWAY INDUSTRY DEVELOPMENT Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant