CN107742418B - Automatic identification method for traffic jam state and jam point position of urban expressway - Google Patents
Automatic identification method for traffic jam state and jam point position of urban expressway Download PDFInfo
- Publication number
- CN107742418B CN107742418B CN201710904106.8A CN201710904106A CN107742418B CN 107742418 B CN107742418 B CN 107742418B CN 201710904106 A CN201710904106 A CN 201710904106A CN 107742418 B CN107742418 B CN 107742418B
- Authority
- CN
- China
- Prior art keywords
- traffic
- lane
- vehicle
- road section
- time
- 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.)
- Active
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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/205—Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental
Abstract
The invention discloses a method for automatically identifying the traffic jam state and the position of a traffic jam point of an urban expressway, which comprises the following steps: 1) setting threshold values of lane-dividing traffic parameters of each monitored road section; 2) collecting vehicle images/images in a field of view, converting to generate traffic data information of the divided lanes, and transmitting the traffic data information of the divided lanes to a traffic information processing server; 3) the traffic information processing server analyzes the congestion state and the position of the congestion point by utilizing real-time traffic data information and a traffic parameter threshold database; 4) and forwarding the analysis result and the corresponding suggestion to the user terminal according to the user setting. The invention can quickly judge the road section position and the lane where the traffic incident such as the cargo falling, the malicious jamming, the fault/illegal parking behavior or the traffic accident occurs at the first time, is beneficial to the traffic management department to reasonably respond in time, avoids the following more serious traffic jam and reduces the secondary accident rate.
Description
Technical Field
The invention relates to an automatic identification method for a traffic jam state and a traffic jam position of an urban expressway, which integrates road monitoring, image analysis and traffic state judgment, and belongs to the technical field of traffic jam monitoring.
Background
With the rapid increase of the automobile inventory in cities in China, the traffic jam condition is more serious. The basic reason that the traffic demand is large and the road infrastructure supply is relatively insufficient is inherent, but there are also 'sporadic traffic jams' caused by 'traffic incidents' such as vehicle 'snarling', fault/illegal parking, malicious traffic jams, goods dropping, traffic accidents, and the like.
The regularity and periodicity of the 'sporadic communication congestion' are not as obvious as the 'sporadic communication congestion', so that the 'sporadic communication congestion' is difficult to predict or prevent in advance; meanwhile, a certain proportion of 'sporadic traffic jam' has a small influence range and short duration, and the necessity of management seems to be insufficient, so that the traffic management department is difficult to pay attention to the traffic management department. However, related studies have shown that some seemingly minor traffic events eventually cause a large area of severe traffic congestion due to mishandling or inadequate response. It is seen that it is necessary for traffic management departments to accurately and timely learn the road traffic conditions (especially the traffic jam state and the positions of the traffic jam points).
Traditional urban road traffic congestion monitoring is mainly realized by manual monitoring, emergency calls or induction coil detectors. The manual monitoring efficiency is low, careless omission easily occurs, and the complex road network of a large city is difficult to deal with; the timeliness of the emergency call is poor, and the accuracy of judging the congestion degree is insufficient; the induction coil detector can only monitor partial traffic data, the road surface needs to be damaged when the system is installed, the follow-up maintenance is troublesome, and great use limitation exists. In recent years, with the rapid development of high-definition video information acquisition and transmission technology and big data processing technology, an automatic urban road traffic jam state monitoring technology based on high-definition video is emerging.
The automatic monitoring of the urban road traffic jam state is to rapidly judge the characteristic parameters according to the real-time traffic characteristic parameters, detect the existence of the traffic jam state and perform early warning or alarm on the monitored traffic jam state. The method is beneficial to the traffic management department to take countermeasures in time, and the severity and the influence range of traffic jam are reduced to the maximum extent.
The existing (high definition) video-based automatic monitoring method for the urban road traffic jam state generally sets a threshold value of traffic parameters (such as occupancy, average speed or section traffic volume) at first, and when real-time traffic parameters acquired by a camera exceed the threshold value for a certain time and to a certain extent, judgment and suggestion on the traffic jam level are formed, and an alarm mechanism is triggered.
Because the relationship between the main road traffic parameters is complex, the traffic characteristics (speed and lane change condition) of vehicles running on the road are also very different, and the existing congestion judgment algorithm based on the overall traffic parameters of the monitored road section has great defects. For example, a vehicle breakdown accident occurs inside a road of a (one-way) three-lane urban expressway, and a plurality of vehicles in the lane where the breakdown vehicle is located are queued. Because the speeds of the other two lanes are not greatly influenced, the road section occupancy rate does not change greatly, and the automatic identification method based on the average speed or the road section occupancy rate cannot give out early warning of traffic jam. However, traffic congestion will then develop on that road segment and there is a significant risk of causing secondary accidents. At that time, the system determines that the traffic jam is late.
For another example, when a relatively long road section along a highway in a certain city is jammed in traffic, a plurality of video monitoring systems along the highway can display real-time traffic parameters exceeding a threshold value and send out an alarm. At this point, it becomes a great challenge whether the limited police force should be assigned to which road segments. Once the judgment is wrong, the police force is continuously transferred to control the traffic jam in time. Therefore, a traffic jam judging mechanism for alarming along the line has no great practical significance.
Disclosure of Invention
The invention provides an automatic identification method for a traffic jam state and a jam point position of an urban expressway, aiming at overcoming the technical defects of the existing traffic jam monitoring method, and the method can automatically early warn, alarm and prompt the jam point position when the urban expressway is jammed (or is about to be jammed), so as to assist a traffic management department in solving the problems in the aspects of judging the traffic jam state, coping with selection schemes and the like, and reduce social and economic influences caused by traffic jam.
In order to solve the technical problem, the invention provides an automatic identification method for urban expressway traffic jam conditions and jam point positions, which comprises the following steps:
1) setting threshold values of traffic parameters of each sub lane of each monitored road section, wherein the traffic parameters comprise normal running speed, space occupancy, lane changing frequency and direction and traffic volume of vehicles in a peak period and a flat period;
2) acquiring vehicle image information in a field of view through a camera arranged beside a monitored road, converting the vehicle image information into lane-dividing real-time traffic data information, and transmitting the lane-dividing real-time traffic data information to a traffic information processing server, wherein the real-time traffic data information comprises the moving speed of a vehicle in the field of view, the space occupancy of each lane in the field of view and the lane change frequency among the lanes in the field of view, and the lane change refers to the situation that the center line of the vehicle crosses a lane line;
3) the traffic information processing server analyzes the congestion condition and the position of the traffic jam according to the real-time traffic data information and the traffic parameter threshold of the monitored road section and by associating the real-time traffic data information acquired by the cameras of the upstream road section and the downstream road section of the monitored road section with the traffic parameter threshold of the related road section;
4) and transmitting the analysis result, the real-time image and the corresponding suggestion to the user terminal according to the user setting.
Further, in the step 3), the congestion condition is judged according to the real-time traffic data information and the traffic parameter threshold, wherein the judgment comprises 'snail' behavior judgment, parking behavior judgment and lane change frequency judgment;
if the vehicle running speed in the peak period is lower than the average vehicle speed of the vehicles in the visual field of the camera or the vehicle running speed in the flat period is lower than the normal running speed threshold value, the following steps are carried out:
when Mean-vt>0.4×vDThe method comprises the following steps:
vtk≤α×Mean-vtpeak hours (1)
vtk≤β×vDFlat peak time interval (2)
Considered a "snail" behavior;
wherein v istkIs the speed of travel of the vehicle k at time t, Mean-vtIs the average speed, v, of the vehicle in the field of view of the camera at time tDα and β are coefficients for controlling the severity of the management for the design speed of the express road section, and can be set in combination with traffic engineering models or historical data of step 1);
if the average speed of the vehicle within the camera field of view:
Mean-vt≤0.4×vD(3)
the overall slow running of the traffic flow is considered;
if the space occupancy of the road right in front of the vehicle is zero and the running speed of the vehicle is continuously zero within a certain time period, namely:
vtk＝v(t+Δtk)＝0 (4)
regarding as a parking behavior;
the lane change frequency judgment comprises the following steps:
when a lane is in:
ΣCmn≥γ×Tm(5)
namely, the lane change frequency is high;
wherein, CmnThe number of times a vehicle changes lane from lane m to adjacent lane n within a time interval Δ t, Σ CmnNumber of changes from lane m to all adjacent lane behaviour, TmThe traffic volume of m lanes in the time interval reaching the upstream boundary line is a coefficient, and the traffic volume is the number of vehicles which run through the upstream boundary line of the camera view field on the m lanes in the time interval delta t.
Further, the threshold setting in step 1) includes: and collecting historical data of the traffic parameters of the lanes of each monitored road section, processing the collected historical data according to the time period of the road section, whether the time period is a working day, a season and a weather factor, setting a threshold value of the traffic parameters of each monitored road section according to the processed data and establishing a historical database.
Further, the space occupancy of each lane in the steps 1) and 2) is a percentage of the total occupied area of the vehicles running on the road section to the total area of the road section at a certain moment.
Further, the analysis of the congestion cause in step 3) includes: vehicle 'snaking', malicious jamming, cargo dropping, malfunction/illegal parking behavior, traffic accidents.
Furthermore, the monitoring road section is an urban expressway and comprises viaducts, tunnels, ground layers and various interweaving areas, wherein the interweaving areas comprise plane interweaving areas, and joints of upper and lower/in/out ramps of the viaducts or the tunnels and the main line.
Further, the step 3) of analyzing the congestion condition and the position of the traffic jam according to the 'snaking' behavior and the parking behavior of the lane comprises the following steps:
when a vehicle which is worried or parked on any lane or multiple lanes of the field of view is located in the field of view for a long time, if the vehicle closest to the front does not reach a boundary line at the downstream of the field of view, the lane is judged to have a fault/illegal parking behavior or traffic accident; if the front vehicle reaches the boundary line of the downstream of the field of view, judging that the downstream direction of the lane has a fault/illegal parking behavior or a traffic accident;
the long-time vehicle in the field of view is defined as the time that the vehicle in the field of view is greater than a set duration threshold, and the duration threshold is set according to the strict degree of management.
Further, analyzing the congestion condition and the position of the blockage point according to the lane changing frequency and the direction of the vehicle in the view field in the step 3), comprising:
when the lane changing frequency of the vehicle in the view field exceeds a set lane changing frequency threshold value, judging the lane avoided of the vehicle according to the lane changing direction of the vehicle and the lane changing frequency of each lane, judging that goods falling, failure/illegal parking behaviors or traffic accidents occur on a downstream road section of the lane avoided of the vehicle, and associating real-time traffic data information acquired by a camera of the downstream road section with a traffic information processing server to determine.
Further, analyzing the congestion condition and the position of the blockage point according to the space occupancy in the field of view in the step 3), including:
when the moving speed of the vehicle in the visual field is not less than the normal running speed, but the real-time space occupancy of the road section is lower than a set space occupancy threshold value, judging that the vehicle 'snaking', cargo falling, fault/illegal parking behavior or traffic accident occurs on the upstream road section of the visual field, and further determining the real-time traffic data information acquired by the traffic information processing server in association with the camera on the upstream road section;
if the average speed of the vehicle in the field of view of the upstream camera is lower than the normal running speed and the real-time space occupancy is higher than the space occupancy threshold value, the traffic incident occurrence point is judged to be located in a 'blind area' road section between the two groups of cameras; if the real-time space occupancy in the field of view of the upstream camera is also lower than the space occupancy threshold, the traffic event occurrence point is judged to be still located on the upstream road section of the upstream camera, and the steps are repeated to determine the specific occurrence position of the traffic event occurrence point.
Further, in step 4):
the user setting comprises setting a threshold value for the duration of the vehicle state of each lane in the visual field;
the analysis results include: and monitoring the space occupancy rate of the road sections in the visual field, the corresponding traffic jam level, the severity of the traffic incident, the lane where the traffic incident occurs and the road section where the lane is located.
The proposal comprises the following steps: real-time or historical images, notices, warnings, penalty violating vehicles, notices or warnings of vehicles traveling on an upstream road segment are manually analyzed.
Has the advantages that: compared with the prior art, the method can automatically monitor and identify the traffic jam state, particularly the sporadic traffic jam state; the method comprises the steps that traffic information state is automatically acquired based on high-definition video signals, so that the positions of road sections and lanes where traffic events such as cargo falling, malicious jamming, fault/illegal parking behaviors or traffic accidents occur can be rapidly judged at the first time; and the traffic jam state and the information of the position of the traffic jam are early-warned and alarmed and issued by using a push mode and a forwarding mode. Compared with the prior art, the method can more accurately and timely find the specific space position of the traffic accident causing the congestion, and is beneficial for a traffic management department to reasonably deal with the traffic accident in time, such as notifying, warning and punishing illegal vehicles, timely sending out police strength or other support strength, notifying or warning running vehicles on an upstream road section, and the like.
Drawings
FIG. 1 is a flow chart of an implementation of the method for automatically identifying the traffic jam state and the position of a traffic jam point on an urban expressway according to the present invention;
FIG. 2 is a schematic view of the field of view of the camera provided by the present invention;
fig. 3 is a logic judgment diagram for automatically identifying the traffic jam state and the position of a traffic jam point of an urban expressway provided by the invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings.
Fig. 1 shows a flowchart of an implementation of the method for automatically identifying a traffic congestion state and a congestion point position of an urban expressway according to the embodiment, which specifically includes the following steps:
in step S11, historical data is collected or a traffic engineering method is used to set a threshold value of each monitored road segment lane-dividing traffic parameter:
the method for acquiring the traffic parameters of the lane sections of the monitored road section comprises the following steps: average vehicle speed, space occupancy, lane change frequency and direction, and traffic volume within a certain time interval; and performing statistical processing such as classification and denoising on the data according to factors such as the time period, whether the data is in a working day, season and weather, obtaining the threshold value of the traffic parameter of each road section under each subdivision classification, and establishing a historical database. The threshold values for the traffic parameters may be set based on empirical data and theoretical derivations using existing traffic engineering methods before sufficient historical data is collected.
In step S12, collecting images/images of vehicles in the field of view by a high-definition camera disposed beside the monitored road, converting to generate traffic data information of divided lanes, and transmitting the traffic data information of divided lanes to a traffic information processing server;
in step S12, the traffic data information includes the moving speed of the vehicle traveling in the field of view, and in order to find that the traveling speed is significantly lower than the "snail" behavior of most other vehicles, the accident/fault/illegal parking behavior, and the behavior of sudden braking of the vehicle being jammed due to malicious jamming, the target that the traveling speed is significantly lower than other vehicles in the peak period or the traveling speed is significantly lower than the normal traveling speed threshold value in the flat period is searched, the vehicle "snail" speed is determined as follows:
if the vehicle is traveling at a significantly lower speed during peak periods than other vehicles in the camera's field of view or at a flat peak period than the normal travel speed threshold, then:
when Mean-vt>0.4×vDThe method comprises the following steps:
vtk≤α×Mean-vtpeak hours (1)
vtk≤β×vDFlat peak time interval (2)
Considered a "snail" behavior.
Wherein v istkIs the speed of travel of the vehicle k at time t, Mean-vtIs the average speed, v, of the vehicle in the field of view of the camera at time tDFor the designed vehicle speed of the express road segment, α and β are coefficients for controlling the severity of the management, and may be set in combination with a traffic engineering model or the historical data of step S11, in this embodiment, the default values of α and β are 0.8 and 0.7, respectively.
If the average speed of the vehicle within the camera field of view:
Mean-vt≤0.4×vD(3)
the traffic flow is considered to be slowly moving as a whole.
If the road right ahead of the vehicle is unblocked, namely the space occupancy of the road within a distance of 5 meters right ahead is zero, and the running speed of the vehicle is continuously zero within a certain time period, namely:
vtk＝v(t+Δtk)＝0 (4)
the parking behavior is considered.
The "space occupancy" in the prior art is defined as: at a certain time t, the total length of the vehicles running on the road section accounts for the percentage of the length of the road section, namely the space occupancy (%) Ot(Σ Length-car)/Length-road; in step S12, "space occupancy" in the present embodiment is newly defined as: at a certain time t, the percentage of the total occupied area of the vehicles running on the road section to the total area of the road section, namely the space occupation rate (%) Ot' (Σ Area-car)/Area-road. This is to take into account that, in a very congested road section, the number of vehicle queue may exceed the number of lanes, for example, in a one-way three-lane express way, four vehicle queue may appear, and the space occupancy mentioned in the following of this embodiment is the redefined space occupancy (%) Ot′＝(ΣArea-car)/Area-road。
In step S12, the traffic data information further includes "lane change frequency" between adjacent lanes in the field of view or frequency of lateral large movement of the traveling vehicle. When a lane is in:
ΣCmn≥γ×Tm； (5)
frequent lane change behavior is considered to exist.
Wherein: cmnThe number of times that the vehicle changes lane from lane m to adjacent lane N within the time interval delta t, m and N are natural numbers of lane numbers, and m and N are belonged to [1, 2, … … N]；ΣCmnThe number of times of changing lanes from lane m to all adjacent lane behaviors; gamma is a coefficient used for controlling the strict degree of monitoring, and the value of gamma is suggested to be 0.8; t ismThe amount of traffic reaching the upstream boundary line for m lanes in a time interval in minutes, where a lane crossing by the vehicle center line is considered to be a lane change, is defined as the number of vehicles traveling across the upstream boundary line of the camera's field of view in m lanes in the time interval Δ t.
In step S13, the traffic information processing server performs congestion status analysis according to the traffic data information, as described below with reference to fig. 3.
In step S14, the analysis results and corresponding suggestions are forwarded to the user terminal according to the user settings. The analysis results include: monitoring the space occupancy of the road section and the corresponding traffic jam level, the possible type of the occurred traffic event, the lane where the traffic event occurs and the road section where the traffic event occurs, wherein the corresponding suggestion comprises the following steps: notifying, warning and punishing the illegal vehicles, sending police force or other support force in time, and notifying or warning the running vehicles on the upstream road section.
Fig. 2 shows a schematic view of the field of view of the camera of the present embodiment.
Where l denotes the road segment covered by the field of view of the current camera, lOn the upper partUpstream links, l, representing links monitored by the current cameraLower partA downstream road segment representing a road segment monitored by the current camera; x represents an upstream boundary line of a current camera monitored section, and Y represents a lower section of the current camera monitored sectionA free boundary line.
Fig. 3 is a logic determination diagram of automatic identification of urban expressway traffic congestion states and congestion point positions according to the present embodiment, and for convenience of description, only the portions related to the present embodiment are shown in the diagram.
According to the information collected by a camera located at a road section, firstly, judging whether a low-speed or parking vehicle is located in a field of view for a long time, wherein the road section comprises a viaduct, a tunnel and a ground floor, the long-time location of the low-speed or parking vehicle in the field of view is defined as that the time of the vehicle which is judged to be low-speed, spiral or stopped in the field of view is greater than a set time threshold, the time threshold is set according to the strict degree of management, and the value range is usually 5-30 seconds:
if some lanes have such vehicles and the vehicle which is most forward in the advancing direction does not reach the downstream boundary line Y of the view field, the fault/illegal parking behavior or the traffic accident is judged to occur, and the traffic accident occurs in the lane (judgment A), and the real-time image/video can be transmitted back for manual analysis.
If some lanes have such vehicles and the vehicle which is most forward in the advancing direction reaches the boundary line Y at the downstream of the visual field, the fault/illegal parking behavior or the traffic accident is judged to occur, and the traffic accident occurs in the downstream direction of the lane (judgment B), and the nearby spherical camera can be guided to turn to the direction for carrying out the illegal behavior or accident confirmation.
If all lanes have low-speed or stop vehicles and the vehicle which is most forward in the advancing direction does not reach the downstream boundary line Y of the view field, the fault/illegal parking behavior or the traffic accident is judged to occur, and the traffic accident seriously affects all the lanes (judgment A), and the real-time image/video is immediately transmitted back for manual analysis.
And if all lanes have low-speed or stopped vehicles and the vehicle which is most ahead in the advancing direction is queued to the downstream boundary line Y of the field of view, judging that the downstream road section has a serious traffic jam state. At the moment, if frequent unidirectional transverse movement or lane change continuously occurs within a certain time range, the occurrence of cargo drop, fault/illegal parking behavior or traffic accidents is judged, and the traffic accidents occur in the downstream direction of the vehicle avoiding the lane (judgment B); if frequent unidirectional lateral movement or lane change does not occur continuously within a certain time range, it is determined that a traffic event occurs far downstream, or that the occurring traffic congestion is not caused by the traffic event but "frequent traffic congestion", that is, it is determined that C. And when B or C is judged, the information collected by the downstream camera is continuously analyzed, for example, the nearby spherical camera is guided to turn to the direction for carrying out violation behaviors or accident confirmation, so as to further determine the specific occurrence position of the traffic incident.
If the vehicle running speed in the field of view is within a reasonable range, but frequent unidirectional transverse movement or lane change continuously occurs within a certain time range, the goods falling, the fault/illegal parking behavior or the traffic accident is judged, the accident occurs in a lane avoided by the vehicle or the downstream direction of the lane, and the real-time image/video can be transmitted back for manual analysis by judging B.
Because the urban expressway has no artificial blocking such as traffic lights, the traffic flow on the urban expressway belongs to continuous traffic flow, the traffic parameters between the upstream and downstream have more direct relation with traffic behaviors, and the traffic parameters acquired by the cameras of the upstream and downstream road sections are related, so that more accurate and timely traffic event information can be acquired.
If the driving speed of the vehicle in the visual field is in a reasonable range, but the space occupancy rate in the working day peak period is obviously lower than the normal level, for example, for the road sections with the space occupancy rate fluctuating between 0.4 and 0.5 in the peak period, the space occupancy rate is continuously lower than 0.3 for 1 minute, the parameter is judged to be obviously lower than the normal level, the normal level refers to the historical database of the step S11 by the threshold value of each road section for value taking, and the vehicle 'snaking', goods falling, fault/illegal parking behaviors or traffic accidents are likely to occur at the upstream of the visual field; if the "space occupancy" is still significantly below normal levels for a period of time, then cargo drops, malfunction/parking violations or traffic accidents are likely to occur upstream of the field of view. At this time, the traffic information acquired by the upstream road section camera can be combined, if the average speed in the field of view of the upstream camera is low and the space occupancy is higher than the threshold value, the road section of the blind area between the two groups of cameras at the traffic incident occurrence point can be judged (judgment D); if the "space occupancy" in the field of view of the upstream camera is also lower than the threshold, then the traffic jam is judged to be still located on the upstream road section before the camera (judgment E), the steps can be repeated to determine the specific occurrence position of the traffic incident occurrence point and guide the nearby spherical camera to turn to the direction for carrying out violation behaviors or accident confirmation.
For the information collected by the camera whose view field is located at the interleaving area, in addition to the above-mentioned judgment criteria, special attention needs to be paid to the "space occupancy" of each lane in the interleaving area, and the interleaving area includes the connection between the main line and the upper and lower/in/out ramps of the plane interleaving area, the viaduct or the tunnel.
If the space occupancy of the inner lane of the main line is low or the vehicle speed is high, and the space occupancy of the outer lane of the main line is high or the vehicle speed is low, and the space occupancy is low or the vehicle speed is high, the values of the space occupancy and the vehicle speed are compared with the values of the historical database in the step S11, then the outer lane or the ramp of the main line is judged to have malicious jamming, fault/illegal parking behavior or traffic accidents (judgment A); if this state continues for a certain time (e.g., more than 30 seconds), it is further determined that malicious congestion, malfunction/illegal parking behavior, or traffic accident has occurred in the outside lane or ramp of the main line (decision a).
In this embodiment, the user can set and adjust the severity of the monitoring and alarm. For example, a threshold value may be set for the length of time that the vehicle is found to be in a low speed or stopped state, and the system will only respond to and analyze the camera field of view for situations where the duration of the low speed or stopped state exceeds the threshold value in order to avoid too frequent alarms and manual intervention.
Claims (8)
1. A method for automatically identifying urban expressway traffic jam conditions and positions of traffic jam points is characterized by comprising the following steps: the method comprises the following steps:
1) setting threshold values of traffic parameters of each sub lane of each monitored road section, wherein the traffic parameters comprise normal running speed, space occupancy, lane changing frequency and direction and traffic volume of vehicles in a peak period and a flat period;
2) acquiring vehicle image information in a field of view through a camera arranged beside a monitored road, converting the vehicle image information into lane-dividing real-time traffic data information, and transmitting the lane-dividing real-time traffic data information to a traffic information processing server, wherein the real-time traffic data information comprises the moving speed of a vehicle in the field of view, the space occupancy of each lane in the field of view and the lane change frequency among the lanes in the field of view, and the lane change refers to the situation that the center line of the vehicle crosses a lane line;
3) the traffic information processing server analyzes the congestion condition and the position of the traffic jam according to the real-time traffic data information and the traffic parameter threshold of the monitored road section and by associating the real-time traffic data information acquired by the cameras of the upstream road section and the downstream road section of the monitored road section with the traffic parameter threshold of the related road section;
4) according to the user setting, transmitting the analysis result, the real-time image and the corresponding suggestion to a user terminal;
judging congestion conditions according to the real-time traffic data information and the traffic parameter threshold in the step 3), wherein the judgment comprises 'snail' behavior judgment, parking behavior judgment and lane change frequency judgment;
if the vehicle running speed in the peak period is lower than the average vehicle speed of the vehicles in the visual field of the camera or the vehicle running speed in the flat period is lower than the normal running speed threshold value, the following steps are carried out:
when Mean-vt>0.4×vDThe method comprises the following steps:
vtk≤α×Mean-vtpeak hours (1)
vtk≤β×vDFlat peak time interval (2)
Considered a "snail" behavior;
wherein v istkIs the speed of travel of the vehicle k at time t, Mean-vtIs the average speed, v, of the vehicle in the field of view of the camera at time tDα and β are coefficients for controlling the severity of the management for the design speed of the express road section, and can be set in combination with traffic engineering models or historical data of step 1);
if the average speed of the vehicle within the camera field of view:
Mean-vt≤0.4×vD(3)
the overall slow running of the traffic flow is considered;
if the space occupancy of the road right in front of the vehicle is zero and the running speed of the vehicle is continuously zero within a certain time period, namely:
vtk＝v(t+Δtk)＝0 (4)
regarding as a parking behavior;
the lane change frequency judgment comprises the following steps:
when a lane is in:
∑Cmn≥γ×Tm(5)
namely, the lane change frequency is high;
wherein, CmnThe number of times the vehicle changes lane from lane m to adjacent lane n within a time interval Δ t, ∑ CmnNumber of changes from lane m to all adjacent lane behaviour, TmThe traffic volume reaching the upstream boundary line of the m lanes in the time interval is a coefficient, and the traffic volume is the number of vehicles driving across the upstream boundary line of the camera view field on the m lanes in the time interval delta t;
wherein, the step 3) of analyzing the congestion condition and the position of the traffic jam according to the 'snaking' behavior and the parking behavior of the lane comprises the following steps:
when a vehicle which is worried or parked on any lane or multiple lanes of the field of view is located in the field of view for a long time, if the vehicle closest to the front does not reach a boundary line at the downstream of the field of view, the lane is judged to have a fault/illegal parking behavior or traffic accident; if the front vehicle reaches the boundary line of the downstream of the field of view, judging that the downstream direction of the lane has a fault/illegal parking behavior or a traffic accident;
the long-time vehicle in the field of view is defined as the time that the vehicle in the field of view is greater than a set duration threshold, and the duration threshold is set according to the strict degree of management.
2. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: the threshold setting in step 1) comprises: and collecting historical data of the traffic parameters of the lanes of each monitored road section, processing the collected historical data according to the time period of the road section, whether the time period is a working day, a season and a weather factor, setting a threshold value of the traffic parameters of each monitored road section according to the processed data and establishing a historical database.
3. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: the space occupancy of each lane in the steps 1) and 2) is a certain instant, and the total occupied area of the vehicles running on the road section accounts for the percentage of the total area of the road section.
4. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: the analysis of the congestion cause in the step 3) comprises the following steps: vehicle 'snaking', malicious jamming, cargo dropping, malfunction/illegal parking behavior, traffic accidents.
5. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: the monitoring road section is an urban expressway and comprises viaducts, tunnels, ground layers and various interweaving areas, and the interweaving areas comprise plane interweaving areas, and joints of upper and lower/inlet and outlet ramps of the viaducts or the tunnels and the main line.
6. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: analyzing the congestion condition and the position of the congestion point according to the lane changing frequency and the direction of the vehicle in the view field in the step 3), comprising the following steps:
when the lane changing frequency of the vehicle in the view field exceeds a set lane changing frequency threshold value, judging the lane avoided of the vehicle according to the lane changing direction of the vehicle and the lane changing frequency of each lane, judging that goods falling, failure/illegal parking behaviors or traffic accidents occur on a downstream road section of the lane avoided of the vehicle, and associating real-time traffic data information acquired by a camera of the downstream road section with a traffic information processing server to determine.
7. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: analyzing the congestion condition and the position of the congestion point according to the space occupancy in the field of view in the step 3), comprising the following steps:
when the moving speed of the vehicle in the visual field is not less than the normal running speed, but the real-time space occupancy of the road section is lower than a set space occupancy threshold value, judging that the vehicle 'snaking', cargo falling, fault/illegal parking behavior or traffic accident occurs on the upstream road section of the visual field, and further determining the real-time traffic data information acquired by the traffic information processing server in association with the camera on the upstream road section;
if the average speed of the vehicle in the field of view of the upstream camera is lower than the normal running speed and the real-time space occupancy is higher than the space occupancy threshold value, the traffic incident occurrence point is judged to be located in a 'blind area' road section between the two groups of cameras; if the real-time space occupancy in the field of view of the upstream camera is also lower than the space occupancy threshold, the traffic event occurrence point is judged to be still located on the upstream road section of the upstream camera, and the steps are repeated to determine the specific occurrence position of the traffic event occurrence point.
8. The method for automatically identifying the traffic jam condition and the position of the jam point of the urban expressway according to claim 1, wherein: in the step 4):
the user setting comprises setting a threshold value for the duration of the vehicle state of each lane in the visual field;
the analysis results include: monitoring the space occupancy rate of the road sections in the visual field and the corresponding traffic jam level, the severity of the traffic incident, the lane where the traffic incident occurs and the road section where the lane is located;
the proposal comprises the following steps: real-time or historical images, notices, warnings, penalty violating vehicles, notices or warnings of vehicles traveling on an upstream road segment are manually analyzed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710904106.8A CN107742418B (en) | 2017-09-29 | 2017-09-29 | Automatic identification method for traffic jam state and jam point position of urban expressway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710904106.8A CN107742418B (en) | 2017-09-29 | 2017-09-29 | Automatic identification method for traffic jam state and jam point position of urban expressway |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107742418A CN107742418A (en) | 2018-02-27 |
| CN107742418B true CN107742418B (en) | 2020-04-24 |
Family
ID=61236335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710904106.8A Active CN107742418B (en) | 2017-09-29 | 2017-09-29 | Automatic identification method for traffic jam state and jam point position of urban expressway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107742418B (en) |
Families Citing this family (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400459A (en) * | 2018-04-24 | 2019-11-01 | 阿里巴巴集团控股有限公司 | For alarm rule configuration method, alarm method and the device of traffic condition |
| CN108597232A (en) * | 2018-05-03 | 2018-09-28 | 张梦雅 | Road traffic safety monitoring system and its monitoring method |
| CN108564791B (en) * | 2018-06-13 | 2021-03-19 | 新华网股份有限公司 | Traffic information processing method and device and computing equipment |
| CN109243181A (en) * | 2018-09-21 | 2019-01-18 | 深圳市轱辘汽车维修技术有限公司 | Traffic accident method for early warning, device, terminal device and storage medium |
| CN110969838B (en) * | 2018-09-30 | 2021-03-09 | 浙江宇视科技有限公司 | Traffic detection method, device and system |
| CN109318895A (en) * | 2018-10-24 | 2019-02-12 | 广州小鹏汽车科技有限公司 | Prevent the automatic Pilot method and system that malice is jumped a queue |
| EP3678108A1 (en) * | 2018-10-25 | 2020-07-08 | Beijing Didi Infinity Technology and Development Co., Ltd. | Method and system for determining whether target road facility is present at intersection |
| CN110184867A (en) * | 2019-06-10 | 2019-08-30 | 葛志凯 | Alleviate traffic congestion and reduces the roading method and system of vehicle exhaust emission |
| CN110415530A (en) * | 2019-06-10 | 2019-11-05 | 许超贤 | A kind of intelligent internet traffic control system method |
| CN110264715B (en) * | 2019-06-20 | 2021-10-15 | 大连理工大学 | Traffic incident detection method based on road section sudden congestion analysis |
| CN110834637B (en) * | 2019-07-29 | 2021-07-20 | 中国第一汽车股份有限公司 | Driving mode switching method and system, vehicle and storage medium |
| CN110491122B (en) * | 2019-07-29 | 2021-03-30 | 安徽科力信息产业有限责任公司 | Method and device for reducing urban congestion ranking |
| CN110473402B (en) * | 2019-08-20 | 2021-04-27 | 河北德冠隆电子科技有限公司 | Abnormal event detection and early warning system based on target abnormal behavior trajectory analysis |
| CN112712702B (en) * | 2019-10-24 | 2022-08-26 | 杭州海康威视系统技术有限公司 | Illegal event duplicate removal method and device, electronic equipment and machine-readable storage medium |
| CN110782680B (en) * | 2019-11-01 | 2021-03-02 | 北京星云互联科技有限公司 | Slow vehicle detection method and device and computer readable storage medium |
| CN110969853B (en) * | 2019-12-11 | 2021-10-26 | Tcl移动通信科技（宁波）有限公司 | Intelligent traffic signal lamp scheduling method and device |
| CN111028507B (en) * | 2019-12-16 | 2022-05-13 | 阿波罗智联(北京)科技有限公司 | Traffic jam cause determining method and device |
| CN111105622B (en) * | 2019-12-23 | 2021-11-02 | 北京中交兴路车联网科技有限公司 | Illegal parking correction method and device and storage medium |
| CN113283272B (en) * | 2020-02-20 | 2022-09-27 | 百度在线网络技术（北京）有限公司 | Real-time image information prompting method and device for road congestion and electronic equipment |
| CN111859291B (en) * | 2020-06-23 | 2022-02-25 | 北京百度网讯科技有限公司 | Traffic accident recognition method, device, equipment and computer storage medium |
| CN111798661A (en) * | 2020-07-13 | 2020-10-20 | 腾讯科技（深圳）有限公司 | Overtaking early warning method and device during vehicle running |
| CN111754786A (en) * | 2020-07-15 | 2020-10-09 | 遵义同望智能科技有限公司 | System for identifying traffic vehicle passing events on highway |
| CN112216119A (en) * | 2020-07-15 | 2021-01-12 | 遵义同望智能科技有限公司 | Method for identifying traffic vehicle passing event on highway |
| CN112053561B (en) * | 2020-09-11 | 2021-11-23 | 深兰人工智能芯片研究院（江苏）有限公司 | Method, system and device for judging and positioning traffic accident on non-monitored road section |
| CN112289063A (en) * | 2020-11-20 | 2021-01-29 | 烟台职业学院 | Smart city data migration and storage management system based on Internet of things |
| CN112562360A (en) * | 2020-11-30 | 2021-03-26 | 重庆电子工程职业学院 | Intelligent urban traffic guidance system and method |
| CN114582137A (en) * | 2020-11-30 | 2022-06-03 | 阿里巴巴集团控股有限公司 | Road condition determining method and device, cloud service and storage medium |
| CN112562361A (en) * | 2020-11-30 | 2021-03-26 | 重庆电子工程职业学院 | Traffic signal lamp control method and system for smart city |
| CN112581759B (en) * | 2020-12-09 | 2021-11-09 | 上海博协软件有限公司 | Cloud computing method and system based on smart traffic |
| CN112634655B (en) * | 2020-12-15 | 2022-11-22 | 阿波罗智联(北京)科技有限公司 | Lane changing processing method and device based on lane line, electronic equipment and storage medium |
| CN112885086B (en) * | 2021-01-18 | 2022-11-22 | 湖南省交通规划勘察设计院有限公司 | Sudden congestion distinguishing system based on multi-source traffic big data |
| CN112509332B (en) * | 2021-02-08 | 2021-05-07 | 腾讯科技（深圳）有限公司 | Road condition determination method, device, medium and electronic equipment |
| CN113284344B (en) * | 2021-04-04 | 2022-07-15 | 北方工业大学 | Parallel lane congestion behavior analysis method based on license plate recognition and trajectory data |
| CN113364861B (en) * | 2021-06-03 | 2022-04-05 | 重庆东登科技有限公司 | Mobile hospital system for emergency medical treatment |
| CN113643529B (en) * | 2021-07-02 | 2022-09-20 | 厦门路桥信息股份有限公司 | Parking lot lane congestion prediction method and system based on big data analysis |
| CN113643534B (en) * | 2021-07-29 | 2023-04-18 | 北京万集科技股份有限公司 | Traffic control method and equipment |
| CN113706870B (en) * | 2021-08-30 | 2022-06-10 | 广州文远知行科技有限公司 | Method for collecting main vehicle lane change data in congested scene and related equipment |
| CN113781786B (en) * | 2021-11-11 | 2022-02-22 | 中移(上海)信息通信科技有限公司 | Method, device and equipment for confirming unviable area and readable storage medium |
| CN114512010B (en) * | 2021-11-19 | 2023-04-07 | 贵州省交通规划勘察设计研究院股份有限公司 | Vehicle guiding system and device suitable for slowly blocking up under road condition |
| CN114220268A (en) * | 2021-12-16 | 2022-03-22 | 济南市公安局交通警察支队 | Method and system for carrying out optimal police dispatch based on road safety index |
| CN114999148A (en) * | 2022-05-16 | 2022-09-02 | 国汽智图(北京)科技有限公司 | Congestion degree monitoring method and device, computer equipment and storage medium |
| CN114937361A (en) * | 2022-05-19 | 2022-08-23 | 广州市粤迅特数码技术有限公司 | Urban traffic service system and operation method |
| CN115050187B (en) * | 2022-08-12 | 2022-11-01 | 杭州城市大脑有限公司 | Public opinion knowledge graph-based digital urban traffic management method |
| CN115512546A (en) * | 2022-10-08 | 2022-12-23 | 河南博汇智能科技有限公司 | Intelligent high-speed traffic flow active management method and device and electronic equipment |
| CN116311913B (en) * | 2023-02-17 | 2024-01-12 | 成都和乐信软件有限公司 | High-speed road section congestion analysis method and system based on AI video intelligent analysis |
| CN116153086B (en) * | 2023-04-21 | 2023-07-18 | 齐鲁高速公路股份有限公司 | Multi-path traffic accident and congestion detection method and system based on deep learning |
| CN116704771B (en) * | 2023-06-21 | 2024-01-12 | 中咨数据有限公司 | Real-time positioning command processing system based on traffic information of congested road section |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1991310A (en) * | 2005-12-26 | 2007-07-04 | 爱信艾达株式会社 | A travel link identification system |
| CN101194485A (en) * | 2005-05-18 | 2008-06-04 | Lg电子株式会社 | Providing traffic information relating to a prediction of congestion status and using the same |
| KR100981375B1 (en) * | 2008-09-16 | 2010-09-10 | 한국건설기술연구원 | Movable Automatic Vehicle Classification |
| CN102142197A (en) * | 2011-03-31 | 2011-08-03 | 汤一平 | Intelligent traffic signal lamp control device based on comprehensive computer vision |
| CN103646542A (en) * | 2013-12-24 | 2014-03-19 | 北京四通智能交通系统集成有限公司 | Forecasting method and device for traffic impact ranges |
| JP5567358B2 (en) * | 2010-02-02 | 2014-08-06 | 株式会社京三製作所 | Traffic signal control apparatus and traffic signal control method |
| CN105825669A (en) * | 2015-08-15 | 2016-08-03 | 李萌 | System and method for identifying urban expressway traffic bottlenecks |
-
2017
- 2017-09-29 CN CN201710904106.8A patent/CN107742418B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101194485A (en) * | 2005-05-18 | 2008-06-04 | Lg电子株式会社 | Providing traffic information relating to a prediction of congestion status and using the same |
| CN1991310A (en) * | 2005-12-26 | 2007-07-04 | 爱信艾达株式会社 | A travel link identification system |
| KR100981375B1 (en) * | 2008-09-16 | 2010-09-10 | 한국건설기술연구원 | Movable Automatic Vehicle Classification |
| JP5567358B2 (en) * | 2010-02-02 | 2014-08-06 | 株式会社京三製作所 | Traffic signal control apparatus and traffic signal control method |
| CN102142197A (en) * | 2011-03-31 | 2011-08-03 | 汤一平 | Intelligent traffic signal lamp control device based on comprehensive computer vision |
| CN103646542A (en) * | 2013-12-24 | 2014-03-19 | 北京四通智能交通系统集成有限公司 | Forecasting method and device for traffic impact ranges |
| CN105825669A (en) * | 2015-08-15 | 2016-08-03 | 李萌 | System and method for identifying urban expressway traffic bottlenecks |
Non-Patent Citations (1)
| Title |
|---|
| "利用实时路况数据聚类方法检测城市交通拥堵点";鲁小丫 等;《地球信息科学学报》;20121231;正文全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107742418A (en) | 2018-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742418B (en) | Automatic identification method for traffic jam state and jam point position of urban expressway | |
| CN106652562B (en) | Highway road traffic safety early warning method | |
| US10460600B2 (en) | Driver behavior monitoring | |
| CN105225500B (en) | A kind of traffic control aid decision-making method and device | |
| Pande et al. | Comprehensive analysis of the relationship between real-time traffic surveillance data and rear-end crashes on freeways | |
| CN109191911A (en) | A kind of tunnel road conditions early warning system, method and computer readable storage medium | |
| Montella et al. | Safety evaluation of automated section speed enforcement system | |
| Hourdos et al. | Real-time detection of crash-prone conditions at freeway high-crash locations | |
| CN104882011B (en) | A kind of vehicle is quickly received a crime report responding system and method | |
| CN107730937A (en) | The tunnel gateway dynamic vehicle speed abductive approach that a kind of street accidents risks minimize | |
| EP3403219A1 (en) | Driver behavior monitoring | |
| CN109191857B (en) | Intelligent traffic management system based on big data | |
| CN113192327B (en) | Road operation risk active prevention and control system and method considering traffic flow and individuals | |
| CN113888873B (en) | Expressway accident detection and early warning system and method based on short-time traffic flow | |
| CN111754786A (en) | System for identifying traffic vehicle passing events on highway | |
| US20220383738A1 (en) | Method for short-term traffic risk prediction of road sections using roadside observation data | |
| US20200118430A1 (en) | System, method and computer program product for radar based car accident prevention | |
| CN113112789A (en) | Method for predicting and controlling influence of urban expressway emergency | |
| Tarko et al. | Probabilistic approach to controlling dilemma occurrence at signalized intersections | |
| Lum et al. | Impacts of red light camera on violation characteristics | |
| CN102360524A (en) | Automatic detection and confirmation method of dangerous traffic flow characteristics of highway | |
| JP2008135070A (en) | Road traffic control system | |
| CN113487873A (en) | Intelligent detection system for road traffic safety | |
| Lavrenz et al. | Use of high-resolution signal controller data to identify red light running | |
| KR101045863B1 (en) | A highway ramp metering system for solving non-recurrent congestion |
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 |