CN116580547A - Intelligent control method and system for buried traffic signal lamp - Google Patents
Intelligent control method and system for buried traffic signal lamp Download PDFInfo
- Publication number
- CN116580547A CN116580547A CN202310652237.7A CN202310652237A CN116580547A CN 116580547 A CN116580547 A CN 116580547A CN 202310652237 A CN202310652237 A CN 202310652237A CN 116580547 A CN116580547 A CN 116580547A
- Authority
- CN
- China
- Prior art keywords
- pedestrians
- pedestrian
- time
- passing
- sidewalk
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 241000283070 Equus zebra Species 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/005—Traffic control systems for road vehicles including pedestrian guidance indicator
-
- 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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/085—Controlling traffic signals using a free-running cyclic timer
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/095—Traffic lights
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a traffic control system, in particular to an intelligent control method and system for an underground traffic signal lamp, which are used for acquiring pedestrian images of detection areas at two ends of a sidewalk in real time and determining the number of pedestrians in the images according to the pedestrian images; acquiring actual time for a pedestrian to pass through a sidewalk at least twice in a history record, and taking the average value of all the actual time as a passing coefficient; according to the current pedestrian number, the pedestrian path set passing time and the passing coefficient, determining the predicted passing time of the current pedestrian number; when the green light reaches the predicted passing time, the position information of the pedestrian is extracted according to the pedestrian image acquired in real time, and the extension time for changing the green light into the red light is determined according to the position information, the pedestrian speed and the passing coefficient. The application can realize the safe passing of pedestrians by controlling the change of the traffic signal lamp, and can give consideration to the passing of motor vehicles, thereby avoiding traffic jam.
Description
Technical Field
The application relates to the field of traffic signal control, in particular to an intelligent control method and system for an underground traffic signal lamp.
Background
Traffic accidents occurring on zebra crossings each year are still frequent, and no matter the traffic accidents are illegal problems of motor vehicles or social phenomena of crossing roads, the traffic accidents still have larger potential safety hazards.
Aiming at the frequent occurrence of traffic accidents on a zebra crossing road, a signal lamp system aiming at the problem of pedestrian crossing road safety is generated, namely, the underground traffic signal lamp is installed, pedestrians can more easily notice the traffic situation at the moment, the underground traffic signal lamp is installed at the two ends and the two sides of a pavement, when red lamps at the two ends are on, the pedestrians are forbidden to pass, green lamps are allowed to pass, and when green lamps at the two ends are on, the traffic signal lamps at the two sides keep yellow and always on. Usually, the traffic lights are switched to preset time, but when the traffic flow is large, a large number of people still exist in the sidewalk when the traffic lights are to be switched to red light, the traffic time is insufficient at this time, most people still follow the people to pass through the sidewalk, the traffic time is finished at this time, vehicles begin to pass, and accidents of 'car hitting people' easily occur at this time.
Therefore, how to intelligently adjust the display condition of the buried traffic signal lamp according to the traffic condition at the moment not only enables traffic to be smooth, but also can ensure the safety problem of pedestrians.
Disclosure of Invention
In order to solve the technical problems, the application aims to provide an intelligent control method and system for an underground traffic signal lamp, and the adopted technical scheme is as follows:
the application provides a technical scheme of an intelligent control method of an underground traffic signal lamp, which comprises the following steps:
acquiring pedestrian images of detection areas at two ends of a sidewalk in real time, and determining the number of pedestrians in the images according to the pedestrian images;
acquiring actual time for a pedestrian to pass through a sidewalk at least twice in a history record, and taking the average value of all the actual time as a passing coefficient; according to the current pedestrian number, the pedestrian path set passing time and the passing coefficient, determining the predicted passing time of the current pedestrian number;
when the green light reaches the predicted passing time, the position information of the pedestrian is extracted according to the pedestrian image acquired in real time, and the extension time for changing the green light into the red light is determined according to the position information, the pedestrian speed and the passing coefficient.
Further, the method also comprises the step of determining the flicker frequency of the adjusting signal lamp in the extended time:
according to pedestrian images acquired in real time, determining the moving direction of each pedestrian, classifying the pedestrians in all directions, and determining the crowd category in each direction; acquiring the speed of pedestrians in each crowd category, and calculating the movement consistency of all pedestrians in the crowd category;
calculating the difference value between the average speed value of all pedestrians in each group of people and the minimum speed value of all pedestrians, and determining a flicker index according to the difference value and the movement consistency;
determining pedestrian distribution indexes in each direction according to the crowd categories in each direction and the number of pedestrians in each crowd category;
and calculating the flicker frequency of the traffic signal lamp based on the flicker indexes, the pedestrian distribution indexes and the pedestrian overall average distance in the two directions.
Further, the process of determining the crowd category for each direction is: and clustering the crowd by adopting a k-means clustering method.
Further, the flicker index is:
Z＝uX·v 2
wherein Z is scintillation index, X is movement consistency of crowd in the same direction, v 2 Is the difference between the average speed and the minimum speed in the population.
Further, the flicker frequency is:
wherein f is the flicker frequency of the buried traffic signal lamps at two sides of the pavement, Z 1 ,Z 2 Respectively the flicker indexes in different directions, D 1 ，D 2 Respectively the overall average distance of pedestrians in different directions, Y 1 ,Y 2 The pedestrian distribution indexes in different directions are shown, t2 is the extension time,represents an upward rounding, wherein the pedestrian overall average distance is +.>i.noteq.j, p is the number of people in one direction, +.>And summing all obtained distances to obtain a value for the distance between any two rows of people in one direction.
Further, the predicted transit time is:
wherein T1 is the predicted passing time, T is the sidewalk set passing time, A is the passing coefficient, X is the current number of people to be passed, X' is the number of pedestrians corresponding to the time when the passing is just completed after the passing time T is passed after the camera acquired by the historical data, and [ (] represents the rounding operation).
Further, the obtaining process of the extension time is as follows:
judging whether pedestrians exist on a pavement according to the pedestrian images acquired in real time, and determining the pavement position of the pedestrians on the pavement at the moment when the pedestrians exist, wherein the pavement position comprises the positions of the two end parts of the pavement and the middle part of the pavement;
and determining the extension time according to the walking position and the walking speed of the pedestrians on the pedestrian image.
Further, the process of adjusting the extended time is as follows:
acquiring an image of the motor vehicle in the motor vehicle road detection area, and determining the number of waiting motor vehicles in the road detection area;
comparing the number of the waiting motor vehicles with the number of pedestrians on the sidewalk, and when the number of the waiting motor vehicles is smaller than the number of the pedestrians on the sidewalk, prolonging the time to be:
wherein s is the length of the sidewalk, v is the walking speed of pedestrians, A is the traffic coefficient, and a is the number of pedestrians on the sidewalk; when the number of the motor vehicles waiting is greater than or equal to the number of pedestrians on the sidewalk, the extension time is as follows:
where b is the number of vehicles waiting.
The application also provides an intelligent control system of the underground traffic light, which comprises a memory and a processor, wherein the processor executes the technical scheme stored in the memory and used for realizing the intelligent control method of the underground traffic light.
The application has the beneficial effects that:
the scheme of the application can be used for predicting the time required by the current pedestrian to pass through the sidewalk by utilizing the computer vision technology, intelligently adjusting the passing time according to the actual passing condition and adjusting the flashing frequency of the lamps at two sides to prompt the pedestrian to pass as soon as possible, thereby realizing high-efficiency and safe passing.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an underground traffic light installation;
FIG. 2 is a method flow chart of an intelligent control method for an underground traffic light of the present application;
FIG. 3 is a schematic illustration of a pedestrian walking position on a sidewalk approaching both ends of the sidewalk;
fig. 4 is a schematic view of a pedestrian walking position on a sidewalk in a middle region of the sidewalk.
Detailed Description
In order to further describe the technical means and effects adopted by the present application for achieving the preset purpose, the following detailed description of the specific embodiments, structures, features and effects thereof according to the present application is given with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
When pedestrians pass through a road, traffic signals are always converted in fixed time, the traffic time is insufficient in the peak period of the pedestrian flow, but the pedestrians are likely to continue to pass along with the people, namely, the pedestrians are still passing when passing is forbidden, and the pedestrians are interwoven with vehicles, so that the problems of accidents, traffic jam and the like are easily caused, therefore, the traffic time is required to be properly adjusted according to the actual traffic situation of the pedestrians, and the flickering frequency of the two side signal lamps is adjusted to prompt the pedestrians to pass, and therefore, the scheme of the application is to control the display situation of the underground traffic signals to guide the pedestrians. .
Therefore, the present application is directed to the fact that the buried traffic signal lamps in fig. 1 are installed at both sides and both ends of a pavement, the buried traffic signal lamps at both ends are rectangular and long-strip-shaped, the traffic lamps at both sides are round to protect the traffic safety of pedestrians, cameras are respectively arranged at both ends of the pavement to collect images, so that the traffic state of the pedestrians in the current image is analyzed, and accordingly, a proper traffic time is calculated according to the traffic state and the buried traffic signal lamps are controlled to display. Specifically, the application provides an intelligent control system for an underground traffic signal lamp, please refer to fig. 2, which comprises the following steps:
firstly, pedestrian images of detection areas at two ends of a sidewalk are acquired in real time, and the number of pedestrians in the images is determined according to the pedestrian images.
In this embodiment, as shown in fig. 1, pedestrian images of detection areas at both ends of a sidewalk are collected by cameras provided at both ends; the detection area is an area which can hold people at two sides of the sidewalk and can be set according to actual conditions.
When the pedestrian image is acquired, when the traffic signal lamp of the sidewalk is about to turn from red to green, the cameras on the two sides of the sidewalk acquire images of the pedestrians at the two ends of the sidewalk at the moment, the optimal passing time of the pedestrians is acquired according to the traffic condition in the images of the pedestrians, and the pedestrians are guided by controlling the display condition of the buried traffic signal lamp.
The people flow condition, namely the acquisition of the number of pedestrians, is that the statistics of the people flow is realized by utilizing the deep neural network, shoes and heads of pedestrians in images are identified by training the neural network, the detected shoes are probably far smaller than the actual number of shoes due to the fact that most of human bodies are shielded, and the number of the heads is easy to acquire compared with the shoes due to the fact that the heads are not easy to be shielded, so that the statistics of the people flow can obtain the pedestrian flow needing to pass in the current waiting area by taking the detected number of the heads as a basis, each image contains one head photo frame, then the pedestrian is one person, and cameras are arranged at two ends of the sidewalk, the monitoring range of the camera is the whole sidewalk and the waiting area, and therefore, the actual people flow is half of the sum of the number of the pedestrians in the images acquired by the two cameras.
The deep neural network is an existing mature image recognition technology, and the specific content of the network is as follows:
1. the network input is the pedestrian image collected by the camera, and the image is output as the surrounding frame containing the pedestrian head and shoes.
2. The network is structured as an Encoder-FC.
3. The loss function of the network is a mean square error loss function.
When the traffic light is about to be changed into a green light, cameras arranged at two ends of the sidewalk are used for collecting the situation of the sidewalk at the moment, the time of the pedestrians passing through the sidewalk is predicted according to the traffic flow at the moment, when the pedestrians are more, the required passing time is longer, and the pedestrians are guided to pass through the sidewalk by controlling the display situation of the underground traffic signal lamp within the maximum passing time.
Secondly, acquiring actual time for a pedestrian to pass through a sidewalk at least twice in a history record, and taking the average value of all the actual time as a passing coefficient; and determining the predicted passing time of the current pedestrian number according to the current pedestrian number, the pavement set passing time and the passing coefficient.
The predicted transit time in this embodiment is:
wherein T1 is the predicted passing time, T is the sidewalk set passing time, A is the passing coefficient, X is the current number of people to be passed, X' is the number of pedestrians corresponding to the time when the passing is just completed after the passing time T is passed after the camera acquired by the historical data, and [ (] represents the rounding operation).
Wherein log is 2 () The base number of the number is 2, or the number can be super-parameter, and the method can be specifically adjusted by an implementer according to specific implementation scenes, wherein the log function is selected because the log function is an increasingly slow function, so that the waiting time is prevented from being prolonged excessively along with the increase of the number of people.
The traffic coefficient a is determined by n sets of history data, wherein the history data is the time taken for a certain number of pedestrians to completely pass through the sidewalk, so as to obtain n sets of values of a, and the traffic coefficient a is finally determined as follows:
wherein A is a traffic coefficient, A i′ The estimated transit time is determined based on the current traffic volume for the time it takes for a certain number of pedestrians in the i' th set of historical data to pass completely through the sidewalk.
It should be noted that, the pavement set transit time T is an initial transit time, which is an initial set value. The acquisition of the traffic coefficient A is historical data determined according to actual conditions, wherein a certain number of the traffic coefficient A is the number of pedestrians collected at the moment closer to the current moment, and the traffic coefficient A has a certain reference value.
In order to prevent the traffic time of the pedestrians from being too long or too short, the traffic time t1 is within the range ofI.e. less than +.>Is set to->The time greater than 2T is set to 2T.
And then, when the green light reaches the predicted passing time, extracting the position information of the pedestrians according to the pedestrian images acquired in real time, and determining the extension time for changing the green light into the red light according to the position information, the pedestrian speed and the passing coefficient.
In this embodiment, on the basis of the predicted traffic time, the underground traffic signal lamps are controlled to be green in duration, that is, the duration of green is t1, when the underground traffic signal lamps at two ends become red after t1 seconds and send out alarm sounds to prohibit traffic, traffic of pedestrians which do not pass at this time is prohibited, the underground traffic signal lamps at two sides become yellow to urge the pedestrians which do not pass yet to pass rapidly, and the traffic time still needs to be properly prolonged to ensure the safety of the pedestrians which do not pass yet at this time, so after the traffic time t1 seconds is finished, cameras at two ends acquire the images of the pedestrians of the current sidewalk once again, and judge whether the pedestrians exist in the sidewalk area, if not, the traffic time does not need to be prolonged, and when the pedestrians still exist on the sidewalk at this time, the traffic time needs to be properly prolonged according to the traffic situation at this time, specifically, the following cases are adopted:
first, according to the pedestrian's position on the pavement, if crowd is located near pavement both ends (see fig. 3) and indicates that the pedestrian is about to accomplish the traffic, the extension time at this moment is:
where t2 is an extension time, s is a length of a sidewalk, v is a walking speed of a pedestrian in normal conditions, and v=1.5 m/s is taken according to an actual experience value.
Secondly, if the middle area contains pedestrians (see fig. 4), the distance of the pedestrians in the area is longer, and the acquisition of the extension time is more factors to be considered; such as the passing direction of pedestrians in the area, the number of people, etc., because a plurality of pedestrians with different passing directions may exist in the area, the passing speed may be slightly reduced due to the mutual avoidance of the opposite pedestrians. Meanwhile, the number of vehicles waiting on the motor vehicle road is also considered, if the extension time is too long, the vehicles are accumulated more and more to cause blockage, so when pedestrians exist in the middle of the pavement, the extension time also considers the vehicle condition at the moment, and the extension passing time of the pedestrians is not too long.
Therefore, the number of vehicles on one side of the pavement at the moment is acquired through the camera on the ground traffic signal lamp, and the number of vehicles in the image is acquired through the neural network, so that the extension time at the moment is comprehensively considered through the number of vehicles and the number of pedestrians:
(1) If the number of waiting vehicles is smaller than the number of pedestrians on the sidewalk, the time prolonged at this time is:
wherein A is a traffic coefficient, a is the number of head bounding boxes on the sidewalk at the time, s is the length of the sidewalk, and v is the walking speed of the pedestrian.
(2) If the number of vehicles is larger than the number of pedestrians on the sidewalk at this time, the pedestrians are considered to pass as soon as possible, and the shortening and prolonging time is as follows:
the method comprises the steps that a is the number of head bounding boxes on the sidewalk, s is the length of the sidewalk, v is the walking speed of pedestrians, b is the number of vehicles waiting for the sidewalk, and when the number of vehicles is more than that of the pedestrians, the extending passing time acquired by the pedestrians is relatively reduced, so that the vehicles and the pedestrians can pass in time.
It should be noted that, the method for acquiring the number of vehicles is the same as the method for acquiring the number of pedestrians, and will not be described here again.
Therefore, the extension time in this embodiment is:
wherein, the liquid crystal display device comprises a liquid crystal display device,indicated as no pedestrians in the middle area,/->Indicating that the middle area contains pedestrians, and when the entire sidewalk does not contain pedestrians, the extension time is 0.
In the embodiment, the sidewalk is divided into three areas, namely a middle part and two end parts, and the proper extension time is determined by judging the area of the pedestrian; dividing the sidewalk into three parts, judging the positions of pedestrians by judging the positions of the surrounding frames of the shoes, and if the middle region R of the sidewalk does not contain pedestrians and is only positioned at two end parts as shown in fig. 3, then the pedestrians on the sidewalk finish passing at the moment, and simultaneously, the two ends of the sidewalk can send out an alarm for prohibiting passing, so that the pedestrians at one end can be prevented from passing to the other end due to insufficient time; if located in the middle portion of the pavement, as shown in fig. 4, a certain extended time is required to complete the passage.
Further, in order to make the pedestrian on the pavement recognize the necessity of rapid traffic at this time in an extended period, the pedestrian needs to be reminded by controlling the flashing frequency of the two-side buried traffic lights, so the step of obtaining the flashing frequency of the signal lights on two sides of the pavement in the extended period further includes:
1. according to pedestrian images acquired in real time, determining the moving direction of each pedestrian, classifying the pedestrians in all directions, and determining the crowd category in each direction; acquiring the speed of pedestrians in each crowd category, and calculating the movement consistency of all pedestrians in the crowd category;
2. calculating the difference value between the average speed value of all pedestrians in each group of people and the minimum speed value of all pedestrians, and determining a flicker index according to the difference value and the movement consistency;
3. determining pedestrian distribution indexes in each direction according to the crowd categories in each direction and the number of pedestrians in each crowd category;
4. and calculating the flicker frequency of the traffic signal lamp based on the flicker indexes, the pedestrian distribution indexes and the pedestrian overall average distance in the two directions.
When classifying pedestrians in all directions in the above embodiment, firstly determining the crowd category of each direction to be real-time monitoring of the sidewalk through a camera, obtaining the moving direction of each pedestrian by utilizing a corner matching technology, and dividing the pedestrians into two directions; secondly, for pedestrians in the same direction, the number of the pedestrians and the distribution positions are calculated, and the more the number of the pedestrians is, the more the distance is, so that the pedestrians belong to scattered traffic at the moment, and the pedestrians need to be improved to be alert and quickly pass through by quickening the flickering of the yellow light.
The method for acquiring the number of the piles comprises the following steps: calculating the distance between pedestrians in the same direction, and calculating the position relationship between the pedestrians by using the center point of the head surrounding frame:
d in ij Expressed as the distance of a pedestrian in the same travel direction, (x) i ,y i ),(x j ,y j ) The coordinates of the center points of the head bounding boxes of the ith pedestrian and the jth pedestrian respectively, because the cameras are shot at two ends, the far-away person images can be slightly smaller, and therefore the distance is larger in the images acquired by the two cameras;
for d ij If the distance is less than or equal to 0.5m, the ith person and the jth person are considered asPeople belong to a person pile, thereby classifying the pedestrians on the sidewalk into k categories.
Of course, as other embodiments, the clustering of people can also be performed by adopting a k-means clustering method.
The movement consistency in this embodiment is:
where X represents the uniformity of movement of pedestrians, and a smaller value indicates a higher uniformity of pedestrian traffic, and a higher probability of arrival together, when X is equal to or greater than 0.1, it is considered that a pedestrian with a significantly faster speed or a pedestrian with a slower speed appears, and for a pedestrian with a slower speed, we need to promote grasping traffic by changing the flicker frequency, wherein,
wherein vp is the average speed of pedestrians in the man pile, v c And m is the number of pedestrians in the pile, wherein the moving speed of the c-th person in the pile is the moving speed of the c-th person in the pile.
The flicker index obtaining process in this embodiment is as follows:
1, calculate v 1 And v 2 ：
v 1 ＝v cmax -vp
v 2 ＝vp-v cmin
V in 1 V is the difference between the maximum speed and the average speed in the pile 2 V is the difference between the average speed and the minimum speed in the man pile cmax For maximum speed in the pile, v cmin Is the minimum speed in the pile;
2, if v 1 <v 2 It is considered that a slower pedestrian is present in the pile, for which case it is necessary to obtain a flicker index:
Z＝uX·v 2
wherein Z is a flicker index,the larger Z is, the higher the corresponding flicker is, the higher the value is, the more inconsistent is, v 2 The larger the speed difference for the slower one, the more far the pedestrian tends to fall behind.
The speed of the pedestrian in the pile, the maximum speed, and the minimum speed are obtained by dividing the distance taken from the pedestrian to the time when the pedestrian turns to a yellow light by the speed of each person, and the distance and time taken by the pedestrian are recorded by the monitoring camera.
Meanwhile, the distribution condition of the number of pedestrians in each pile in the same direction is calculated.
Wherein Y represents the dispersion condition of the number of pedestrians in each pile on the sidewalk, k represents the number of piles, r e For the number of pedestrians of the e-th person pile,the larger the Y value is, the larger the probability of showing the pedestrians with the falling bill is, and the flicker frequency is required to be adjusted to enable the pedestrians to grasp and pass through.
Meanwhile, the average distance of the whole pedestrians in the same direction is obtained:
wherein D is the overall average distance of pedestrians in the same direction, p is the number of people in one direction,for calculating the distance between any two rows of people in one direction, and summing the obtained distances to obtain a value, the larger the value of D is, the larger the pedestrian span passing in the same direction is, the possible dispersion is larger, the grasping time is required to pass, and the smaller the value of D is, the line passing in the same direction is illustratedPeople are more concentrated. At this time, the flicker frequencies at the two sides of the sidewalk are as follows:
wherein f is the flicker frequency of the buried traffic signal lamps at two sides of the pavement, Z 1 ,Z 2 The flicker indexes in different directions respectively show that the larger the value is, the pedestrians in the people pile have single pedestrians and are far behind, D 1 ，D 2 The average distances in different directions respectively show that the larger the value is, the longer the passing team is, the fast passing is needed, Y 1 ,Y 2 The pedestrian distribution conditions in different directions are shown, the larger the value is, the larger the probability of pedestrians with falling orders is, the flicker frequency is required to be increased to prompt the pedestrians with falling orders to pass rapidly, t2 is the extension time,representing an upward rounding. k (k) 1 ,k 2 The larger the number of people piles, the more dispersed the people, and D 1 ，D 2 The greater the overall team length, the greater the corresponding frequency will increase, thereby promoting pedestrian gripping time through the pavement.
The faster the yellow lights of the signal lights on both sides of the pavement in this embodiment flash, the higher the necessity for faster traffic.
The scheme of the application obtains the expected passing time and the time t1 and t2 which need to be prolonged through the steps. When the red light of the sidewalk is finished, the camera collects the image at the moment and obtains the predicted passing time t1, the camera collects the image again after the moment t1 and obtains the extension time t2 at the moment, and the passing time t2 is the forbidden passing time with fixed duration. The circulation can dynamically adjust the passing time according to the real-time traffic flow so as to improve the passing efficiency.
The two-end buried traffic signal lamps are controlled to be green when the passing time is estimated, the two-end buried traffic signal lamps are yellow and do not flash to ensure the passing of pedestrians, the two-end buried traffic signal lamps are controlled to be red when the passing time is prolonged to prevent the pedestrians which do not pass at the moment from continuing to pass, but the two-end buried traffic signal lamps flash according to the passing condition of the pedestrians to prompt the pedestrians to pass, the two-end buried traffic signal lamps are controlled to be red which lasts for a fixed time period to prevent the pedestrians from passing after the passing time is prolonged, and the two-end buried traffic signal lamps are not lightened to ensure the normal passing of the vehicles.
The scheme of the application can solve the safety problem and traffic passing problem when pedestrians pass through the road in the peak period, predicts the time required by the current pedestrians to pass through the sidewalk by utilizing the computer vision technology, intelligently adjusts the passing time according to the actual passing condition and adjusts the flashing frequency of the lamps at two sides to prompt the pedestrians to pass as soon as possible, thereby realizing high-efficiency and safe passing.
The application also provides an intelligent control system of the underground traffic light, which comprises a memory and a processor, wherein the processor executes the technical scheme stored in the memory and used for realizing the intelligent control method of the underground traffic light.
Because an intelligent control method of an underground traffic light has been described in detail in the above method embodiments, details are not repeated here.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (9)
1. An intelligent control method of an underground traffic signal lamp is characterized by comprising the following steps:
acquiring pedestrian images of detection areas at two ends of a sidewalk in real time, and determining the number of pedestrians in the images according to the pedestrian images;
acquiring actual time for a pedestrian to pass through a sidewalk at least twice in a history record, and taking the average value of all the actual time as a passing coefficient; according to the current pedestrian number, the pedestrian path set passing time and the passing coefficient, determining the predicted passing time of the current pedestrian number;
when the green light reaches the predicted passing time, the position information of the pedestrian is extracted according to the pedestrian image acquired in real time, and the extension time for changing the green light into the red light is determined according to the position information, the pedestrian speed and the passing coefficient.
2. The intelligent control method for an underground traffic light according to claim 1, further comprising the step of determining a flicker frequency of the adjustment signal for an extended period of time:
according to pedestrian images acquired in real time, determining the moving direction of each pedestrian, classifying the pedestrians in all directions, and determining the crowd category in each direction; acquiring the speed of pedestrians in each crowd category, and calculating the movement consistency of all pedestrians in the crowd category;
calculating the difference value between the average speed value of all pedestrians in each group of people and the minimum speed value of all pedestrians, and determining a flicker index according to the difference value and the movement consistency;
determining pedestrian distribution indexes in each direction according to the crowd categories in each direction and the number of pedestrians in each crowd category;
and calculating the flicker frequency of the traffic signal lamp based on the flicker indexes, the pedestrian distribution indexes and the pedestrian overall average distance in the two directions.
3. The intelligent control method of an underground traffic light according to claim 2, wherein the determining of the crowd category for each direction is: and clustering the crowd by adopting a k-means clustering method.
4. The intelligent control method of an underground traffic light according to claim 2, wherein the flicker index is:
Z＝uX·v 2
wherein Z is scintillation index, X is movement consistency of crowd in the same direction, v 2 Is the difference between the average speed and the minimum speed in the population.
5. The intelligent control method of an underground traffic light according to claim 4, wherein the flicker frequency is:
wherein f is the flicker frequency of the buried traffic signal lamps at two sides of the pavement, Z 1 ,Z 2 Respectively the flicker indexes in different directions, D 1 ，D 2 Respectively the overall average distance of pedestrians in different directions, Y 1 ,Y 2 The pedestrian distribution indexes in different directions are shown, t2 is the extension time,represents an upward rounding, wherein the pedestrian overall average distance is +.>i is not equal to j, p is the number of people in one direction, C P 2 And summing all obtained distances to obtain a value for the distance between any two rows of people in one direction.
6. The intelligent control method of an underground traffic light according to claim 1, wherein the predicted transit time is:
wherein T1 is the predicted passing time, T is the sidewalk set passing time, A is the passing coefficient, X is the current number of people to be passed, X' is the number of pedestrians corresponding to the time when the passing is just completed after the passing time T is passed after the camera acquired by the historical data, and [ (] represents the rounding operation).
7. The intelligent control method of an underground traffic light according to claim 1, wherein the obtaining process of the extension time is:
judging whether pedestrians exist on a pavement according to the pedestrian images acquired in real time, and determining the pavement position of the pedestrians on the pavement at the moment when the pedestrians exist, wherein the pavement position comprises the positions of the two end parts of the pavement and the middle part of the pavement;
and determining the extension time according to the walking position and the walking speed of the pedestrians on the pedestrian image.
8. The intelligent control method of an underground traffic light according to claim 7, wherein the process of adjusting the extended time is:
acquiring an image of the motor vehicle in the motor vehicle road detection area, and determining the number of waiting motor vehicles in the road detection area;
comparing the number of the waiting motor vehicles with the number of pedestrians on the sidewalk, and when the number of the waiting motor vehicles is smaller than the number of the pedestrians on the sidewalk, prolonging the time to be:
s is the length of the sidewalk, v is the walking speed of the pedestrians in normal conditions, A is the passing coefficient, and a is the number of the pedestrians on the sidewalk;
when the number of the motor vehicles waiting is greater than or equal to the number of pedestrians on the sidewalk, the extension time is as follows:
where b is the number of vehicles waiting.
9. An intelligent control system for an underground traffic light, comprising a memory and a processor, wherein the processor executes steps stored in the memory for implementing an intelligent control method for an underground traffic light as claimed in any one of claims 1 to 8.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2022108737805 | 2022-07-25 | ||
| CN202210873780.5A CN114973701A (en) | 2022-07-25 | 2022-07-25 | Intelligent control method and system for buried traffic signal lamp |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116580547A true CN116580547A (en) | 2023-08-11 |
| CN116580547B CN116580547B (en) | 2024-05-03 |
Family
ID=82970306
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210873780.5A Pending CN114973701A (en) | 2022-07-25 | 2022-07-25 | Intelligent control method and system for buried traffic signal lamp |
| CN202310652237.7A Active CN116580547B (en) | 2022-07-25 | 2023-06-02 | Intelligent control method and system for buried traffic signal lamp |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210873780.5A Pending CN114973701A (en) | 2022-07-25 | 2022-07-25 | Intelligent control method and system for buried traffic signal lamp |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN114973701A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079448A (en) * | 2023-08-23 | 2023-11-17 | 南京鑫荣汇信息科技有限公司 | Induction system and method for intelligent panel active luminous sign |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116206436B (en) * | 2023-04-27 | 2023-07-07 | 山东领军智能交通科技有限公司 | Laser zebra crossing early warning equipment based on visible red light and control method thereof |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11275562A (en) * | 1998-03-20 | 1999-10-08 | Toshiba Corp | Moving person monitoring device |
| WO2008013386A1 (en) * | 2006-07-23 | 2008-01-31 | Tp-I Co., Ltd | System for controlling traffic light at crosswalk and method therefor |
| US20190333370A1 (en) * | 2018-04-27 | 2019-10-31 | Cubic Corporation | Adaptively controlling traffic movements for pedestrian safety |
| CN112309146A (en) * | 2020-10-28 | 2021-02-02 | 平安科技（深圳）有限公司 | Intelligent control method and system of traffic signal lamp, storage medium and computing equipment |
| KR102243845B1 (en) * | 2020-07-01 | 2021-04-23 | 주식회사 동부아이씨티 | Pedestrian information providing device at crosswalk |
| KR20210091569A (en) * | 2020-01-14 | 2021-07-22 | 렉스젠(주) | Traffic signal control system and method thereof |
| US20210319694A1 (en) * | 2020-04-09 | 2021-10-14 | Hyundai Mobis Co., Ltd. | Traffic light controller and method of controlling traffic light using the same |
| KR102317320B1 (en) * | 2021-06-18 | 2021-10-26 | (주)이티엑스 | Pedestrian Safety Management System |
| KR102338221B1 (en) * | 2020-08-14 | 2021-12-10 | 김윤규 | Auxiliary Traffic Light for Preventing Accident in Blind Spot |
| CN114511999A (en) * | 2020-11-17 | 2022-05-17 | 郑州宇通客车股份有限公司 | Pedestrian behavior prediction method and device |
| CN114530047A (en) * | 2022-01-28 | 2022-05-24 | 浙江梧斯源通信科技股份有限公司 | Stop line with early warning function and stop line lighting control method |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104282158B (en) * | 2013-07-10 | 2016-03-30 | 杭州海康威视数字技术股份有限公司 | A kind of traffic lights intelligent control method and system |
| CN104966401B (en) * | 2015-06-30 | 2017-06-16 | 广州市高科通信技术股份有限公司 | Road traffic signal control method and system based on video detection pedestrian's street crossing |
| CN105957356B (en) * | 2016-05-30 | 2018-06-29 | 曹莲英 | A kind of traffic control system and method based on pedestrian's quantity |
| CN107452212B (en) * | 2016-05-30 | 2020-08-25 | 深圳市奥芭特科技有限公司 | Crossing signal lamp control method and system |
| CN108074404A (en) * | 2016-11-14 | 2018-05-25 | 伍煜东 | Intelligent traffic management systems and method |
| CN106355885A (en) * | 2016-11-24 | 2017-01-25 | 深圳市永达电子信息股份有限公司 | Traffic signal dynamic control method and system based on big data analysis platform |
| CN110969879B (en) * | 2018-09-29 | 2022-12-27 | 上海博泰悦臻网络技术服务有限公司 | Automatic control method and system of traffic signal lamp |
| US11205082B2 (en) * | 2019-10-08 | 2021-12-21 | Toyota Research Institute, Inc. | Spatiotemporal relationship reasoning for pedestrian intent prediction |
-
2022
- 2022-07-25 CN CN202210873780.5A patent/CN114973701A/en active Pending
-
2023
- 2023-06-02 CN CN202310652237.7A patent/CN116580547B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11275562A (en) * | 1998-03-20 | 1999-10-08 | Toshiba Corp | Moving person monitoring device |
| WO2008013386A1 (en) * | 2006-07-23 | 2008-01-31 | Tp-I Co., Ltd | System for controlling traffic light at crosswalk and method therefor |
| US20190333370A1 (en) * | 2018-04-27 | 2019-10-31 | Cubic Corporation | Adaptively controlling traffic movements for pedestrian safety |
| KR20210091569A (en) * | 2020-01-14 | 2021-07-22 | 렉스젠(주) | Traffic signal control system and method thereof |
| US20210319694A1 (en) * | 2020-04-09 | 2021-10-14 | Hyundai Mobis Co., Ltd. | Traffic light controller and method of controlling traffic light using the same |
| KR102243845B1 (en) * | 2020-07-01 | 2021-04-23 | 주식회사 동부아이씨티 | Pedestrian information providing device at crosswalk |
| KR102338221B1 (en) * | 2020-08-14 | 2021-12-10 | 김윤규 | Auxiliary Traffic Light for Preventing Accident in Blind Spot |
| CN112309146A (en) * | 2020-10-28 | 2021-02-02 | 平安科技（深圳）有限公司 | Intelligent control method and system of traffic signal lamp, storage medium and computing equipment |
| WO2021189970A1 (en) * | 2020-10-28 | 2021-09-30 | 平安科技（深圳）有限公司 | Intelligent control method and system for traffic light, and storage medium and computing device |
| CN114511999A (en) * | 2020-11-17 | 2022-05-17 | 郑州宇通客车股份有限公司 | Pedestrian behavior prediction method and device |
| KR102317320B1 (en) * | 2021-06-18 | 2021-10-26 | (주)이티엑스 | Pedestrian Safety Management System |
| CN114530047A (en) * | 2022-01-28 | 2022-05-24 | 浙江梧斯源通信科技股份有限公司 | Stop line with early warning function and stop line lighting control method |
Non-Patent Citations (1)
| Title |
|---|
| 李成龙;: "右转车道与人行横道拥堵的分析与治理", 居舍, no. 27, 30 September 2017 (2017-09-30) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079448A (en) * | 2023-08-23 | 2023-11-17 | 南京鑫荣汇信息科技有限公司 | Induction system and method for intelligent panel active luminous sign |
| CN117079448B (en) * | 2023-08-23 | 2024-03-15 | 南京鑫荣汇信息科技有限公司 | Induction system and method for intelligent panel active luminous sign |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114973701A (en) | 2022-08-30 |
| CN116580547B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116580547B (en) | Intelligent control method and system for buried traffic signal lamp | |
| CN108417057B (en) | Intelligent signal lamp timing system | |
| CN113256965B (en) | Traffic risk sensing system and method based on smart city | |
| US20210201672A1 (en) | Video-based main road cooperative signal machine control method | |
| US10699568B1 (en) | Video-based crossroad signal machine control method | |
| US6411328B1 (en) | Method and apparatus for traffic incident detection | |
| US11250699B2 (en) | System and method of adaptive traffic management at an intersection | |
| CN111798678A (en) | Urban traffic intelligent monitoring coordination management system based on big data | |
| CN103955705A (en) | Traffic signal lamp positioning, recognizing and classifying method based on video analysis | |
| CN101727748A (en) | Method, system and equipment for monitoring vehicles based on vehicle taillight detection | |
| KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
| CN105741559A (en) | Emergency vehicle lane illegal occupation detection method based on lane line model | |
| WO2022213542A1 (en) | Method and system for clearing information-controlled intersection on basis of lidar and trajectory prediction | |
| CN113055649A (en) | Tunnel intelligent video monitoring method and device, intelligent terminal and storage medium | |
| CN111899514A (en) | Artificial intelligence's detection system that blocks up | |
| CN114781479A (en) | Traffic incident detection method and device | |
| CN111754767B (en) | Highway traffic early warning method, device and system based on intelligent lamp pole | |
| CN106327880A (en) | Vehicle speed identification method and system based on monitored video | |
| CN114170795A (en) | Internet of things traffic monitoring system in intelligent traffic system and use method thereof | |
| CN116128360A (en) | Road traffic congestion level evaluation method and device, electronic equipment and storage medium | |
| KR101133222B1 (en) | System and Method for monitoring traffic and accident based on image processing | |
| CN117198058B (en) | Road traffic intelligent supervision system based on remote sensing image | |
| CN102044152A (en) | Day and night video detecting method and device | |
| KR20200124972A (en) | System and method for detecting vehicle violating traffic regulation | |
| CN115662145A (en) | Emergency shunting method for vehicles on accident road section based on big data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |