CN114999171A - Lane change monitoring processing method, device and system - Google Patents
Lane change monitoring processing method, device and system Download PDFInfo
- Publication number
- CN114999171A CN114999171A CN202210546012.9A CN202210546012A CN114999171A CN 114999171 A CN114999171 A CN 114999171A CN 202210546012 A CN202210546012 A CN 202210546012A CN 114999171 A CN114999171 A CN 114999171A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- preset
- lane
- predetermined
- lanes
- 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.)
- Pending
Links
- 230000008859 change Effects 0.000 title claims abstract description 93
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims description 13
- 238000012369 In process control Methods 0.000 description 52
- 210000004544 dc2 Anatomy 0.000 description 52
- 238000004190 ion pair chromatography Methods 0.000 description 52
- 230000006399 behavior Effects 0.000 description 21
- 238000003860 storage Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Abstract
The application discloses a lane change monitoring processing method, a device and a system, wherein the method comprises the following steps: acquiring running data of a preset vehicle in a preset section of a road, wherein the running data comprises: a lane in which the vehicle is scheduled to travel; the driving data is obtained by respectively shooting the driving of a preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in a preset section and are mutually separated by preset distances in the extending direction of the road; judging whether lanes where the scheduled vehicle runs and shot by each camera in the multiple cameras are the same lane or not; and if the lane change is not carried out, the lane change is determined to be carried out when the predetermined vehicle runs in the predetermined interval, otherwise, the lane change is carried out when the predetermined vehicle runs in the predetermined interval. Through the method and the device, the problem that the monitoring range is limited or the influence of GPS signals is large in vehicle lane change monitoring in the prior art is solved, the GPS signals of the vehicle are not depended on, and the vehicles can be monitored more accurately by continuously shooting the vehicles through a plurality of cameras.
Description
Technical Field
The application relates to the field of intelligent transportation, in particular to a lane change monitoring processing method, device and system.
Background
The lane change behavior of the motor vehicle can occur in the driving process, and the lane change behavior is illegal under the condition that the road marking line is a solid line, so that some means are needed to monitor the lane change behavior of the vehicle. The following two monitoring methods are used in the prior art:
chinese patent application No. 201910435955.2 discloses a method for lane change detection and illegal lane change identification. The method uses a video acquisition device, and identifies, positions and judges the illegal lane change of the driving according to the real-time video image acquired by the acquisition device. But only can be subjected to the limited shooting range of a single video acquisition device, and the single-point monitoring can be carried out in the visual image range of the video acquisition device.
Chinese patent application No. 201910496508.8 discloses a vehicle supervision method, apparatus and computer-readable storage medium. In the patent application document, the high-precision coordinate position of the monitored vehicle is obtained by loading the electronic map of the lane information, and then the purpose of monitoring illegal lane change in real time can be realized by the change of the coordinate position of the monitored vehicle. However, the technology requires that the vehicle must be loaded with an electronic map and transmitted to a monitoring medium in real time to realize monitoring; moreover, the technology is greatly influenced by GPS signals and cannot be used in special scenes such as tunnels.
In view of the above-mentioned problem that the monitoring range is limited or the monitoring range is greatly influenced by the GPS signal in the vehicle lane change monitoring, no corresponding solution is provided in the prior art.
Disclosure of Invention
The embodiment of the application provides a lane change monitoring processing method, a lane change monitoring processing device and a lane change monitoring processing system, which are used for at least solving the problem that in the prior art, the monitoring range is limited or the influence of GPS signals is large in the lane change monitoring of a vehicle.
According to an aspect of the present application, there is provided a lane change monitoring processing method, including: acquiring running data of a predetermined vehicle in a predetermined section of a road, wherein the running data comprises: a lane in which the predetermined vehicle is traveling; the driving data are obtained by respectively shooting the driving of the preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in the preset section and are mutually separated by preset distances in the extending direction of the road; judging whether lanes where the scheduled vehicle runs and shot by each camera in the multiple cameras are the same lane or not; and if the lane change is not carried out, the preset vehicle is determined to run in the preset interval, and otherwise, the lane change behavior is carried out when the preset vehicle runs in the preset interval.
Further, the acquiring of the traveling data of the predetermined vehicle within the predetermined section includes: acquiring license plate information of the preset vehicle, which is obtained by shooting by a last camera before the preset vehicle leaves the preset interval; and acquiring the license plate information shot by each camera and the lane on which the preset vehicle runs corresponding to the license plate information according to the license plate information.
Further, when the time that the predetermined vehicle enters the predetermined interval exceeds a predetermined time and the license plate information captured by the last camera before the predetermined vehicle leaves the predetermined interval is not yet acquired, determining whether lanes where the predetermined vehicle runs and captured by each of the plurality of cameras are all the same lane includes: the camera is used for acquiring license plate information of the preset vehicle shot in the preset interval; and judging whether the lanes where the vehicles run are the same lane or not according to the lanes where the vehicles run and obtained by shooting the license plate information of the preset vehicles through the camera.
Further, the license plate information shot by each camera and the lane where the predetermined vehicle runs corresponding to the license plate information are stored in a Key-Value pair manner, where the license plate information is a Key, and the lane where the predetermined vehicle runs is a Value.
Further, determining whether the lanes where the predetermined vehicle runs, captured by each of the plurality of cameras, are all the same lane includes: acquiring all key-value pairs corresponding to the license plate information of the preset vehicle; and judging whether the lanes where the preset vehicle runs are the same according to whether all the values Value stored in the key-Value pair are consistent, wherein if all the values Value are consistent, the lanes where the preset vehicle runs are the same, and otherwise, the lanes are different.
Further, all the key-value pairs are stored in a first cache, the key-value pairs corresponding to the license plate of the predetermined vehicle are deleted from the first cache when the lanes where the predetermined vehicle runs are determined to be the same lane, and the key-value pairs corresponding to the license plate of the predetermined vehicle are moved from the first cache to a second cache when the lanes where the predetermined vehicle runs are different lanes, wherein the second cache is used for storing the key-value pairs corresponding to the vehicle with lane change behavior.
Further, still include: and traversing the first cache, and if the existence of the key-value pair in the first cache exceeds the preset time length, deleting the key-value pair from the first cache.
Further, after determining that the lane change behavior occurs when the predetermined vehicle travels within the predetermined interval, the method further comprises: acquiring a first image shot by a first camera and a second image shot by a second camera, wherein the first camera and the second camera are two adjacent cameras in the multiple cameras, and the lane where the predetermined vehicle is located in the first image is different from the lane where the predetermined vehicle is located in the second image; and splicing the first image and the second image and then storing.
According to another aspect of the present application, there is also provided a lane change monitoring processing apparatus, including: the acquisition module is used for acquiring running data of a preset vehicle in a preset section of a road, wherein the running data comprises: a lane in which the predetermined vehicle is traveling; the driving data are obtained by respectively shooting the driving of the preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in the preset section and are mutually separated by preset distances in the extending direction of the road; the judging module is used for judging whether the lanes where the preset vehicle runs, which are shot by each camera in the plurality of cameras, are the same lane or not; and the determining module is used for determining that the lane change is not carried out when the preset vehicle runs in the preset interval if the lane change is carried out in the preset interval, and otherwise, the lane change is carried out when the preset vehicle runs in the preset interval.
According to another aspect of the present application, there is also provided a lane change monitoring processing system, including: the system comprises a plurality of cameras, a control unit and a display unit, wherein the cameras are used for respectively shooting the running of a preset vehicle in a preset section of a road, and are arranged in the preset section and are mutually separated by preset distances in the extending direction of the road; software for use in the above method.
Further, still include: and the server is connected with the plurality of cameras and is used for operating the software.
In the embodiment of the application, the method for acquiring the running data of the predetermined vehicle in the predetermined section of the road is adopted, wherein the running data comprises the following steps: a lane in which the predetermined vehicle is traveling; the driving data are obtained by respectively shooting the driving of the preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in the preset section and are mutually separated by preset distances in the road extension direction; judging whether lanes where the scheduled vehicle runs and shot by each camera in the multiple cameras are the same lane or not; and if the lane change is not carried out, the preset vehicle is determined to run in the preset interval, and otherwise, the lane change behavior is carried out when the preset vehicle runs in the preset interval. Through the method and the device, the problem that the monitoring range is limited or the influence of GPS signals is large in vehicle lane change monitoring in the prior art is solved, the embodiment of the method and the device do not depend on the GPS signals of the vehicle, and the vehicle lane change can be monitored more accurately by continuously shooting the vehicle through a plurality of cameras.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a flowchart of a lane change monitoring processing method according to an embodiment of the present application.
Fig. 2 is a three-channel scene erection diagram according to an embodiment of the application.
FIG. 3 is a schematic flow chart provided by the multi-channel IPC illegal lane change monitoring method according to the embodiment of the application.
Fig. 4A is a first schematic view of a passing characteristic data structure according to an embodiment of the present application.
Fig. 4B is a schematic diagram of a passing characteristic data structure according to an embodiment of the present application.
Fig. 5 is a flow chart of vehicle passing data processing according to an embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an aspect of the present application, there is provided a lane change monitoring processing method, including:
step S102, acquiring the running data of a preset vehicle in a preset section of a road, wherein the running data comprises: a lane in which the vehicle is scheduled to travel; the driving data is obtained by respectively shooting the driving of a preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in a preset section and are mutually separated by preset distances in the extending direction of a road;
step S104, judging whether lanes where the scheduled vehicle runs and which are shot by each camera in the plurality of cameras are the same lane or not;
and step S106, if the lane change is the same, determining that the preset vehicle does not change the lane when running in the preset section, otherwise, determining that the lane change action occurs when the preset vehicle runs in the preset section.
Through the steps, a plurality of cameras with preset distances are arranged along a preset section (for example, a road section with a solid line) needing lane change monitoring, and whether lane change occurs is judged according to whether a preset vehicle shot by each camera runs on the same lane.
The Camera referred to in this embodiment may be referred to as IPC, which is short for IP Camera, that is, a webcam (or referred to as a webcam), and is capable of implementing at least one of the following functions: and performing video and audio coding, network transmission, mobile video analysis alarm and the like. According to different functions of IPC, the system is divided into a bayonet IPC and an electric police IPC. The card port IPC can achieve information acquisition of all passing vehicles, and the electric police IPC can acquire driving information generally when a driving triggers a specific violation. Cameras with various functions can be used in the present embodiment, and the following embodiments will describe the bayonet IPC as an example.
In the present embodiment, cameras are disposed at predetermined distances, and for convenience of description, cameras disposed at predetermined distances are referred to as IPCs disposed in different channels. In this embodiment, a plurality of cameras are used, and therefore, it is also called multi-channel IPC.
The single-card-port IPC, the electric police IPC or IPCs with other functions are single-channel IPCs, and single-channel video stream analysis and transmission of snapshot images and data can be achieved. IPCs of different channels can realize linkage snapshot through network information interaction, and the purpose of cooperative operation is achieved.
Fig. 2 is a schematic diagram of a three-channel scenario assumption according to an embodiment of the present application, as shown in fig. 2, in a section of illegal lane change monitoring road segment, including: solid lines or double solid lines are arranged among the 1 st lane 201, the 2 nd lane 202 and the 3 rd lane 203, and the lanes are invariable lanes; the 1 st monitoring 204 position is a monitoring point in the 1 st channel checkpoint IPC205 field of view; the 2 nd monitoring location 206 is a monitoring point within the IPC field of view of the 2 nd channel gate 207; the 3 rd monitoring location 208 is a monitoring point within the 3 rd channel mount 209IPC field of view. Wherein, three bayonets IPC are provided, which include: the 1 st channel card port IPC205, the 2 nd channel card port IPC207 and the 3 rd channel card port IPC209 are connected with the intelligent terminal server 211 in a network mode. In addition, optionally, in order to supplement light, a flash lamp may be provided, and several flash lamp holders 210, for example, are provided near the 1 st channel bayonets IPC205, the 2 nd channel bayonets IPC207, and the 3 rd channel bayonets IPC209 to provide auxiliary lighting.
The following alternative embodiments may be employed in fig. 2 to determine the spacing between the cameras: acquiring a shooting visual field of a camera, wherein the shooting visual field is used for indicating the maximum distance which can be shot by the camera; the method comprises the steps of arranging a plurality of cameras according to shooting videos of the cameras, wherein the distance between two adjacent cameras in the plurality of cameras is smaller than the sum of the maximum distances which can be shot by the two adjacent cameras. By means of the camera arrangement mode, shooting dead angles of a plurality of cameras arranged in the preset interval can be avoided, and therefore lane changing behavior can be judged better.
Fig. 2 relates to an intelligent terminal server 211, which may also be referred to as a server for short, and on which software is executed, which is used to execute the method steps in the present embodiment. The intelligent terminal server is used as hardware, can be accessed to IPCs of various types and multiple channels in a mixed mode, and can also establish a star topology structure under the condition that the IPCs of multiple channels are accessed. Optionally, the server can provide edge computing capabilities such as network, audio/video codec, image processing, analysis and calculation, storage, upload control, and the like.
In an optional embodiment, by means of the image processing function of the server, splicing lane change vehicle images can be further performed, that is, after it is determined that lane change occurs when the predetermined vehicle travels in the predetermined section, a first image captured by a first camera and a second image captured by a second camera can be acquired, wherein the first camera and the second camera are two adjacent cameras in the plurality of cameras, and a lane in which the predetermined vehicle is located in the first image is different from a lane in which the predetermined vehicle is located in the second image; and splicing the first image and the second image and then storing. Evidence of a lane change violation can be preserved by this process.
In fig. 2, the data of the driving lane of the corresponding vehicle may be obtained when the predetermined vehicle leaves the monitored predetermined section, and at this time, the license plate information of the predetermined vehicle, which is obtained by the last camera (IPC 209 in fig. 2) before the predetermined vehicle leaves the monitored predetermined section, is obtained; and acquiring the license plate information shot by each camera and a lane for the preset vehicle to run corresponding to the license plate information according to the license plate information. Then, it is known whether the predetermined vehicle has made a lane change within the monitored area or not based on the data. The optional processing mode can obtain the data of all driving lanes of the vehicle in the preset section when the vehicle leaves, so that whether the lane changing behavior of the vehicle occurs can be judged more comprehensively.
In one case, there is a possibility that the last camera does not acquire the license plate information of the predetermined vehicle, in order to solve the problem, a time period for the predetermined vehicle to enter the predetermined interval may be counted, and in a case that the time period for the predetermined vehicle to enter the predetermined interval exceeds the predetermined time period and the license plate information acquired by the last camera before the predetermined vehicle leaves the predetermined interval is not acquired, the determining may be performed according to lanes acquired by the cameras which have acquired the predetermined vehicle, that is, determining whether lanes where the predetermined vehicle runs and acquired by each of the plurality of cameras includes: the camera is used for acquiring license plate information of a preset vehicle shot in the preset interval; and judging whether the lanes where the vehicles run are the same lane or not according to the lanes where the vehicles run and obtained by shooting the license plate information of the preset vehicles through the camera. The optional implementation mode can solve the problem of missed judgment possibly occurring under the condition that the last camera does not shoot the license plate information.
In the embodiment, in order to improve the calculation efficiency, a Key-Value pair mode is adopted for storage, namely the license plate information shot by each camera and a lane, corresponding to the license plate information, of a scheduled vehicle to run are stored in a Key-Value pair mode, wherein the license plate information is a Key, and the lane, corresponding to the scheduled vehicle to run, of the scheduled vehicle is a Value.
In this case, it is determined whether the lanes where the predetermined vehicle runs, which are shot by each of the plurality of cameras, are all the same lane, and it is only necessary to acquire all key-value pairs corresponding to the license plate information of the predetermined vehicle; then, whether the lanes where the predetermined vehicle runs are all the same lanes is judged according to whether all the values stored in the key-Value pairs are consistent, wherein if all the values are consistent, the lanes where the predetermined vehicle runs are all the same lanes, otherwise, the lanes are different lanes. This processing method is for improving the computational efficiency.
As the number of vehicles passing through the predetermined area increases, two-part cache may be used to store the key-value pairs, wherein all the key-value pairs may be stored in a first cache, and when it is determined that lanes where the predetermined vehicles travel are all the same, the key-value pair corresponding to the license plate of the predetermined vehicle is deleted from the first cache, and when the lanes where the predetermined vehicles travel are different, the key-value pair corresponding to the license plate of the predetermined vehicle is moved from the first cache to a second cache, wherein the second cache is used to store the key-value pair corresponding to the vehicle with lane change behavior.
In this processing mode, when lanes corresponding to license plate information are all the same lane, it is indicated that no lane change behavior occurs, and at this time, the key-value pair corresponding to the license plate information can be deleted, which is beneficial to clearing cache. In order to solve the problem, in an optional implementation, the first cache may be traversed according to a predetermined period, and if the key-value pair in the first cache exceeds a preconfigured duration, the key-value pair is deleted from the first cache.
An alternative embodiment of the present application is described below in conjunction with fig. 2 and 3. Fig. 3 is a flowchart of illegal lane change detection according to an embodiment of the present application, and as shown in fig. 3, this alternative embodiment includes the following steps:
step S301: the gates IPC of each lane are numbered in the order from front to back in the traveling direction, and the numbers are stored in advance in the smart terminal server 211 and associated with each other. Each time the checkpoint IPC uploads vehicle data (i.e., data captured when a vehicle passes through the checkpoint IPC, which is also referred to as travel data or vehicle passing characteristic data), the checkpoint IPC uploads the number through a "checkpoint IPC channel number" field.
Step S302: the intelligent terminal server 211 polls the vehicle passing data obtained by capturing and identifying the motor vehicle from all the channel bayonets IPC such as the 1 st channel bayonets IPC205, the 2 nd channel bayonets IPC207, the 3 rd channel bayonets IPC209 and the like. When the vehicle passes through each channel card gate IPC, the vehicle passing data of the vehicle is generated. The vehicle passing data in this step may include, but is not limited to: the car passing picture, the license plate number, the card port IPC channel number, the lane number, the snapshot time, the snapshot place and the like.
In this step, when the motor vehicle passes through the 1 st monitoring location 204, the 1 st channel checkpoint IPC205 actively takes a snapshot and identifies the motor vehicle, integrates vehicle information, road information and camera channel information into vehicle data, and uploads the vehicle data to the intelligent terminal server 211 in a network manner. When the motor vehicle passes through the 2 nd and 3 rd monitoring locations 206 and 208, the 2 nd and 3 rd channel gates IPC207 and IPC209 also snap the motor vehicle in the same manner, and process data is formed and uploaded.
Because the driving directions of all lanes of the monitored road section are unidirectional, when the intelligent terminal server 211 receives the vehicle passing data sent by the 1 st channel gate IPC205, the intelligent terminal server represents that the vehicle enters the illegal lane change monitoring section, and when the intelligent terminal server 211 receives the vehicle passing data sent by the 3 rd channel gate IPC209, the intelligent terminal server represents that the vehicle leaves the illegal lane change monitoring section.
Step S303: when the intelligent terminal server 211 receives a piece of vehicle passing data, the intelligent terminal server 211 stores the vehicle passing data and updates the database, and meanwhile, the intelligent terminal server 211 copies some fields from the vehicle passing data to assemble a piece of Key-Value type vehicle passing characteristic data taking the license plate number as a Key.
As shown in fig. 4A, Key is "license plate number 401", and a set of values of Value is composed of "bayonet IPC channel number 402", "lane number 403", and "snapshot time 404". As shown in fig. 4B, Value is an array or vector type, so that keys and values are in a one-to-many correspondence relationship, and a function of storing multiple pieces of passing feature data for the same license plate number can be realized.
In the following examples, Key 1 The license plate number 401 is "zhe a ×); value1 1 The gate IPC channel number 402 is 1, the lane number 403 is 2, and the capturing time 404 is 1623748592; value1 2 The gate IPC channel number 402 is 2, the lane number 403 is 3, and the capturing time 404 is 1623748612; value1 3 The gate IPC channel number 402 of (1) is 3, the lane number 403 is 2, and the snapshot time 404 is 1623748624.
Step S304: and storing the passing characteristic data into a Key-Value type cache.
Step S305: and traversing the vehicle passing characteristic data of each motor vehicle in the cache by the independent thread, judging whether the vehicles illegally change lanes one by one, searching two pieces of vehicle passing data with different lane numbers of the adjacent lane gates IPC of the license plate number from the magnetic disk when the vehicles illegally change lanes, and matching and synthesizing evidence pictures.
The independent thread performs traversal on data in the key-value type cache and a method for judging illegal lane change, as shown in fig. 5. The independent thread firstly traverses the cache, when the Value corresponding to a certain license plate number has the vehicle passing characteristic data of the last card entrance IPC channel, the vehicle is considered to be driven out of the illegal lane change detection interval, the license plate number is used as 'Key' in the cache, and all the vehicle passing characteristic data of the license plate number are taken out; and comparing every two adjacent lane numbers of the adjacent lane gates with each other to determine whether the lane numbers of the adjacent lane gates are different, if so, determining that the motor vehicle with the license plate number has illegal lane changing behaviors, and otherwise, determining that the motor vehicle passes through normally. If the motor vehicle with the license plate number has illegal lane change behaviors, all the passing characteristic data of the motor vehicle with the license plate number are transferred into an illegal sub cache.
And the law violation son searches two pieces of vehicle passing characteristic data with different lane numbers of adjacent channel gates IPC, respectively assembles the two pieces of vehicle passing characteristic data into a database query statement, and searches corresponding vehicle passing data from the magnetic disk. And then, matching the two vehicle passing data, and carrying out picture synthesis on the vehicle passing pictures to obtain an evidence picture. And then, storing the synthesized picture in a hard disk, and updating the database. And finally, emptying the violation sub-cache.
For one particular case that may exist: if the last checkpoint IPC channel is missed, the last checkpoint IPC channel passing characteristic data can never be waited, and other passing characteristic data of the license plate number are always stored in the cache. Thus, when traversing the cache, if: and if the current time-snapshot time > passes through the illegal lane change monitoring interval for the longest time, deleting all vehicle passing characteristic data of the license plate number. The illegal lane change monitoring interval can be set according to deployment conditions as required for the longest time.
For such a situation, in another optional implementation manner, if missed shooting occurs in the last camera, the passing data corresponding to the license plate number shot by other cameras in the predetermined interval may be acquired, and then whether lane change behavior occurs in the predetermined interval in the vehicle corresponding to the license plate number is determined according to the passing data shot by other cameras. Since all the vehicle passing data corresponding to the license plate number are deleted when the current time-snapshot time > passes through the illegal lane change monitoring interval (i.e., the predetermined interval) for the longest time, in this embodiment, the vehicle passing data obtained by shooting with other cameras should be used for judgment before all the vehicle passing data are deleted, and at this time, a first time length may be preconfigured, where the first time length is less than the longest time passing through the illegal lane change monitoring interval. And under the condition that the current time-snapshot time (such as the time of the process data corresponding to the license plate number arranged for the last time) is longer than the first time length and the current time-snapshot time is shorter than the longest illegal lane change detection interval, judging whether the lane change behavior of the vehicle corresponding to the license plate number occurs by using the vehicle passing data obtained by shooting through other cameras.
For another special case that may exist: if any one of the IPC channels of the checkpoint captures the motor vehicle with the same license plate number for multiple times in a short time, the IPC channel of the same checkpoint has multiple passing characteristic data. Considering that the front-back distance of the detection position in the field range of the IPC of the checkpoint is small and the possibility of lane change is small, the passing characteristic data with the largest snapshot time of the IPC channel of the checkpoint is taken. In this case, it can be understood that a plurality of pieces of passing data are obtained by shooting with the same camera, the plurality of pieces of process data include snapshot time, and the snapshot time is a value accumulated according to a time unit (which may be accumulated according to seconds, milliseconds, and the like), for example, the accumulation is started from a zero point 0:00 time point of the day, and if the snapshot time is 60000, it means that the snapshot time is 60000 milliseconds away from the zero point, that is, 1 minute away from the zero point, and the snapshot time is zero point zero 1 minute. Therefore, under the condition that the same camera shoots and obtains a plurality of vehicle passing data of the same vehicle, the vehicle passing data with longer snapshot time is the latest vehicle passing data, the vehicle passing data with the largest snapshot time is selected, the vehicle passing data with the latest snapshot time is selected, and the judgment can be more accurate by using the latest vehicle passing data. As another optional embodiment, when one camera captures a plurality of driving data of the same predetermined vehicle, whether the lane where the predetermined vehicle is driving is the same lane may be determined according to the lane where the predetermined vehicle is driving captured by the same camera, and then whether the lane where the predetermined vehicle is driving is the same lane may be determined according to the lanes where the plurality of cameras capture driving, so that the behavior of the vehicle changing lanes continuously in the same camera monitoring range may be solved.
If the steps S304 and S305 are completed in two software threads, software locking needs to be performed on the cache, and a mutual exclusion operation needs to be performed.
S306: and finally, uploading the matching data and the evidence picture to the platform.
According to the optional embodiment, the bayonets IPCs of the channels and the corresponding light supplementing devices are sequentially arranged on a section of illegal lane change road section to be monitored from front to back, the bayonets IPCs of the channels are numbered in sequence, and the numbers are stored in advance on the intelligent terminal server and are associated; the intelligent terminal server polls to obtain real-time vehicle passing data from all the channel gates IPC; when the intelligent terminal server receives a piece of vehicle passing data, the vehicle passing data is stored, and certain fields are copied from the vehicle passing data to be assembled into a piece of Key-Value type vehicle passing characteristic data taking a 'license plate number' as a 'Key'; storing the passing characteristic data into a cache of key value pair types; traversing data in Key-Value type cache and judging illegal lane change by an independent thread, when the illegal lane change is determined, taking vehicle passing data with different IPC lane numbers of adjacent lane gates of the license plate number from a hard disk of the intelligent terminal server, matching the vehicle passing data and synthesizing an evidence picture; and finally uploading the evidence picture to the platform. The optional embodiment breaks through the traditional 'single-point' illegal lane change monitoring scheme, and can effectively solve the problems of continuous illegal lane change monitoring needing long intervals and large data volume in scenes such as tunnels, high speed and the like and the matching problem of multichannel IPC illegal data. Meanwhile, credible matching fusion of data of the multi-channel IPC is completed in the subnet by utilizing the edge computing capability of the intelligent terminal server (the credible matching fusion is to match vehicle passing characteristic data to obtain whether the vehicle has lane change or not and judge whether lane change behaviors are illegal or not), the platform computing power can be greatly released, and the running load of the central server is reduced.
In one embodiment, the IPC may determine the process data by sending the process data to a central server through a network (e.g., a wireless communication network such as a mobile communication network), the central server and the IPC are not in the same subnet, and data transmission between the central server and the IPC may be performed only by routing through a router. Therefore, in the above embodiment, an intelligent terminal server may be used, and the intelligent terminal server is an edge server, and the edge server and the IPC are arranged in the same subnet, so that the data transmission speed of the edge server and the IPC is relatively fast, the data delay is low, and the lane change behavior determination by the edge server can also reduce the calculation pressure of the central server. The edge server can be connected with the central server through a network, so that the judgment result of the lane changing behavior and/or the vehicle passing data can be sent to the central server, and the central server can store the data or perform statistical integration of the data.
In this embodiment, an electronic device is provided, comprising a memory in which a computer program is stored and a processor configured to run the computer program to perform the method in the above embodiments.
The programs described above may be run on a processor or may also be stored in memory (or referred to as computer-readable media), which includes both non-transitory and non-transitory, removable and non-removable media, that implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
These computer programs may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks, and corresponding steps may be implemented by different modules.
Such an apparatus or system is provided in this embodiment. The device is called a lane change monitoring processing device and comprises: the acquisition module is used for acquiring running data of a preset vehicle in a preset section of a road, wherein the running data comprises: a lane in which the predetermined vehicle is traveling; the driving data are obtained by respectively shooting the driving of the preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in the preset section and are mutually separated by preset distances in the road extension direction; the judging module is used for judging whether the lanes where the preset vehicle runs, which are shot by each camera in the plurality of cameras, are the same lane or not; and the determining module is used for determining that the lane change is not performed when the preset vehicle runs in the preset interval if the lane change is performed in the preset interval, and otherwise, the lane change is performed when the preset vehicle runs in the preset interval.
The system or the apparatus is used for implementing the functions of the method in the foregoing embodiments, and each module in the system or the apparatus corresponds to each step in the method, which has been described in the method and is not described herein again.
Optionally, the obtaining module includes: the first acquisition unit is used for acquiring license plate information of the preset vehicle, which is obtained by shooting by the last camera before the preset vehicle leaves the preset interval; and the second acquisition unit is used for acquiring the license plate information shot by each camera and the lane on which the preset vehicle runs corresponding to the license plate information according to the license plate information.
Optionally, the license plate information shot by each camera and the lane where the predetermined vehicle runs corresponding to the license plate information are stored in a Key-Value pair manner, where the license plate information is a Key, and the lane where the predetermined vehicle runs is a Value.
Optionally, the determining module includes: a third obtaining unit, configured to obtain all key-value pairs corresponding to license plate information of the predetermined vehicle; and the judging unit is used for judging whether the lanes where the preset vehicle runs are the same lane or not according to the consistency of all the values stored in the key-Value pair, wherein if all the values are consistent, the lanes where the preset vehicle runs are the same lane, and if not, the lanes are different lanes.
Optionally, all the key-value pairs are stored in a first cache, when it is determined that lanes where the predetermined vehicle travels are all the same lane, the key-value pair corresponding to the license plate of the predetermined vehicle is deleted from the first cache, and when the lanes where the predetermined vehicle travels are different lanes, the key-value pair corresponding to the license plate of the predetermined vehicle is moved from the first cache to a second cache, where the second cache is used for storing the key-value pair corresponding to the vehicle that has the lane change behavior.
Optionally, the method further comprises: and the deleting module is used for traversing the first cache and deleting the key-value pair from the first cache if the existence of the key-value pair in the first cache exceeds the preset duration.
Optionally, after determining that the lane change behavior occurs when the predetermined vehicle travels within the predetermined interval, the method further comprises: a second obtaining module, configured to obtain a first image captured by a first camera and a second image captured by a second camera, where the first camera and the second camera are two adjacent cameras in the multiple cameras, and a lane in which the predetermined vehicle is located in the first image is different from a lane in which the predetermined vehicle is located in the second image; and the storage module is used for splicing the first image and the second image and then storing the spliced images.
Optionally, when the time that the predetermined vehicle enters the predetermined interval exceeds a predetermined time and the license plate information obtained by the last camera before the predetermined vehicle leaves the predetermined interval is not obtained yet, the determining module is configured to: the camera is used for acquiring license plate information of the preset vehicle shot in the preset interval; and judging whether the lanes where the vehicles run are the same lane or not according to the lanes where the vehicles run and obtained by shooting the license plate information of the preset vehicles through the camera.
The problem that the monitoring range is limited or the influence of GPS signals is large in vehicle lane change monitoring in the prior art is solved through the embodiment, and therefore the vehicle lane change can be monitored more accurately through continuous shooting of the vehicles through a plurality of cameras without depending on the GPS signals of the vehicles.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A lane change monitoring processing method is characterized by comprising the following steps:
acquiring running data of a predetermined vehicle in a predetermined section of a road, wherein the running data comprises: a lane in which the predetermined vehicle is traveling; the driving data are obtained by respectively shooting the driving of the preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in the preset section and are mutually separated by preset distances in the extending direction of the road;
judging whether lanes where the scheduled vehicle runs and shot by each camera in the multiple cameras are the same lane or not;
and if the lane change is not carried out, the preset vehicle is determined to run in the preset interval, and otherwise, the lane change behavior is carried out when the preset vehicle runs in the preset interval.
2. The method of claim 1, wherein obtaining travel data for the predetermined vehicle within the predetermined interval comprises:
acquiring license plate information of the preset vehicle, which is obtained by shooting by a last camera before the preset vehicle leaves the preset interval;
and acquiring the license plate information shot by each camera and the lane of the preset vehicle corresponding to the license plate information according to the license plate information.
3. The method of claim 2, wherein in a case that the license plate information captured by the last camera before the predetermined vehicle leaves the predetermined section is not acquired when the time for the predetermined vehicle to enter the predetermined section exceeds a predetermined time, determining whether the lanes in which the predetermined vehicle travels captured by each of the plurality of cameras are all the same lane comprises:
the camera is used for acquiring license plate information of the preset vehicle shot in the preset interval;
and judging whether the lanes where the vehicles run are the same lane or not according to the lanes where the vehicles run and obtained by shooting the license plate information of the preset vehicles through the camera.
4. The method according to claim 1 or 2, wherein the license plate information shot by each camera and the lane where the predetermined vehicle runs corresponding to the license plate information are stored by using a Key-Value pair, wherein the license plate information is a Key, and the lane where the predetermined vehicle runs is a Value.
5. The method of claim 4, wherein determining whether the lanes in which the predetermined vehicle travels captured by each of the plurality of cameras are all the same lane comprises:
acquiring all key-value pairs corresponding to the license plate information of the preset vehicle;
and judging whether the lanes where the preset vehicle runs are all the same lanes according to whether all the values stored in the key-Value pair are consistent or not, wherein if all the values are consistent, the lanes where the preset vehicle runs are all the same lanes, and otherwise, the lanes are different lanes.
6. The method of claim 5, wherein all the key-value pairs are stored in a first cache, and wherein the key-value pairs corresponding to the license plate of the predetermined vehicle are deleted from the first cache if it is determined that the lanes in which the predetermined vehicle travels are all the same lane, and wherein the key-value pairs corresponding to the license plate of the predetermined vehicle are moved from the first cache to a second cache if the lanes in which the predetermined vehicle travels are different lanes, wherein the second cache is used for storing the key-value pairs corresponding to the vehicle in which lane change behavior occurs.
7. The method of claim 6, further comprising:
and traversing the first cache, and if the existence of the key-value pair in the first cache exceeds the preset time length, deleting the key-value pair from the first cache.
8. The method of claim 1, wherein after determining that lane change behavior occurs when the predetermined vehicle is traveling within the predetermined interval, the method further comprises:
acquiring a first image shot by a first camera and a second image shot by a second camera, wherein the first camera and the second camera are two adjacent cameras in the plurality of cameras, and the lane where the preset vehicle is located in the first image is different from the lane where the preset vehicle is located in the second image;
and splicing the first image and the second image and then storing.
9. A lane change monitoring processing apparatus, comprising:
the acquisition module is used for acquiring running data of a preset vehicle in a preset section of a road, wherein the running data comprises: a lane in which the predetermined vehicle is traveling; the driving data are obtained by respectively shooting the driving of the preset vehicle by a plurality of cameras, and the plurality of cameras are arranged in the preset section and are mutually separated by preset distances in the extending direction of the road;
the judging module is used for judging whether the lanes where the preset vehicle runs, which are shot by each camera in the plurality of cameras, are the same lane or not;
and the determining module is used for determining that the lane change is not performed when the preset vehicle runs in the preset interval if the lane change is performed in the preset interval, and otherwise, the lane change is performed when the preset vehicle runs in the preset interval.
10. A lane change monitoring processing system, comprising:
the system comprises a plurality of cameras, a control unit and a display unit, wherein the cameras are used for respectively shooting the running of a preset vehicle in a preset section of a road, and are arranged in the preset section and are separated from each other by a preset distance in the extending direction of the road;
software for performing the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210546012.9A CN114999171A (en) | 2022-05-19 | 2022-05-19 | Lane change monitoring processing method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210546012.9A CN114999171A (en) | 2022-05-19 | 2022-05-19 | Lane change monitoring processing method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114999171A true CN114999171A (en) | 2022-09-02 |
Family
ID=83027101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210546012.9A Pending CN114999171A (en) | 2022-05-19 | 2022-05-19 | Lane change monitoring processing method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114999171A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120132812A (en) * | 2011-05-30 | 2012-12-10 | 휴앤에스(주) | Matching system of violated vehicle for hi-pass road |
| KR20130106658A (en) * | 2012-03-20 | 2013-09-30 | (주)아이티에스뱅크 | A method and system of auto detecting a lane offense car |
| WO2017157119A1 (en) * | 2016-03-18 | 2017-09-21 | 中兴通讯股份有限公司 | Method and device for identifying abnormal behavior of vehicle |
| CN107967323A (en) * | 2017-11-24 | 2018-04-27 | 泰华智慧产业集团股份有限公司 | The method and system of abnormal in-trips vehicles analysis are carried out based on big data |
| CN108806269A (en) * | 2018-06-22 | 2018-11-13 | 安徽科力信息产业有限责任公司 | A kind of method and device of record motor vehicle continuous transformation track illegal activities |
| CN109191830A (en) * | 2018-08-09 | 2019-01-11 | 昆明理工大学 | A kind of congestion in road detection method based on video image processing |
| KR20190026248A (en) * | 2017-09-04 | 2019-03-13 | 한국도로공사 | An enforcing system for smart traffic violation |
| CN109686096A (en) * | 2019-03-07 | 2019-04-26 | 王伟名 | A kind of express highway all-way section speed-measuring method |
| CN110675639A (en) * | 2019-12-03 | 2020-01-10 | 武汉中科通达高新技术股份有限公司 | Method for analyzing true cards of fake-licensed vehicle based on bayonet vehicle passing data |
| CN111028503A (en) * | 2018-10-09 | 2020-04-17 | 杭州海康威视系统技术有限公司 | Vehicle lane change monitoring method and device |
| CN111340003A (en) * | 2020-03-26 | 2020-06-26 | 公安部交通管理科学研究所 | Evidence obtaining method and system for illegal lane change behavior in electronic police blind area |
| CN113345218A (en) * | 2020-03-03 | 2021-09-03 | 杭州海康威视数字技术股份有限公司 | Vehicle driving abnormity detection method and device, electronic equipment and readable storage medium |
-
2022
- 2022-05-19 CN CN202210546012.9A patent/CN114999171A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120132812A (en) * | 2011-05-30 | 2012-12-10 | 휴앤에스(주) | Matching system of violated vehicle for hi-pass road |
| KR20130106658A (en) * | 2012-03-20 | 2013-09-30 | (주)아이티에스뱅크 | A method and system of auto detecting a lane offense car |
| WO2017157119A1 (en) * | 2016-03-18 | 2017-09-21 | 中兴通讯股份有限公司 | Method and device for identifying abnormal behavior of vehicle |
| KR20190026248A (en) * | 2017-09-04 | 2019-03-13 | 한국도로공사 | An enforcing system for smart traffic violation |
| CN107967323A (en) * | 2017-11-24 | 2018-04-27 | 泰华智慧产业集团股份有限公司 | The method and system of abnormal in-trips vehicles analysis are carried out based on big data |
| CN108806269A (en) * | 2018-06-22 | 2018-11-13 | 安徽科力信息产业有限责任公司 | A kind of method and device of record motor vehicle continuous transformation track illegal activities |
| CN109191830A (en) * | 2018-08-09 | 2019-01-11 | 昆明理工大学 | A kind of congestion in road detection method based on video image processing |
| CN111028503A (en) * | 2018-10-09 | 2020-04-17 | 杭州海康威视系统技术有限公司 | Vehicle lane change monitoring method and device |
| CN109686096A (en) * | 2019-03-07 | 2019-04-26 | 王伟名 | A kind of express highway all-way section speed-measuring method |
| CN110675639A (en) * | 2019-12-03 | 2020-01-10 | 武汉中科通达高新技术股份有限公司 | Method for analyzing true cards of fake-licensed vehicle based on bayonet vehicle passing data |
| CN113345218A (en) * | 2020-03-03 | 2021-09-03 | 杭州海康威视数字技术股份有限公司 | Vehicle driving abnormity detection method and device, electronic equipment and readable storage medium |
| CN111340003A (en) * | 2020-03-26 | 2020-06-26 | 公安部交通管理科学研究所 | Evidence obtaining method and system for illegal lane change behavior in electronic police blind area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11120282B2 (en) | Traffic violation vehicle identification system, server and non-transitory recording medium in which vehicle control program is recorded | |
| WO2019095588A1 (en) | Roadside parking management method, device and system based on multiple cameras | |
| CN105243851A (en) | Vehicle monitoring method and system | |
| CN104200671A (en) | Method and system for managing virtual gate based on big data platform | |
| CN110634306A (en) | Method and device for determining vehicle position, storage medium and computing equipment | |
| CN108806272A (en) | A kind of method and device for reminding more motor vehicle car owner's illegal parking behaviors | |
| CN111340710B (en) | Method and system for acquiring vehicle information based on image stitching | |
| CN105185108A (en) | Automatic snapshot system of illegal parking at yellow grid lines | |
| CN105185121A (en) | Method for parallelly recognizing license plate via virtual checkpoint | |
| Chang et al. | AI City Challenge 2019-City-Scale Video Analytics for Smart Transportation. | |
| CN108230669B (en) | Road vehicle violation detection method and system based on big data and cloud analysis | |
| CN204833705U (en) | Illegal automatic snapshot system that parks of yellow gridlines | |
| CN107071337A (en) | The transmission method and device of a kind of video monitoring image | |
| WO2016132769A1 (en) | Imaging device, control method for imaging device, and control program | |
| KR20200026492A (en) | Accident monitoring system in tunnel using camera grouping of IoT based | |
| EP3975133A1 (en) | Processing of images captured by vehicle mounted cameras | |
| CN113112813B (en) | Illegal parking detection method and device | |
| CN112182289B (en) | Data deduplication method and device based on Flink frame | |
| CN111429723B (en) | Communication and perception data fusion method based on road side equipment | |
| CN103383814B (en) | A kind of grasp shoot method violating the regulations | |
| CN114999171A (en) | Lane change monitoring processing method, device and system | |
| CN114863690B (en) | Method, device, medium and electronic equipment for identifying solid line lane change | |
| CN202939798U (en) | Intelligent high-definition electronic police system | |
| CN112347996A (en) | Scene state judgment method, device, equipment and storage medium | |
| CN114299744A (en) | Panoramic parking lot system and management scheme |
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 |