CN113345242A

CN113345242A - Method, device and equipment for detecting plugged vehicle

Info

Publication number: CN113345242A
Application number: CN202010100187.8A
Authority: CN
Inventors: 姬朋立; 卢玥; 王湛; 冷继南
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-02-18
Filing date: 2020-02-18
Publication date: 2021-09-03

Abstract

The application provides a method, a device and equipment for detecting a jammed vehicle, which comprise the following steps: the method comprises the steps of obtaining a video corresponding to a road, recording information of at least one vehicle running on the road in the video, obtaining a running track of the at least one vehicle according to the video, determining a potential vehicle with congestion according to the running track of the at least one vehicle, determining that the determined potential vehicle with congestion has congestion at the current moment or the historical moment, further obtaining road condition information corresponding to the road, and determining the vehicle with congestion in the potential vehicle with congestion according to the road condition information. According to the method and the device, the potential vehicle with the jam is determined through the running track, the vehicle with the jam is determined from the potential vehicle with the jam through the road condition information, misjudgment caused by directly determining the vehicle with the jam as the vehicle with the jam in the prior art can be avoided, and therefore reliability and accuracy of determining the vehicle with the jam are improved.

Description

Method, device and equipment for detecting plugged vehicle

Technical Field

The disclosure relates to the field of intelligent traffic, in particular to a method, a device and equipment for detecting a jammed vehicle.

Background

The plugging is the behavior that when a driving motor vehicle stops and queues up or slowly runs when meeting a motor vehicle in front, the driving motor vehicle overtakes by means of the lane or occupies the opposite lane and alternately waits for the vehicle. Vehicle jamming is a common illegal action in the traffic field, and not only seriously affects the traffic operation efficiency of cities, but also is a main factor causing traffic accidents.

In the prior art, a method for detecting vehicle jamming is simple, so that the problem of false detection with high probability exists.

Disclosure of Invention

The embodiment of the disclosure provides a method, a device and equipment for detecting a jammed vehicle.

According to an aspect of an embodiment of the present disclosure, there is provided a method of jammed vehicle detection, the method including:

acquiring a video corresponding to a road, wherein the video records information of at least one vehicle running on the road;

obtaining a driving track of at least one vehicle according to the video;

determining a potential vehicle with congestion according to the running track of at least one vehicle, wherein the potential vehicle with congestion has congestion behavior at the current time or the historical time;

and acquiring road condition information corresponding to the road, and determining the vehicles with the congestion in the potential vehicles with the congestion according to the road condition information.

In the embodiment of the disclosure, the potential vehicles with congestion are determined according to the driving track, and the vehicles with congestion are determined from the potential vehicles with congestion according to the road condition information, so that the defect that vehicles with congestion are determined as the vehicles with congestion in the prior art in an error manner can be avoided, and the reliability and the accuracy of determining the vehicles with congestion are improved.

In some embodiments, determining a congested vehicle among the potential congested vehicles based on the road condition information includes:

determining an invalid jam area in the road according to the road condition information;

determining whether a jamming behavior of a potential jammed vehicle occurs in the determined invalid jamming area;

determining as the congested vehicle a vehicle whose congestion behavior in the potential congested vehicle does not occur in the invalid congestion zone.

In the embodiment of the disclosure, the invalid plugging area is determined, so that the plugged vehicles are determined according to the relation between the plugging behavior of the potential plugged vehicles and the invalid plugging area, and vehicles which are not actually judged to be plugged vehicles in the potential plugged vehicles are screened out, so that the accurate judgment of the plugged vehicles is realized.

In some embodiments, the traffic information includes one or more of the following information: a historical trajectory of a vehicle traveling on the road at a historical time period, marking information of the road, and traffic event information about the road at a current time.

In some embodiments, when the traffic information includes a historical track of vehicles traveling on the road for a historical period of time, then determining an invalid congested area in the road based on the traffic information includes:

calculating the track similarity of the historical tracks;

determining the historical track with the track similarity larger than a preset similarity threshold as the historical track corresponding to the same lane;

clustering the historical tracks corresponding to the same lane, and determining standard tracks corresponding to the lanes;

and determining the invalid jam area according to the standard tracks corresponding to the two adjacent lanes.

In some embodiments, when the traffic information includes marking information of the road, determining the invalid congested area in the road according to the traffic information includes:

calculating the distance between the marking line information of any two adjacent lanes of the road;

and if the calculated distance is smaller than a preset marking distance threshold, determining the area corresponding to the marking distance threshold smaller than the marking distance threshold as the invalid jamming area.

In some embodiments, when the traffic information includes traffic event information about the road at the current time, determining an invalid congested area in the road according to the traffic information includes:

determining the position information of the traffic incident according to the traffic incident information related to the road at the current moment;

and determining the invalid plug area according to the determined position information.

In some embodiments, determining the invalid padded area based on the determined location information comprises:

and determining the invalid plug area according to a preset range threshold and the determined position information.

In some embodiments, invalid congested area data in the road is obtained, and a congested vehicle is determined among the potential congested vehicles according to the invalid congested area data.

In some embodiments, the method further comprises:

calculating an influence value of the traffic efficiency of the traffic jam vehicle on the road according to the running track;

and when the influence value is larger than a preset influence threshold value, generating alarm information.

In the embodiment of the disclosure, the warning information is generated so that relevant workers can take corresponding measures to relieve traffic pressure based on the warning information, and therefore the technical effects of solving the problem of traffic congestion as soon as possible and ensuring traffic safety are achieved.

In some embodiments, the generating the alert information comprises:

determining lane change information of the plugged vehicle within a preset time length, wherein the lane change information comprises lane information before and after lane change and lane change frequency;

and generating the alarm information according to the lane change information.

In some embodiments, the warning information carries adjustment information for setting a lane and/or adjustment information for a transportation facility.

In some embodiments, the adjustment information of the lane setting may include: and setting a left-turning waiting area and/or a right-turning waiting area.

In some embodiments, the left turn waiting area is a one-to-two left turn waiting area;

the right-turn waiting area is a one-to-two right-turn waiting area.

In some embodiments, the adjustment information of the lane setting includes: the partially straight lane is set as a left-turn lane and/or the partially straight lane is set as a right-turn lane.

In some embodiments, the adjustment information of the lane setting includes: and arranging a waiting area of a straight lane.

In some embodiments, the adjustment information of the lane setting may include: a variable lane is provided.

In some embodiments, the adjustment information for the transportation facility includes: the corresponding lane dotted line is adjusted to a solid line or a guardrail is disposed on the lane line.

According to another aspect of the embodiments of the present disclosure, there is also provided an apparatus for detecting a jammed vehicle, the apparatus including:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a video corresponding to a road, and the video records information of at least one vehicle running on the road;

the data processing module is used for obtaining the running track of the at least one vehicle according to the video;

the vehicle congestion detection module is used for determining a potential vehicle congestion according to the running track of the at least one vehicle, and the potential vehicle congestion behavior exists at the current moment or the historical moment;

the traffic jam detection module is further used for acquiring road condition information corresponding to the road and determining a traffic jam vehicle in the potential traffic jam vehicles according to the road condition information.

In some embodiments, the congestion detection module is specifically configured to determine an invalid congestion area in the road according to the road condition information, determine whether a congestion behavior of the potential congestion vehicle occurs in the invalid congestion area, and determine that a vehicle in the potential congestion vehicle, which does not occur in the invalid congestion area, is the congestion vehicle.

In some embodiments, the congestion detection module is further configured to obtain invalid congestion area data in the road, and determine a congested vehicle among the potential congested vehicles according to the invalid congestion area data.

In some embodiments, the apparatus further comprises:

and the recommending module is used for calculating an influence value of the traffic efficiency of the traffic jam vehicle on the road according to the running track, and generating alarm information when the influence value is greater than a preset influence threshold value.

In some embodiments, the recommendation module is configured to determine lane change information of the jammed vehicle within a preset time period, where the lane change information includes lane information before and after lane change and lane change frequency, and generate the warning information according to the lane change information.

According to another aspect of the embodiments of the present disclosure, there is also provided an electronic device including a processor and a memory, wherein:

the memory having stored therein computer instructions;

the processor executes the computer instructions to perform the method of any aspect of the embodiments above.

According to another aspect of the embodiments of the present disclosure, there is also provided a computer-readable storage medium storing computer instructions, which when executed by a computer, the computer performs the method according to any of the embodiments.

According to another aspect of the embodiments of the present disclosure, there is also provided a computer program product, which when run on a processor, can implement the method according to any one of the embodiments above.

Drawings

The drawings are included to provide a further understanding of the embodiments of the disclosure, and are not intended to limit the disclosure. Wherein the content of the first and second substances,

fig. 1 is a schematic view of an application scenario of a method of jammed vehicle detection according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram of an application scenario of a method of jammed vehicle detection according to an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart diagram of a method of jammed vehicle detection in an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart diagram illustrating a method for determining a vehicle meeting a predetermined condition as a potential jammed vehicle according to an embodiment of the present disclosure;

FIG. 5 is a schematic view of a display interface according to an embodiment of the disclosure;

FIG. 6 is a flowchart illustrating a method for generating invalid plugged regions based on historical tracks according to an embodiment of the disclosure;

FIG. 7 is a schematic illustration of a historical track and a standard track of an embodiment of the present disclosure;

FIG. 8 is a schematic view of a display interface according to another embodiment of the present disclosure;

FIG. 9 is a schematic view of a display interface according to another embodiment of the present disclosure;

FIG. 10 is a schematic view of a display interface according to another embodiment of the present disclosure;

FIG. 11 is a schematic view of a display interface according to another embodiment of the present disclosure;

FIG. 12 is a schematic view of a display interface according to another embodiment of the present disclosure;

FIG. 13 is a schematic view of a display interface according to another embodiment of the present disclosure;

FIG. 14 is a block diagram of an apparatus for jammed vehicle detection of an embodiment of the present disclosure;

FIG. 15 is a block diagram of an apparatus for jammed vehicle detection in another embodiment of the present disclosure;

fig. 16 is a block diagram of an electronic device of an embodiment of the disclosure.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. They are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

In order to reduce traffic accidents and improve traffic efficiency, jammed vehicles are often detected. The vehicle with the jam is used for vehicles with the jam behavior, and the jam behavior is used for representing the behaviors of borrowing to overtake or occupying opposite lanes and alternately waiting for the vehicles when the current vehicles stop, queue or slowly run when meeting the front vehicles. The traffic congestion behavior is a common illegal behavior in the traffic field, which not only seriously affects the traffic operation efficiency of cities, but also is a main factor causing traffic accidents. According to statistics, the forced lane changing and blocking behavior of one vehicle can cause the passing delay of about 7 vehicles, the vehicle passing amount of one traffic light is reduced by 30-40%, and the whole traffic flow is recovered to an orderly and smooth state by at least two signal light periods. In addition, 50% of urban traffic accidents belong to scratch and rear-end collision accidents, and 50% of the scratch and rear-end collision accidents are caused by jamming. In addition, in the regulations of No. 1 and No. 90 in item 45 and the regulations of the use of the evidence of drivers of motor vehicles in item 45 of the road traffic safety law, when vehicles in front stop, queue or slowly run, the vehicles passing by the road, occupying opposite lanes and waiting for passing through are also subjected to punishment, namely, 100 yuan of punishment and 2 points of credit.

The method for detecting a jammed vehicle adopted in the related art includes: and judging whether each lane of the road on which the vehicles run is queued and/or congested, and if one lane is queued and/or congested, identifying the vehicles passing through the lane from another lane as congested vehicles. However, in some cases, the vehicle meeting the above determination condition is not a congested vehicle, such as a situation of lane reduction, a vehicle with an accident in a lane, lane construction, and the like. Therefore, it is desirable to provide a method that can accurately detect whether a vehicle is a jammed vehicle. Before introducing the method for detecting a jammed vehicle provided by the embodiment of the present disclosure, an application scenario of the method for detecting a jammed vehicle according to the embodiment of the present disclosure is explained in detail.

The method for detecting the vehicle with the jam can be applied to detecting whether the vehicle running on the road is the vehicle with the jam or not. The execution subject of the method for detecting the jammed vehicle may be a device for detecting the jammed vehicle (hereinafter referred to as a detection device), and the detection device may include an image collector disposed on at least one side of the road, so that the image collector collects a video corresponding to the road. Wherein, the image collector can comprise equipment with a shooting function, such as an electric police bayonet snapshot machine. Of course, the detection device may be a server having a communication function and a data processing function, and the server is connected to the image collector disposed on at least one side of the road and receives the video sent by the image collector based on the communication function.

Illustratively, as shown in fig. 1, the detection apparatus may operate in a cloud computing device system (which may include at least one cloud computing device, such as a server, etc.), may also operate in an edge computing device system (which may include at least one edge computing device, such as a server, a desktop computer, etc.), and may also operate in various terminal computing devices (such as a notebook computer, a personal desktop computer, etc.).

The detection device may also be logically a device composed of various parts, for example, the detection device may include an acquisition module, a data processing module, a jamming detection module, and the like. The various components of the apparatus for jammed vehicle detection may be deployed in different systems or servers, respectively. Each part of the detection device can be respectively operated in any two of the cloud computing equipment system, the edge computing equipment system and the terminal computing equipment. The cloud computing device system, the edge computing device system and the terminal computing device are connected through communication paths, and can communicate with each other and transmit data.

Referring to fig. 2, fig. 2 is a schematic view of an application scenario of the method for detecting a jammed vehicle according to the embodiment of the disclosure.

In the application scenario shown in fig. 2, the vehicles traveling on the road include four vehicles, which are respectively a vehicle 1, a vehicle 2, a vehicle 3, and a vehicle 4, the image acquisition device 5 disposed on one side of the road can acquire video and road condition information corresponding to the road, and send the acquired video and road junction information to the server 6 in communication connection with the image acquisition device 5, and the server 6 analyzes the received video and road condition information to determine whether there is a congested vehicle in the four vehicles. In this application scenario, the detection apparatus in this application may be the server 6 in fig. 2, or a software system running on the server 6 in fig. 2, or the image capture apparatus 5 and the server 6 in fig. 2 may be collectively referred to as the detection apparatus in this application.

The following describes the technical solutions of the present disclosure and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present disclosure will be described below with reference to the accompanying drawings.

According to one aspect of the disclosed embodiments, a method of jammed vehicle detection is provided.

Referring to fig. 3, fig. 3 is a schematic flow chart illustrating a method for detecting a jammed vehicle according to an embodiment of the disclosure.

As shown in fig. 3, the method includes:

s101: and collecting a video corresponding to the road.

The information recorded in the video includes, but is not limited to, lane information of a road and information of a vehicle traveling on the road. The lane information comprises information such as the number of lanes, lane lines and the like; the information of the vehicle includes information such as a license plate of the vehicle, a model of the vehicle, and a position of the vehicle.

For the implementation subject of the method for detecting a jammed vehicle according to the embodiment of the present disclosure, reference may be made to the above description, and details are not repeated here.

It should be noted that the above examples are only used for exemplarily illustrating the manner of obtaining the video, and are not to be construed as a specific limitation on the manner of obtaining the video according to the embodiment of the present disclosure, nor as a specific limitation on the execution subject of the embodiment of the present disclosure.

S102: and generating a driving track of the vehicle driving on the road according to the video.

The driving track refers to a sequence in which the geographical positions of the vehicle at different times are recorded.

For example, after the detection device acquires the video, the content of the video is detected, the position of the vehicle in the image recorded in the video frame corresponding to each moment of the video is obtained, the geographic position of the vehicle on the traffic road at each moment is further obtained according to the calibration relation between the image acquirer and the shot traffic road, and the sequence formed by the geographic positions of one vehicle at each moment is the driving track of the vehicle. And, the information such as speed and angle of a certain vehicle at a certain moment or a certain geographical position can be calculated according to the running track of the vehicle.

S103: and determining the vehicles meeting the preset conditions as potential vehicles.

Wherein the preset conditions include: the driving track indicates that a certain vehicle has lane changing behavior and jamming behavior; and the lane after lane change is in a congestion state.

As can be seen in fig. 4, in some embodiments, the steps may specifically include:

s31: judging whether the vehicle has lane change behavior according to the driving track, if so, executing S32; if not, S35 is executed, and the vehicle is a non-potential-jammed vehicle.

For example, if the driving trajectory of a vehicle in a first time period (hereinafter referred to as a first sub-trajectory) is in a first lane, the driving trajectory of the vehicle in a second time period (hereinafter referred to as a second sub-trajectory) is in a second lane, the driving trajectory of the vehicle in a third time period (hereinafter referred to as a third sub-trajectory) is a driving trajectory corresponding to the lane change action, that is, a part of the trajectory in the third sub-trajectory is in the first lane, a part of the trajectory is in the second lane, the first lane and the second lane are adjacent lanes, any time in the second time period is a time before any time in the third time period, and any time in the second time period is a time after any time in the first time period, the vehicle may be determined as a vehicle with lane change action, and the first lane may be determined as an initial lane, the second lane is determined as a lane after lane change (hereinafter simply referred to as a target lane).

Fig. 5 is a picture of a road recorded by video frames corresponding to several moments in a sequential time period in a video, and it can be known from fig. 5 through 2-1 to 2-4 that, if the first sub-tracks of the vehicle C are all located in lane 2, the second sub-tracks are all located in lane 1, the third sub-tracks are partially located in lane 1, and partially located in lane 2, it can be determined that the vehicle C is a vehicle with lane change behavior, lane 2 is an initial lane of the vehicle C, and lane 1 is a target lane of the vehicle C.

In some embodiments, the method of determining whether the driving trajectory within a certain time period is in the same lane (taking lane 2 as an example) may include: calculating the distance between the driving track in the time length and the standard track of the lane 2, judging the distance between the driving track in the time length and the standard track of the lane 2 and the preset first threshold value, and if the distance between the driving track in the time length and the standard sub-track of the lane 2 is smaller than the first threshold value, determining that the driving track in the time length is in the lane 2, namely the driving track in the time length is in the same lane.

The standard track of a certain lane may be determined based on the lane line of the lane, or may be calculated and determined by clustering the driving tracks of the historical vehicles, or may be determined based on demand or experience. Also, the first threshold may be set based on requirements or experience, or may be set in advance through a simulation test so as to be set based on a test result.

In some embodiments, determining whether a lane change action occurs for the travel track (exemplified by the third sub-track) for a certain length of time includes: determining a curve where the third sub-track is located, calculating an included angle between the curve and the initial lane direction (wherein the initial lane direction may be the direction of a lane line of the lane), and judging the size of the included angle between the curve and the initial lane direction and a preset second threshold value, if the included angle between the curve and the initial lane direction is greater than the second threshold value, and the starting track of the third sub-track is located in the second lane, and the ending track is located in the first lane, determining that the vehicle has lane change behavior.

As shown in fig. 5 2-2, if an angle between a curve where the third sub-trajectory of the vehicle C is located and the direction of the lane 2 (the initial lane of the vehicle C) is α, and α is greater than the second threshold, the third sub-trajectory is a corresponding driving trajectory when the lane change action occurs in the vehicle C.

Similarly, the second threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

S32: judging whether the lane where the vehicle is located after lane changing (namely, the target lane) is congested, if so, executing S33; if not, S35 is executed, and the vehicle is a non-potential-jammed vehicle.

The steps may specifically include: determining a vehicle in the target lane, wherein the distance between the vehicle and the vehicle with lane change behavior (such as the vehicle C in the example) is smaller than a preset third threshold value, determining the running track of the vehicle, wherein the distance between the vehicle and the vehicle with lane change behavior (such as the vehicle C in the example) is smaller than the preset third threshold value, calculating the determined average speed of the vehicle according to the determined running track of the vehicle, judging the size of the average speed and a preset fourth threshold value, and if the average speed is smaller than the fourth threshold value, determining that the target lane is congested.

Similarly, the third threshold and the fourth threshold may be set based on requirements or experience, or may be set in advance through a simulation test so as to be set based on a test result.

It should be noted that when the average speed is less than the first threshold, it indicates that the determined overall vehicle speed of the vehicle is relatively slow, and in the case of clear lane, the vehicle generally does not run at a slow speed, so that when the average speed is less than the first threshold, it may be determined that the target lane is in a congested state. Since the vehicle having a long distance from the vehicle C does not have a great influence on the speed of the vehicle C (or the vehicles around the vehicle C), the accuracy and reliability of the subsequent average speed calculation can be ensured by determining the vehicle for calculating the average speed through the third threshold, and the target lane congestion can be accurately determined.

S33: judging whether the vehicle has a jamming behavior, if so, executing S34; if not, S35 is executed.

S34: the vehicle is determined to be a potentially jammed vehicle.

S35: the vehicle is determined to be a non-potentially jammed vehicle.

Based on the above example, as can be seen from fig. 5, the step may specifically include: determining vehicles adjacent to the vehicle C in the front and back of the lane 1 (i.e. the target lane), as can be seen from fig. 5, referring to 2-3, if the vehicles adjacent to the vehicle C in the front and back are the vehicle a and the vehicle B, determining the distance between the vehicle a and the vehicle B according to the traveling track of the vehicle a and the traveling track of the vehicle B, and determining that the vehicle C has a congestion behavior if the distance between the distance and a preset fifth threshold is smaller than the fifth threshold.

Similarly, the fifth threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

It should be understood that, by performing the above steps S31-S35 on all or part of the vehicles detected in the video corresponding to the road, it is possible to determine the potential vehicles in the road, that is, the vehicles meeting the above preset condition are potential vehicles.

S104: acquiring road condition information corresponding to a road, and determining an invalid jam area of the road according to the road condition information.

Wherein the traffic information includes at least one of a historical track of a vehicle traveling on the lane during a historical period, marking information of the road, and traffic event information related to the road at the current time.

Wherein the definition of the invalid congestion area is determined as follows according to the historical track of the vehicle running on the lane in the historical period:

the historical track refers to a driving track corresponding to each vehicle driving on the road collected within a preset second time period, for example, the driving tracks of all vehicles driving on the road within one week are collected, and the historical track is analyzed to determine an invalid judgment area of the jammed vehicle. In the invalid congestion area, even if a certain vehicle meets the preset condition, the vehicle is not a congested vehicle but a non-congested vehicle.

It should be noted that, in the embodiment of the present disclosure, by determining the invalid congestion area based on the historical track, it may be possible to avoid the misjudgment of the congested vehicle due to factors such as road design, for example, if a certain area is changed from three lanes to two lanes, all vehicles arriving at the area from one lane of the three lanes need to change lanes to the other lane to continue driving, and therefore, although the vehicle congestion caused by the road design factor may also meet the preset condition of the congestion judgment, the area may be regarded as an invalid congestion area, that is, a potential congested vehicle appearing in the area is actually a non-congested vehicle. The invalid jam area which can be determined based on the historical track can avoid the problems of low accuracy and time delay caused by manual partition and the like, so that the effectiveness and the reliability of the detection of the jam vehicles are improved.

As can be known from fig. 6, in some embodiments, generating the invalid jam area based on the historical track specifically includes:

s41: and performing track similarity calculation on the historical tracks, and determining the historical tracks with the track similarity larger than a preset similarity threshold value as the historical tracks corresponding to the same lane.

The track similarity is used for representing the similarity degree between the historical tracks and can be used for evaluating the distance between the historical tracks, if the track similarity of a certain historical track is large, the shorter the distance between the two historical tracks is, the higher the possibility that the two historical tracks are located in the same lane is, and therefore the two historical tracks can be determined to be the historical tracks corresponding to the same lane.

The similarity threshold is a parameter for measuring whether vehicles with different historical tracks are located in the same lane. Similarly, the similarity threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

In some embodiments, a method of calculating a distance between two historical tracks may comprise: and (3) making equally spaced dividing lines in a direction perpendicular to the lane direction to generate a dividing interval, sequentially connecting the historical track with the intersection points of the dividing lines aiming at each historical track to generate a preprocessed historical track, and calculating the distance between the two preprocessed historical tracks.

The two historical tracks are respectively T1 and T2, so that the historical tracks before and after preprocessing are clearly distinguished.

The distance between the two preprocessed historical tracks can be calculated by adopting a hausdorff (hausdorff) distance, and specific algorithms can refer to the prior art and are not described herein again.

In some embodiments, if the preprocessed historical track T1 spans 4 partitions and the preprocessed historical track T2 spans 6 partitions, when calculating the distance between two preprocessed historical tracks, the distance between two preprocessed historical tracks spanning the same 4 partitions is calculated, and the sum of the 4 distances is calculated, so as to mark the calculated sum as the distance between two historical tracks.

S42: and clustering the historical tracks corresponding to the same lane, and determining the standard tracks corresponding to the lanes.

After S41, the historical tracks corresponding to the lanes may be determined, in this step, for each lane, the historical tracks corresponding to the lane are clustered, and after the clustering, a standard track may be obtained, where the standard track is used to represent the rules of the historical tracks corresponding to the lane, and the historical tracks corresponding to the standard track may be referred to as sub-tracks of the standard track.

For example, if a lane corresponds to n historical tracks, clustering is performed on the n historical tracks to obtain a standard track, and any one of the n historical tracks can be referred to as a sub-track of the standard track.

In some embodiments, a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) may be used to perform Clustering processing on historical tracks corresponding to a certain lane, and for the historical tracks in each cluster obtained through the Clustering processing, a mean value of intersection points of each partition line and the historical tracks is calculated, so as to generate a standard track. The schematic diagram of the historical track and the standard track can be referred to in fig. 7.

S43: and determining an invalid jam area according to the standard tracks corresponding to the two adjacent lanes.

The steps may specifically include: calculating the hausdorff distance of two standard tracks corresponding to two adjacent lanes in the same segmentation interval, when the hausdorff distance is smaller than a preset distance threshold, determining a point of the distance threshold where the hausdorff distance is smaller than the preset distance threshold, and generating an invalid jam area according to the two standard tracks and the point.

The distance threshold is a parameter for measuring the distance between two standard tracks of two adjacent lanes in the same segmentation interval.

Of course, in some embodiments, the invalid plugged region may also be determined manually by a worker based on historical trajectories.

This step is now explained in detail by taking fig. 8 as an example, as shown in fig. 8, a road includes three lanes, and the standard trajectories corresponding to the three lanes are T1, T2 and T3, respectively.

In some embodiments, as can be seen from fig. 8 5-1, T1 and T2 are adjacent standard traces, and T2 and T3 are adjacent standard traces. And the hausdorff distance of the T1 and the T2 in the same partition interval is greater than or equal to the distance threshold, then a1 enclosed by the T1 and the T2 can be determined as an effective jam region. And in the initial stage of T2 and T3, the hausdorff distance of T2 and T3 in the same partition is greater than or equal to the distance threshold, and from the point F, the hausdorff distance of T1 and T2 in the same partition is less than the distance threshold, then a perpendicular to the T2 is made according to the point F, and a point perpendicular to the point T2 is obtained, so as to generate an invalid jam region a 2.

In other embodiments, as can be seen from fig. 8 5-2, T1 and T2 are adjacent standard traces, and T2 and T3 are adjacent standard traces. And the hausdorff distance of the T1 and the T2 in the same partition interval is greater than or equal to the distance threshold, then a1 enclosed by the T1 and the T2 can be determined as an effective jam region. And in the initial stage of T2 and T3, the hausdorff distances of T2 and T3 in the same partition are both smaller than the distance threshold, and from the point F, the hausdorff distances of T1 and T2 in the same partition are both greater than or equal to the distance threshold, then a perpendicular to T2 is made according to the point F, and a point perpendicular to T2 is obtained, so as to generate an invalid jam region a 2.

Similarly, the distance threshold may be set based on requirements or experience, or may be set in advance through simulation tests so as to be set based on test results.

With reference to the above example, in the embodiment of the present disclosure, if two lanes are converged into one lane, a corresponding invalid congested area may be generated through the above method; if two lanes are separated from one lane, the corresponding invalid congestion areas can be generated by the method. The invalid congestion area is determined so as to accurately determine whether a potential congestion vehicle is a congestion vehicle.

The above example exemplarily describes determining invalid plugged regions based on historical tracks, and the reticle information and determining invalid plugged regions based on the reticle information are now set forth as follows:

the marking information is used to characterize information of a marking line, such as a lane line, that identifies a lane.

It is worth to be noted that the reticle information can be divided into at least two cases, one case is reticle information determined based on the collected video; in another case, the reticle information is real-time received reticle information.

The marking information is described by taking the example of including the lane line.

Generally, a lane line on a lane is completed by a worker working on the spot, and after the completion of the work, the identified lane line may be released through a network for three days or more, so that each server or other device updates the lane line. The method of the embodiment of the present disclosure may detect a plugged vehicle in real time, or may detect a plugged vehicle based on a preset time interval, for example, a plugged vehicle is detected every half day or half hour of a day, and the specific detection time may be set based on a requirement, for example, a plugged vehicle is detected every half day for half hour. Thus, in the disclosed embodiments, lane lines may be divided into the two cases described above based on their source. By adopting the first case, the latest dynamic lane line can be acquired, and the change state of the lane line can be acquired in time, so that the accurate judgment of the jammed vehicle is realized. And if the lane line is updated timely, the change state of the lane line can be acquired timely through the second condition, and higher calculation amount caused by the first condition is saved.

In some embodiments, if updated information of a lane line is not received during execution of the method of jammed vehicle detection of an embodiment of the present disclosure, it may be determined whether there is an invalid jammed area based on the lane line determined by the video.

Specifically, the distance between the lane lines of two adjacent lanes is calculated (for the calculation method of the distance, see the above example, and it is not described here again), and if the distance between the lane lines of two adjacent lanes of consecutive multiple divided sections is smaller than the preset lane line distance threshold, the section corresponding to the multiple divided sections may be determined as the invalid jam area. The region corresponding to a4 as shown at 6-1 in fig. 9, and the region corresponding to A3 as shown at 6-2 in fig. 9. Whereas A1, A2 and A3 shown in FIG. 6-1 of FIG. 9 are all effective plugging regions, A1, A2 and A4 shown in FIG. 6-2 of FIG. 9 are all effective plugging regions.

The lane line distance threshold is a parameter for measuring the distance between the lane lines of two adjacent lanes. Similarly, the lane line distance threshold may be set based on requirements or experience, or may be set based on a test result by performing a simulation test in advance.

In other embodiments, if updated information of the lane line is received during the execution of the method for detecting a jammed vehicle according to the embodiments of the present disclosure, an invalid jammed area may be determined based on the updated information of the lane line. Such as determining invalid plugged areas based on demand or experience, or based on simulation test results.

The above examples exemplarily describe reticle information and describe determining invalid congested areas based on reticle information, and the current traffic event and determining invalid congested areas based on the current traffic event are now set forth as follows:

the current traffic event information is used for representing the current traffic accident of the road or the traffic information of road maintenance and the like. For example: the current traffic incident information can be divided into two types, one type is information corresponding to a traffic accident, and the other type is information corresponding to road maintenance. Traffic accidents include, but are not limited to, vehicle collisions, breaks and parking violations; road repair may include road occupation, etc.

It should be noted that the current traffic event information can be divided into at least two cases, wherein one case is that the current traffic event information is information of a traffic accident and the like determined based on the acquired video; the other condition is that the current traffic event information is the received information such as traffic accidents.

In some embodiments, the invalid congestion area corresponding to the current traffic event information may be determined according to a preset sixth threshold, which may be specifically referred to in fig. 10. As shown in fig. 10, Ed is a sixth threshold.

Similarly, the sixth threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

In some embodiments, in the first case, if it is determined based on the video that the traveling tracks of the two vehicles do not change any more and the time duration of no change is greater than the preset time threshold, indicating that the two vehicles may have a traffic accident such as a collision, the invalid congestion area is determined according to the traveling tracks of the two vehicles and the sixth threshold.

The time threshold is a parameter for measuring the time length of the two vehicles when the traveling tracks of the two vehicles no longer change. Similarly, the time threshold is set based on requirements or experience, or a simulation test may be performed in advance so as to set based on a test result.

Of course, in other embodiments, in the first case, the invalid plugged region may also be determined by performing the clustering process and calculating the hausdorff distance. For a specific clustering process and a method for implementing the hausdorff distance, reference may be made to the above example, which is not described herein again, and for a specific result, reference may be made to fig. 11. In fig. 11, a1 is an effective plugged region, and a2 is an ineffective plugged region.

In some embodiments, if the second case is, the receiving manner includes receiving current traffic event information published by the traffic department based on the communication link, and may also include receiving current traffic event information reported by traffic participants (including traffic event parties or bystanders) based on a telephone manner, and may also include receiving current traffic event information published by social media based on the communication link, and so on.

Optionally, in other embodiments, the detection device may further obtain data of the invalid congested area of the road from other devices or apparatuses, and determine the invalid congested area of the road directly according to the data of the invalid congested area.

S105: the potential plugged-in vehicle is determined to be a plugged-in vehicle or a non-plugged-in vehicle.

In some embodiments, the step may specifically include: after determining a potential jammed vehicle based on the above example and determining an invalid jammed area based on the road condition information, it may be determined whether the travel track of the potential jammed vehicle is located in the invalid jammed area, and if so, the potential jammed vehicle may be determined as a non-jammed vehicle.

Due to the fact that the invalid jam region on the road can be determined according to the road condition information, the situation that vehicles with jam behaviors in the invalid jam region are judged as jammed vehicles is avoided, and the technical effect of reliability of detection of the jammed vehicles can be improved through the method for detecting the jammed vehicles.

In other embodiments, the step may specifically include: and determining the marking distance of the two adjacent lanes according to the marking information of the two adjacent lanes, and if the marking distance is smaller than a marking distance threshold value, determining the potential vehicle as a non-vehicle.

The marking distance threshold value is a parameter for measuring the distance between the markings of two adjacent lanes. Similarly, the reticle distance threshold may be set based on requirements or experience, or may be set in advance through a simulation test so as to be set based on a test result.

In this step, the reticle information may be understood as reticle information determined based on the video, that is, reticle information determined based on the historical track, and may also be understood as reticle information currently received. Based on the above example, it can be known that, relatively speaking, since the currently received marking information is real-time information and the historical track belongs to information corresponding to a past period of time, when the currently received marking information is information corresponding to a past period of time, the processing is relatively more suitable to be performed based on the period of time, and a corresponding invalid jam region is obtained. Therefore, the method of this step is more suitable for use when the reticle information is received.

That is, when determining that a potential congested vehicle is a congested vehicle or a non-congested vehicle according to the marking information, it may be divided into two cases, where one case is that the marking information is determined based on a historical track, it is preferable to determine an invalid congested area according to the marking information, and determine that the potential congested vehicle is a congested vehicle or a non-congested vehicle by determining whether a running track of the potential congested vehicle is the invalid congested area; in another case, if the marking information is currently received marking information, it is preferable to determine the marking distance between two adjacent lanes according to the currently received marking information, and determine the potential vehicle to be a vehicle with congestion or a vehicle without congestion according to the marking distance.

In other embodiments, the step may specifically include: the method comprises the steps of determining position information of a current traffic incident according to current traffic incident information, determining position information of lane changing of a potential traffic incident according to a running track of the potential traffic incident, judging whether the distance between the position information of the current traffic incident and the position information of the lane changing is smaller than a position threshold value or not, and determining the potential traffic incident as a non-traffic incident if the distance between the position information of the current traffic incident and the position information of the lane changing is smaller than the position threshold value.

The position threshold is a parameter for measuring the distance between the position information of the current traffic incident and the position information of the lane change. Similarly, the position threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

Similarly, in this step, the current traffic event information may be understood as the current traffic event information determined based on the video, that is, the current traffic event information determined based on the historical track, and may also be understood as the current traffic event information currently received. Based on the above example, it can be known that, relatively speaking, since the currently received traffic event information is real-time information and the historical track belongs to information corresponding to a past period of time, when the currently received traffic event information is information corresponding to a past period of time, the processing is relatively more suitable for being performed based on the period of time, and a corresponding invalid congestion area is obtained. Therefore, the method of this step is more suitable for being adopted when the traffic event information is that the current traffic event information is received.

That is, when determining that a potential congested vehicle is a congested vehicle or a non-congested vehicle according to the current traffic event information, the determination may be divided into two cases, one case is that the current traffic event information is determined based on a historical track, it is preferable to determine an invalid congested area according to the current traffic event information, and determine that the potential congested vehicle is a congested vehicle or a non-congested vehicle by determining whether a running track of the potential congested vehicle is located in the invalid congested area; if the distance between the current traffic event information and the position information of the current traffic event is less than the position threshold, the potential congested vehicle is closer to the occurrence place of the current traffic event, and the potential congested vehicle can select lane change to ensure safe driving and the like, so that the potential congested vehicle is determined to be a non-congested vehicle.

S106: and calculating the influence value of the traffic jam vehicle on the lane traffic efficiency according to the running track.

Wherein the impact value is used to characterize the degree of impact of a jammed vehicle on the lane traffic efficiency, and the lane traffic efficiency is used to characterize the efficiency of the traffic of a vehicle travelling in the lane, i.e. the lane traffic efficiency may be understood as the percentage of vehicles travelling from the lane in a unit time to the total number of vehicles travelling in the lane in a certain time period.

In some embodiments, the influence value may be expressed by a congestion delay time ratio, that is, the influence of congestion on the lane passing efficiency may be measured by the congestion delay time ratio, and the congestion delay time ratio is used to represent the ratio between delay times of normal time for vehicle passing due to vehicle congestion.

Specifically, for a certain congested time span, and for a certain congested vehicle within the time span, the following time span of x vehicles which are not affected by the congested vehicle and are in front of the congested vehicle is counted (where the following time span refers to a time difference of two vehicles passing through the counted positions). For example, in a time span, a vehicle with a jam is taken as a starting vehicle to traverse forwards, during the forward traversal, if the vehicle affected by the jam is encountered, the vehicle is skipped, only the vehicles not affected by the jam are counted, the vehicle is traversed forwards until the vehicle not affected by the jam is found, and the average following time interval is calculated; and counting the average following time distance among x vehicles affected by the jamming backwards (including the jammed vehicles) in a time span. Therefore, the extra time delay of the vehicle affected by the jamming can be calculated, and the jamming delay time ratio is calculated so as to measure the influence of the jamming on the lane passing efficiency through the jamming delay time ratio, wherein the jamming delay time ratio is used for representing the proportion of the sum of the time delays of all the jammed vehicles caused by the jamming in the total normal vehicle following time (a preset standard parameter), and the formula of the jamming delay time ratio is as follows:

Pe＝SUM_(i＝1)^m(Oft-Nft)i/SUM_(i＝1)^nNfti

where Pe is the jam delay time ratio, m is the number of vehicles affected by the jam in the time span, n is the number of total vehicles passing through the time span, Oft is the average following distance obtained by backward statistics, and Nft is the average following distance obtained by forward statistics.

This step is now described in detail in connection with FIG. 12 as follows:

as shown in fig. 12, the vehicle E is a vehicle with congestion, if the vehicle with congestion has an influence on the traffic efficiency of two subsequent vehicles, the average following time distances of the vehicles B to a and the vehicles C to B are calculated, if the average following time distance is a normal following time distance (a preset standard parameter), the following time distances of the vehicles E to C and the vehicles D to E are calculated, and the normal following time distances are subtracted respectively, so as to obtain the congestion delay time lengths of the vehicle E and the vehicle D affected by congestion, and the sum of the congestion delay time lengths is divided by the total following time distance of the vehicles a to F passing through in the congestion period, that is, the ratio of the congestion delay time in the time span of the current congestion period.

S107: and when the influence value is larger than a preset influence threshold value, generating and sending alarm information.

The steps may specifically include: and comparing the influence value with an influence threshold, and if the influence value is greater than the influence threshold, generating and sending alarm information.

Wherein the influence threshold is used as a parameter for measuring the influence of the jammed vehicle on the lane passing efficiency. Similarly, the influence threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

Based on the above example, the influence value may be represented by a congestion delay time ratio, and accordingly, the influence threshold may also be represented by a time ratio threshold, and then S107 may specifically include:

and comparing the plugging delay time ratio with a time ratio threshold, and if the plugging delay time ratio is greater than the time ratio threshold, generating and sending alarm information.

Similarly, the time ratio threshold is a parameter for measuring the influence of the jammed vehicle on the lane passing efficiency. The time ratio threshold may be set based on a demand or experience, or may be set based on a test result by performing a simulation test in advance.

It is worth mentioning that it is difficult for a lane to avoid congestion during certain time periods or certain road segments, such as commuting peak hours, holidays, etc. Therefore, in order to ensure the validity and reliability of the generated and sent warning information, so as to avoid wasting resources such as manpower and material resources for lane maintenance, in some embodiments, on the basis of this step, an average value of the congestion delay time ratio within a preset third time period may be calculated, and if the average value is greater than the congestion delay time ratio threshold, the warning information is generated and sent. The third time period may be a day unit, such as one or more days, or an hour unit, such as six hours or ten hours, etc.

In some embodiments, the warning information carries adjustment information for lane setting and/or adjustment information for transportation facilities.

It is worth to be noted that imbalance in the traffic efficiency of the lanes at the intersection (the number of times that the vehicle waits at the red light of the intersection before passing through the intersection) is a main factor for the traffic jam at the intersection. For example, when the left-turn lane is inefficient, vehicles may jam in the left-turn queuing vehicles from the straight lane. Therefore, the purpose of the adjustment information of the lane setting is to balance the traffic efficiency among the lanes and reduce the traffic jam. As shown in fig. 13 at 10-1, the vehicles in the left-turn lane have long queue length and more red light waiting times relative to the straight lane, so that if the vehicles in the straight lane change to the left-turn lane, the changed vehicles are determined as the jammed vehicles; 10-2 in FIG. 13 indicates that the red light waiting times are unbalanced between lanes (i.e., between the straight lane and the left-turn lane), so that if a left-turn lane vehicle changes to a straight lane, the changed vehicle is determined to be a jammed vehicle.

In some embodiments, if the frequency of the vehicles in the straight lane jamming the left-turn lane exceeds a preset frequency threshold (i.e. the lane change frequency is greater than the frequency threshold), the absolute value of the difference between the average traffic light waiting times of the vehicles in the left-turn lane and the straight lane is less than a preset absolute value threshold, and the intersection width (i.e. the sum of the widths of all lanes) exceeds a width threshold, the lane setting adjustment information may include: and setting a left-turning waiting area, wherein the left-turning waiting area can be specifically set as a one-to-two left-turning waiting area.

The frequency threshold value is a parameter for measuring the frequency of the vehicle in the straight lane jamming the left-turn lane. Similarly, the frequency threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

The absolute value threshold is a parameter for measuring the absolute value of the difference value of the average traffic light waiting times of the vehicles in the left-turn lane and the straight-going lane. Similarly, the absolute value threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

The width threshold is a parameter for measuring the width of the intersection. Similarly, the width threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

In other embodiments, if the frequency of the vehicle in the straight lane jamming the left-turn lane exceeds the frequency threshold and the absolute value of the average number of times of waiting for the traffic lights of the left-turn lane than the vehicle in the straight lane is greater than or equal to the absolute value threshold, the lane setting adjustment information includes: and setting a part of straight lanes as left-turn lanes.

In other embodiments, if the frequency of the vehicle jamming the straight lane in the left-turn lane exceeds the frequency threshold, the absolute value of the difference between the average waiting times of the traffic lights in the left-turn lane and the straight lane is less than the absolute value threshold, and the intersection width exceeds the second width threshold, the lane setting adjustment information includes: and arranging a waiting area of a straight lane.

In other embodiments, if the frequency of the vehicle in the left-turn lane jamming the straight-through lane exceeds the frequency threshold and the absolute value of the average traffic light of the straight-through lane is greater than or equal to the absolute value threshold than the vehicle in the left-turn lane, the lane setting adjustment information includes: and setting a part of straight lanes as left-turn lanes.

In other embodiments, if the frequency of the vehicle jamming to the straight lane and the vehicle jamming to the left-turn lane of the straight lane at different time periods at the same intersection exceeds the frequency threshold, the lane setting adjustment information may include: a variable lane is provided. For example, a lane is set as a straight-ahead lane during a time period when a vehicle turning left into the lane is congested with a frequency of the straight-ahead lane exceeding a frequency threshold; and setting the lane as a left-turn lane in a time period when the frequency of the vehicles in the straight lane being jammed in the left-turn lane exceeds a frequency threshold.

In some embodiments, if the frequency of congestion per unit time between two lanes exceeds the threshold frequency of congestion, the adjustment information of the transportation facility includes: adjusting the corresponding lane dotted line into a solid line or arranging a guardrail on the lane line to prevent the jam.

The congestion frequency threshold is a parameter for measuring the congestion frequency of the unit time length between the two lanes. Similarly, the plugging frequency threshold may be set based on requirements or experience, or may be set in advance through simulation testing so as to be set based on the testing result.

Of course, in other embodiments, if it is determined that a certain road is an accident-high road section in a certain time period according to the lane change frequency, the warning information may also carry request information requesting assistance of the police force scene.

Specifically, if a certain link is frequently determined as an invalid congested area due to traffic event information within a certain time period, that is, if the link is switched between the invalid congested area and an effective congested area multiple times within a certain time period, it is determined that the link is an accident-prone link, and request information requesting police site support may be issued to a traffic department.

According to another aspect of the disclosed embodiment, the disclosed embodiment further provides a device for detecting a jammed vehicle.

Referring to fig. 14, fig. 14 is a block diagram of a device for detecting a jammed vehicle according to an embodiment of the disclosure.

As shown in fig. 14, the apparatus includes: an acquisition module 11, a data processing module 12, and a jamming detection module 13, wherein,

the system comprises an acquisition module 11, a display module and a display module, wherein the acquisition module is used for acquiring a video corresponding to a road, and the video records information of at least one vehicle running on the road;

the data processing module 12 is used for obtaining a running track of at least one vehicle according to the video;

the vehicle congestion detection module 13 is configured to determine a potential vehicle congestion according to a driving track of at least one vehicle, where the potential vehicle congestion exists at a current time or a historical time;

the jam detection module 13 is further configured to acquire road condition information corresponding to the road, and determine a jammed vehicle among the potential jammed vehicles according to the road condition information.

In some embodiments, the congestion detection module 13 is specifically configured to determine an invalid congestion area in the road according to the road condition information, determine whether congestion behavior of the potential congested vehicle occurs in the invalid congestion area, and determine that a vehicle in the potential congested vehicle that is not the vehicle that occurs in the invalid congestion area is a congested vehicle.

In some embodiments, the traffic information includes one or more of the following: the traffic information includes a history track of a vehicle traveling on a road at a history period, marking information of the road, and traffic event information about the road at the present time.

In some embodiments, the jam detection module 13 is further configured to obtain invalid jam area data in the road, and determine a jammed vehicle among the potential jammed vehicles according to the invalid jam area data.

As can be seen in fig. 15, in some embodiments, the apparatus further comprises:

and the recommending module 14 is used for calculating an influence value of the traffic efficiency of the traffic jam vehicle on the road according to the running track, and generating alarm information when the influence value is greater than a preset influence threshold value.

That is, in the embodiment of the present disclosure, the acquisition module 11 may be configured to perform S101 in the above method embodiment; the data processing module 12 may be configured to execute S102 in the above method embodiment; the jam detection module 13 may be configured to perform S103 to S105 in the above method embodiment; the recommending module 14 may be used to execute S106 and S107 in the above method embodiments.

According to another aspect of the embodiments of the present disclosure, an electronic device and a readable storage medium are also provided.

Referring to fig. 16, fig. 16 is a block diagram of an electronic device according to an embodiment of the disclosure.

Electronic devices are intended to represent, among other things, various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 16, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 16 illustrates an example of one processor 601.

The memory 602 is a non-transitory computer readable storage medium provided by the present disclosure. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the detection method of a jammed vehicle provided by the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores computer instructions for causing a computer to perform the detection method of a jammed vehicle provided by the present disclosure.

Memory 602, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 602, that is, implements the detection method of the jammed vehicle in the above method embodiment.

The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 optionally includes memory located remotely from the processor 601, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603, and the output device 604 may be connected by a bus or other means, and fig. 16 illustrates an example of connection by a bus.

The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

Specifically, the user may input the marking information of the road and/or the traffic event information about the road at the present time to the computer through the keyboard and the pointing device, and the user may be specifically a traffic management-related worker.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Specifically, the server can acquire the marking line information of the road sent by the client and/or the traffic event information of the road at the current moment through interaction with the client.

In some embodiments, if the server receives the marking information of the road, the client interacting with the server may be a client of a traffic management related department, such as a traffic manager, which transmits the marking information of the road set or corrected by the traffic manager to the server.

In other embodiments, if the server receives the traffic event information about the road at the current time sent by the client, the client interacting with the server may be a client corresponding to any vehicle user, for example, a two-vehicle collision traffic accident occurs on a certain road, and a user driving on the road transmits the information about the two-vehicle collision traffic accident to the server through the client (which may be a mobile phone of the user).

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions of the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of jammed vehicle detection, the method comprising:

acquiring a video corresponding to a road, wherein information of at least one vehicle running on the road is recorded in the video;

obtaining a driving track of the at least one vehicle according to the video;

determining a potential vehicle with congestion according to the running track of the at least one vehicle, wherein the potential vehicle with congestion has congestion behavior at the current moment or the historical moment;

and acquiring road condition information corresponding to the road, and determining a vehicle with congestion in the potential vehicles with congestion according to the road condition information.

2. The method of claim 1, wherein the determining congested vehicles among the potential congested vehicles according to the road condition information comprises:

determining an invalid congestion area in the road according to the road condition information;

determining whether a jamming behavior of the potential jammed vehicle occurs in the invalid jamming area;

determining a vehicle in the potential congested vehicle that is not in the invalid congested zone as the congested vehicle.

3. The method according to claim 1 or 2, wherein the traffic information comprises one or more of the following information: a historical trajectory of a vehicle traveling on the road at a historical time period, marking information of the road, and traffic event information about the road at a current time.

4. The method of claim 1, further comprising: and acquiring invalid congestion area data in the road, and determining a congested vehicle in the potential congested vehicles according to the invalid congestion area data.

5. The method according to any one of claims 1 to 4, further comprising:

6. The method of claim 5, wherein the generating the alert information comprises:

and generating the alarm information according to the lane change information.

7. An apparatus for jammed vehicle detection, the apparatus comprising:

8. The apparatus according to claim 7, wherein the congestion detection module is specifically configured to determine an invalid congestion area in the road according to the road condition information, determine whether congestion behavior of the potential congested vehicle occurs in the invalid congestion area, and determine that the vehicle in the potential congested vehicle that is not the vehicle that occurs in the invalid congestion area is the congested vehicle.

9. The apparatus according to claim 7 or 8, wherein the traffic information comprises one or more of the following information: a historical trajectory of a vehicle traveling on the road at a historical time period, marking information of the road, and traffic event information about the road at a current time.

10. The apparatus of claim 7, wherein the congestion detection module is further configured to obtain invalid congestion area data in the road, and determine a congested vehicle among the potential congested vehicles according to the invalid congestion area data.

11. The apparatus of any one of claims 7 to 10, further comprising:

12. The device according to claim 11, wherein the recommending module is configured to determine lane change information of the congested vehicle within a preset time period, where the lane change information includes lane information before and after lane change and lane change frequency, and generate the warning information according to the lane change information.

13. An electronic device, comprising a processor and a memory, wherein:

the memory having stored therein computer instructions;

the processor executes the computer instructions to perform the method of any of claims 1-6.

14. A computer-readable storage medium having stored thereon computer instructions which, when executed by a computer, cause the computer to perform the method of any one of claims 1-6.