CN116363871B - Expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoration method - Google Patents
Expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoration method Download PDFInfo
- Publication number
- CN116363871B CN116363871B CN202310072943.4A CN202310072943A CN116363871B CN 116363871 B CN116363871 B CN 116363871B CN 202310072943 A CN202310072943 A CN 202310072943A CN 116363871 B CN116363871 B CN 116363871B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- path
- information
- data
- portal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000004927 fusion Effects 0.000 claims abstract description 25
- 238000011084 recovery Methods 0.000 claims abstract description 6
- 208000024891 symptom Diseases 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 11
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000007418 data mining Methods 0.000 abstract description 4
- 239000000284 extract Substances 0.000 abstract description 3
- 230000002265 prevention Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a highway holiday non-sign vehicle epidemic situation early warning and entrance information restoring method, which utilizes RSU equipment and snapshot shooting equipment on an ETC portal of a portal frame to analyze and extract data, extracts vehicle information passing through the provincial portal frame and realizes the recognition of vehicles outside the provincial portal frame. Aiming at the conditions of ETC traffic data missing detection, false detection and repeated detection, multi-source data fusion is carried out on ETC transaction flow data, vehicle re-identification information, highway network data and the like based on big data mining and an artificial intelligent algorithm, so that vehicle track restoration is realized. Matching and matching the track information with the ambiguous path of the highway network model to realize the recovery of the non-sign vehicle entrance information. Based on multi-source data fusion, the entry information restoration of the non-sign vehicle is realized by using an artificial intelligence algorithm. The invention solves the current situation that the epidemic situation analysis and epidemic vehicle early warning are difficult for vehicles without entrance information of major holiday non-sign lane vehicles.
Description
Technical Field
The invention relates to the technical field of expressway intelligent traffic and vehicle-road coordination, in particular to an expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoring method.
Background
The toll station and the service area are used as important places for epidemic situation prevention and control of the expressway, and how to perform epidemic situation early warning and epidemic situation prevention and control analysis by utilizing the technologies of artificial intelligence, big data mining, the Internet of things and the like is the current research focus. Experimental attempts of intelligent epidemic prevention and control are also carried out in various places, such as a detection and early warning system for a highway epidemic prevention and control vehicle is put forward in the state of Zhejiang, and the system judges whether the vehicle is an epidemic area vehicle or not by identifying the vehicle and comparing the vehicle with database information, and feeds back monitoring results to different platforms; the traffic transportation part provides a highway epidemic situation prevention and control non-inductive personnel detection and vehicle track tracking system, which comprises an epidemic situation big data subsystem, a vehicle track tracking subsystem, a service area management subsystem, an epidemic situation prevention and control strategy automatic research and judgment subsystem and a service area upstream vehicle induction scheduling subsystem.
At present, an RSU antenna device, a snapshot camera and a network transmission device are paved on ETC portal equipment. The analysis of the data collected by the ETC portal of the fowler-province was performed during the period of the clear, five-section sign of 2022 as follows: the lane snapshot rate of the direct vehicle during the non-symptom period is about 91%, and the lane snapshot success rate during the daily operation period is 98%. The straight through ETC vehicle ratio. Five-section full-province no-sign straight-through lane transit vehicles have an ETC vehicle ratio of about 59%.
Most of the prior art schemes are based on OBU signals recognized by antenna equipment or vehicle entrance information obtained by taking a card when a vehicle enters a toll station, and the current toll station extracts the entrance information of the vehicle and matches the epidemic area information to judge whether the vehicle comes from the epidemic area or not. The method relies on the integrity and accuracy of the entrance information of the vehicles, and when the vehicles enter the expressway network through the non-sign lanes, the method cannot locate and trace back the departure places of the vehicles passing through the holiday non-sign lanes, so that the vehicles of the holiday non-sign lanes have no entrance information.
In addition, the data sharing of the traffic data in each province is not realized, and although the data is uniformly uploaded to the internet-of-things center, the cross-province inquiry of the traffic data by each province is relatively difficult, and the data island is formed by the traffic data in the province, so that the difficulty in identifying and supervising the vehicles entering the outer provinces of the holidays of major festival exists.
Disclosure of Invention
Aiming at the situation that the non-sign vehicles have no entrance information through non-sign lanes and the ETC traffic data have poor quality and have poor track reduction effect in the holiday of major festivals, the invention provides the epidemic early warning and entrance information reduction method for the non-sign vehicles on the holiday of the expressway, and the recognition of the non-sign vehicles, the track reduction of the vehicles and the entrance information reduction of the non-sign vehicles can be realized by utilizing the fusion of big data and artificial intelligence based on multi-source data.
The technical scheme adopted by the invention is as follows:
the expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoring method comprises the following specific steps:
step 1, obtaining target highway network data and constructing a highway network model;
step 2, acquiring ambiguity paths of a designated starting node and a middle termination point based on a Dijkstra algorithm of depth constraint to form a shortest ambiguity path set B;
specifically, as the highway network is large in scale and the ambiguous paths between any nodes of the highway are numerous, the path length of the ambiguous paths is constrained by comprehensively considering the driving behavior and the running path cost of a vehicle owner, and the ambiguous paths of the designated starting node and the designated middle termination point are acquired by adopting a Dijkstra algorithm based on depth constraint.
Step 3, acquiring vehicle passing data and a shortest ambiguous path set B, and performing data screening and data fusion processing to generate vehicle track data;
step 4, analyzing the vehicle track data and judging whether the current vehicle is an exempt vehicle; if yes, extracting the exit vehicle information from the passing data of the non-sign vehicles and entering a step 5; otherwise, extracting the exit vehicle information from the passing data of the non-symptom-free vehicles and entering a step 8;
step 5, judging whether the ETC vehicle is an ETC vehicle or not through the exit vehicle information; if yes, executing the step 6; otherwise, executing the step 7;
step 6, aiming at the ETC vehicle, comparing whether transaction information of the provincial portal exists in the passing path by utilizing transaction data of the ETC vehicle passing through the ETC portal; if yes, judging that the outer province enters the vehicle and pushing early warning information; otherwise, ending the early warning process;
step 7, extracting vehicle snapshot license plates through collected data of the snapshot equipment for information matching aiming at the non-ETC vehicles, and judging whether license plate information of the vehicles is recognized by the snapshot equipment on the provincial portal frame or not; if yes, judging that the vehicle enters the province, and pushing early warning information; otherwise, ending the early warning process;
step 8, judging whether an entrance toll station of the non-symptom-free vehicle is a provincial toll station; if yes, early warning is carried out; otherwise, ending the early warning process;
further, in step 1, modeling the positions and topological relations of ETC portal frames, service areas and toll stations on the expressway by using graph theory, and modeling the topological structures of the ETC portal frames, service areas and toll stations by using weighted directed graphs according to the properties of the expressway for directional driving and controlling access to represent portal topological graphs in the expressway, wherein N, L, D represents the communication relations among nodes in the road network and road distances respectively; the specific expression of DG is as follows:
wherein Node i 、Node j For two different nodes i and j of the highway,indicating the connection condition of two nodes and returning the road network distance, inf indicates Node i And Node j And cannot be directly communicated.
Specifically, the nodes of the expressway comprise toll stations, ETC (electronic toll collection) portal frames and service areas; when Node i And Node j Connected and the distance between the nodes is 7632mOther nodes are similar; when Node i And Node j Is not communicated withWhen Node i ＝Node j Then->
Further, the ambiguous path set B generation steps are as follows:
step 2-1, acquiring a starting point O, an ending point D and a termination length cutoff;
step 2-2, calculating a shortest path between the starting point 0 and the end point D by using a shortest path method as a shortest path Pk, and representing the shortest path as a plurality of nodes and splitting the shortest path into a plurality of edges;
step 2-3, judging whether the number K of the current shortest paths is smaller than the maximum candidate path number K and the candidate shortest paths are also included; if yes, executing the step 2-4; otherwise, executing the step 2-8;
specifically, as an implementation method, the maximum candidate path number K takes a value of 15.
Step 2-4, each node except the end point on the shortest path Pk is respectively used as a deviation point;
step 2-5, traversing each deviation point, and calculating and obtaining the shortest path from each deviation point to the end point;
step 2-6, for each deviation point, combining the paths from the start point to the deviation point and the paths from the deviation point to the end point into a new candidate path and adding the new candidate path into the candidate path set
Step 2-7, judging whether the candidate path set is an empty set or not; if yes, executing the step 2-8; otherwise, traversing the candidate path set, taking the path with the path length smaller than the termination length data as the shortest path, moving the shortest path out of the candidate path set, and executing the step 2-3;
step 2-8, all shortest paths will be found to form the ambiguity path set B.
Further, the vehicle traffic data in step 3 includes ETC portal traffic data, ETC entry data, ETC portal snapshot video data, and toll booth snapshot data.
Further, the step of generating the vehicle track based on the multi-source data fusion in the step 3 is as follows:
step 3-1, extracting ETC portal transaction data, sorting according to the passing time and generating an ETC portal transaction path TradePath, tradePath expression as follows:
TradePath＝{Plate，OBUID，T A ，N A }
wherein Plate is a vehicle license Plate number; the OBUID is vehicle-mounted OBU information; t (T) A For time series of transactions, T A ＝<T A 1，T A 2...，T A n＞，T A 1 is the first transaction time, T A n is the n-th transaction time elapsed; n (N) A For trading portal sequence, N A ＝<N A 1，N A 2...，N A n>，N A 1 is the first node of high-speed transaction on a vehicle, N A n is the nth node of the vehicle transaction, namely the last node;
step 3-2, extracting ETC portal snapshot data, sequencing according to snapshot time, and generating an expression of an ETC portal snapshot path CapPath, capPath as follows:
CapPath＝{Plate，VehColor，ReID，T B ，N B }
wherein Plate is a vehicle license Plate number; vehCOlor is vehicle color; the ReID is a unique vehicle identifier identified by a vehicle re-identification system after the video is captured by the capturing equipment; t (T) B For snap-shooting time series, T B ＝＜T B 1，T B 2...，T B m＞，T B 1 is the first snapshot time, T B m is the m-th snapshot time; n (N) B To take a candid photograph of the gantry sequence, N B ＝<N B 1，N B 2...，N B m>，N B 1 is a first node of high-speed snapshot on a vehicle, and Nn is an mth node of the vehicle snapshot, namely a last node;
step 3-3, fusing the TradePath and the CapPath to generate fusion Path; the expression for fusion Path is as follows:
FusionPath＝{Plate，VehColor，ReID，T C ，N C ，S}
wherein Plate is a vehicle license Plate number; vehCOlor is vehicle color; the ReID is a unique vehicle identifier identified by a vehicle re-identification system after the video is captured by the capturing equipment; t (T) C To fuse the track time series, T C ＝<T C 1，T C 2...，T C k>，T C 1 is the first portal transit time, T C k is the passing time of the kth portal; n (N) C For passing through the portal sequence N C ＝<N C 1，N C 2...，N C k>，N C 1 is the first node of high-speed traffic on the vehicle, N C k is the last node of the vehicle traffic; s is a sequence of data sources, s=<S1，S2...，Sk>S1 represents N C 1 or T C 1, wherein the data source is the transaction number of the ETC portal or the snapshot data of the ETC portal.
And 3-4, performing track matching on the fusion path and the path of the ambiguous vehicle track data B by using a track matching algorithm, matching the running path of the current vehicle, and matching the entrance toll station information of the current standard track to restore the vehicle entrance toll station information.
Specifically, the current standard trajectory is derived by querying a road network model constructed from the highway portal topology.
Further, in the step 3-4, all paths in the fusion path and the ambiguous vehicle track data B are subjected to matching analysis, and after matching is successful, entrance information is obtained; the specific steps of the track matching algorithm are as follows:
and 3-4-1, extracting traffic node information related to fusion path, and matching with paths in the ambiguous vehicle track data B to generate a potential path set PotentialPathSet.
And 3-4-2, calculating Sim (FusionPath, potentialPath) by using the track similarity, and selecting the potential path with the highest similarity.
And 3-4-3, extracting an entrance toll station of the PotentialPath as entrance toll station information of the current track.
Further, the exit vehicle information of the non-sign vehicle in step 4 includes license plate information, pass id, physical address (Media Access Control Address, MAC) of On Board Unit (OBU), and path information.
Further, the exit vehicle information of the non-qualified vehicle in step 4 includes license plate information, pass, entrance toll booth, entrance time, physical address (Media Access Control Address, MAC) of On Board Unit (OBU), and path information.
According to the technical scheme, the RSU equipment and the snapshot shooting equipment on the ETC portal of the portal are utilized, the data are analyzed and extracted, the vehicle information passing through the provincial portal is extracted, and the recognition of the vehicle outside the provincial portal is realized. Aiming at the conditions of ETC traffic data missing detection, false detection and repeated detection, multi-source data fusion is carried out on ETC transaction flow data, vehicle re-identification information, highway network data and the like based on big data mining and an artificial intelligent algorithm, so that vehicle track restoration is realized. Matching and matching the track information with the ambiguous path of the highway network model to realize the recovery of the non-sign vehicle entrance information.
Compared with the prior art, the invention has the following beneficial effects: 1. and identifying and extracting the vehicles passing through the provincial portal by utilizing the RSU equipment and the snapshot equipment, identifying the vehicles outside the provincial portal, generating early warning information, and pushing the early warning information to on-site epidemic prevention personnel for epidemic prevention and control when the vehicles are out of high speed. The method solves the problem that the traffic data of the provincial domain cannot be directly shared, so that the vehicle is free from entrance information during major holidays, and the early warning of the vehicle outside the provincial domain is difficult. 2. Based on multi-source data fusion, the entry information restoration of the non-sign vehicle is realized by using an artificial intelligence algorithm. The method solves the current situation that the epidemic situation analysis and epidemic vehicle early warning are difficult for vehicles without entrance information of major holiday non-sign lane vehicles.
Drawings
The invention is described in further detail below with reference to the drawings and detailed description;
FIG. 1 is a schematic diagram of a highway holiday immune vehicle epidemic situation early warning flow;
FIG. 2 is a schematic diagram of the high entry information reduction method of the present invention;
FIG. 3 is a schematic diagram of a highway network model of a certain province;
FIG. 4 is a flow chart of a Di Jie Style algorithm based on depth constraints;
fig. 5 is a schematic diagram of track fusion.
Detailed Description
For the purposes, technical solutions and advantages of the embodiments of the present application, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
As shown in one of fig. 1 to 5, the invention discloses a highway holiday immune vehicle epidemic early warning and entrance information restoring method, which comprises the following specific steps:
step 1, obtaining target highway network data and constructing a highway network model;
step 2, acquiring ambiguity paths of a designated starting node and a middle termination point based on a Dijkstra algorithm of depth constraint to form a shortest ambiguity path set B;
specifically, as the highway network is large in scale and the ambiguous paths between any nodes of the highway are numerous, the path length of the ambiguous paths is constrained by comprehensively considering the driving behavior and the running path cost of a vehicle owner, and the ambiguous paths of the designated starting node and the designated middle termination point are acquired by adopting a Dijkstra algorithm based on depth constraint.
Step 3, acquiring vehicle passing data and a shortest ambiguous path set B, and performing data screening and data fusion processing to generate vehicle track data;
step 4, analyzing the vehicle track data and judging whether the current vehicle is an exempt vehicle; if yes, extracting the exit vehicle information from the passing data of the non-sign vehicles and entering a step 5; otherwise, extracting the exit vehicle information from the passing data of the non-symptom-free vehicles and entering a step 8;
step 5, judging whether the ETC vehicle is an ETC vehicle or not through the exit vehicle information; if yes, executing the step 6; otherwise, executing the step 7;
step 6, aiming at the ETC vehicle, comparing whether transaction information of the provincial portal exists in the passing path by utilizing transaction data of the ETC vehicle passing through the ETC portal; if yes, judging that the outer province enters the vehicle and pushing early warning information; otherwise, ending the early warning process;
step 7, extracting vehicle snapshot license plates through collected data of the snapshot equipment for information matching aiming at the non-ETC vehicles, and judging whether license plate information of the vehicles is recognized by the snapshot equipment on the provincial portal frame or not; if yes, judging that the vehicle enters the province, and pushing early warning information; otherwise, ending the early warning process;
step 8, judging whether an entrance toll station of the non-symptom-free vehicle is a provincial toll station; if yes, early warning is carried out; otherwise, ending the early warning process;
further, in step 1, modeling the positions and topological relations of ETC portal frames, service areas and toll stations on the expressway by using graph theory, and modeling the topological structures of the ETC portal frames, service areas and toll stations by using weighted directed graphs according to the properties of the expressway for directional driving and controlling access to represent portal topological graphs in the expressway, wherein N, L, D represents the communication relations among nodes in the road network and road distances respectively; the specific expression of DG is as follows:
wherein Node i 、Node j For two different nodes i and j of the highway,representing the connection condition of two nodes and returning to the road networkDistance, inf represents Node i And Node j And cannot be directly communicated.
Specifically, the nodes of the expressway comprise toll stations, ETC (electronic toll collection) portal frames and service areas; when Node i And Node j Connected and the distance between the nodes is 7632mOther nodes are similar; when Node i And Node j Is not communicated withWhen Node i ＝Node j Then->
Further, the ambiguous path set B generation steps are as follows:
step 2-1, acquiring a starting point O, an ending point D and a termination length cutoff;
step 2-2, calculating a shortest path between the starting point 0 and the end point D by using a shortest path method as a shortest path Pk, and representing the shortest path as a plurality of nodes and splitting the shortest path into a plurality of edges;
step 2-3, judging whether the number K of the current shortest paths is smaller than the maximum candidate path number K and the candidate shortest paths are also included; if yes, executing the step 2-4; otherwise, executing the step 2-8;
step 2-4, each node except the end point on the shortest path Pk is respectively used as a deviation point;
step 2-5, traversing each deviation point, and calculating and obtaining the shortest path from each deviation point to the end point;
step 2-6, for each deviation point, combining the paths from the start point to the deviation point and the paths from the deviation point to the end point into a new candidate path and adding the new candidate path into the candidate path set
Step 2-7, judging whether the candidate path set is an empty set or not; if yes, executing the step 2-8; otherwise, traversing the candidate path set, taking the path with the path length smaller than the termination length data as the shortest path, moving the shortest path out of the candidate path set, and executing the step 2-3;
step 2-8, all shortest paths will be found to form the ambiguity path set B.
Further, the vehicle traffic data in step 3 includes ETC portal traffic data, ETC entry data, ETC portal snapshot video data, and toll booth snapshot data.
Further, the step of generating the vehicle track based on the multi-source data fusion in the step 3 is as follows:
step 3-1, extracting ETC portal transaction data, sorting according to the passing time and generating an ETC portal transaction path TradePath, tradePath expression as follows:
TradePath＝{Plate，OBUID，T A ，N A }
wherein Plate is a vehicle license Plate number; the OBUID is vehicle-mounted OBU information; t (T) A For time series of transactions, T A ＝<T A 1，T A 2...，T A n＞，T A 1 is the first transaction time, T A n is the n-th transaction time elapsed; n (N) A For trading portal sequence, N A ＝<N A 1，N A 2...，N A n>，N A 1 is the first node of high-speed transaction on a vehicle, N A n is the nth node of the vehicle transaction, namely the last node;
specifically, the TradePath comprises license plate number information, vehicle-mounted OBU information, a transaction time sequence and a transaction portal sequence.
Step 3-2, extracting ETC portal snapshot data, sequencing according to snapshot time, and generating an expression of an ETC portal snapshot path CapPath, capPath as follows:
CapPath＝{Plate，VehColor，ReID，T B ，N B }
wherein Plate is a vehicle license Plate number; vehCOlor is vehicle color; the ReID is a unique vehicle identifier identified by a vehicle re-identification system after the video is captured by the capturing equipment; t (T) B For snap-shooting time series, T B ＝<T B 1，T B 2...，T B m>，T B 1 is the first snapshot time, T B m is the passing m-th snapshot time；N B To take a candid photograph of the gantry sequence, N B ＝<N B 1，N B 2...，N B m>，N B 1 is a first node of high-speed snapshot on a vehicle, and Nn is an mth node of the vehicle snapshot, namely a last node;
specifically, the CapPath includes license plate number information, vehicle color, vehicle ReID, snapshot time series, and snapshot portal series.
Step 3-3, fusing the TradePath and the CapPath to generate fusion Path; the expression for fusion Path is as follows:
FusionPath＝{Plate，VehColor，ReID，T C ，N c ，S}
wherein Plate is a vehicle license Plate number; vehCOlor is vehicle color; the ReID is a unique vehicle identifier identified by a vehicle re-identification system after the video is captured by the capturing equipment; t (T) C To fuse the track time series, T C ＝<T C 1，T C 2...，T C k>，T C 1 is the first portal transit time, T C k is the passing time of the kth portal; n (N) C For passing through the portal sequence N C ＝<N C 1，N C 2...，N C k>，N C 1 is the first node of high-speed traffic on the vehicle, N C k is the last node of the vehicle traffic; s is a sequence of data sources, s=<S1，S2...，Sk>S1 represents N C 1 or T C 1, wherein the data source is the transaction number of the ETC portal or the snapshot data of the ETC portal.
And 3-4, performing track matching on the fusion path and the path of the ambiguous vehicle track data B by using a track matching algorithm, matching the running path of the current vehicle, and matching the entrance toll station information of the current standard track to restore the vehicle entrance toll station information.
Specifically, the current standard trajectory is derived by querying a road network model constructed from the highway portal topology.
Further, in the step 3-4, all paths in the fusion path and the ambiguous vehicle track data B are subjected to matching analysis, and after matching is successful, entrance information is obtained; the specific steps of the track matching algorithm are as follows:
and 3-4-1, extracting traffic node information related to fusion path, and matching with paths in the ambiguous vehicle track data B to generate a potential path set PotentialPathSet.
And 3-4-2, calculating Sim (FusionPath, potentialPath) by using the track similarity, and selecting the potential path with the highest similarity.
And 3-4-3, extracting an entrance toll station of the PotentialPath as entrance toll station information of the current track.
Further, the exit vehicle information of the non-sign vehicle in step 4 includes license plate information, pass id, physical address (Media Access Control Address, MAC) of On Board Unit (OBU), and path information.
Further, the exit vehicle information of the non-qualified vehicle in step 4 includes license plate information, pass, entrance toll booth, entrance time, physical address (Media Access Control Address, MAC) of On Board Unit (OBU), and path information.
According to the technical scheme, the RSU equipment and the snapshot shooting equipment on the ETC portal of the portal are utilized, the data are analyzed and extracted, the vehicle information passing through the provincial portal is extracted, and the recognition of the vehicle outside the provincial portal is realized. Aiming at the conditions of ETC traffic data missing detection, false detection and repeated detection, multi-source data fusion is carried out on ETC transaction flow data, vehicle re-identification information, highway network data and the like based on big data mining and an artificial intelligent algorithm, so that vehicle track restoration is realized. Matching and matching the track information with the ambiguous path of the highway network model to realize the recovery of the non-sign vehicle entrance information.
Compared with the prior art, the invention has the following beneficial effects: 1. and identifying and extracting the vehicles passing through the provincial portal by utilizing the RSU equipment and the snapshot equipment, identifying the vehicles outside the provincial portal, generating early warning information, and pushing the early warning information to on-site epidemic prevention personnel for epidemic prevention and control when the vehicles are out of high speed. The method solves the problem that the traffic data of the provincial domain cannot be directly shared, so that the vehicle is free from entrance information during major holidays, and the early warning of the vehicle outside the provincial domain is difficult. 2. Based on multi-source data fusion, the entry information restoration of the non-sign vehicle is realized by using an artificial intelligence algorithm. The method solves the current situation that the epidemic situation analysis and epidemic vehicle early warning are difficult for vehicles without entrance information of major holiday non-sign lane vehicles.
It will be apparent that the embodiments described are some, but not all, of the embodiments of the present application. Embodiments and features of embodiments in this application may be combined with each other without conflict. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments of the present application is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Claims (4)
1. The highway holiday non-sign vehicle epidemic situation early warning and entrance information restoring method is characterized in that: the method comprises the following specific steps:
step 1, obtaining target highway network data and constructing a highway network model; modeling the positions and topological relations of ETC portal frames, service areas and toll stations on the expressway by using a graph theory, and modeling the topological structures of the ETC portal frames, the service areas and the toll stations by using weighted directed graphs according to the properties of the expressway for directional driving and controlling access to the expressway so as to represent portal topological graphs in the expressway, wherein N, L, D respectively represents the nodes in the road network, the communication relation among the nodes and the road distance; the specific expression of DG is as follows:
wherein Node i 、Node j For two different nodes i and j of the highway,indicating the connection condition of two nodes and returning the road network distance, inf indicates Node i And Node j The two parts cannot be directly communicated;
step 2, acquiring an ambiguous path of a designated starting node and an ending point based on a Dijkstra algorithm of depth constraint to form a shortest ambiguous path set B; the ambiguous path set B generation steps are as follows:
step 2-1, acquiring a starting point O, an ending point D and a termination length cutoff;
step 2-2, calculating a shortest path between a starting point O and an end point D by using a shortest path method as a shortest path Pk, and representing the shortest path as a plurality of nodes and splitting the nodes into a plurality of edges;
step 2-3, judging whether the number K of the current shortest paths is smaller than the set maximum candidate path number K and the candidate shortest paths are also included; if yes, executing the step 2-4; otherwise, executing the step 2-8;
step 2-4, each node except the end point on the shortest path Pk is respectively used as a deviation point;
step 2-5, traversing each deviation point, and calculating and obtaining the shortest path from each deviation point to the end point;
step 2-6, for each deviation point, combining the paths from the start point to the deviation point and the paths from the deviation point to the end point into a new candidate path and adding the new candidate path into the candidate path set
Step 2-7, judging whether the candidate path set is an empty set or not; if yes, executing the step 2-8; otherwise, traversing the candidate path set, taking the path with the path length smaller than the termination length data as the shortest path, moving the shortest path out of the candidate path set, and executing the step 2-3;
step 2-8, finding all shortest paths to form an ambiguous path set B;
step 3, acquiring vehicle passing data and a shortest ambiguous path set B, and performing data screening and data fusion processing to generate vehicle track data; the step of generating the vehicle track based on multi-source data fusion in the step 3 is as follows:
step 3-1, extracting ETC portal transaction data, sorting according to the passing time and generating an ETC portal transaction path TradePath, tradePath expression as follows:
TradePath＝{Plate,OBUID,T A ,N A }
wherein Plate is a vehicle license Plate number; the OBUID is vehicle-mounted OBU information; t (T) A For time series of transactions, T A ＝<T A 1,T A 2…,T A n>，T A 1 is the first transaction time, T A n is the n-th transaction time elapsed; n (N) A For trading portal sequence, N A ＝<N A 1,N A 2…,N A n>，N A 1 is the first node of high-speed transaction on a vehicle, N A n is the nth node of the vehicle transaction, namely the last node;
step 3-2, extracting ETC portal snapshot data, sequencing according to snapshot time, and generating an expression of an ETC portal snapshot path CapPath, capPath as follows:
CapPath＝{Plate,VehColor,ReID,T B ,N B }
wherein Plate is a vehicle license Plate number; vehCOlor is vehicle color; the ReID is a unique vehicle identifier identified by a vehicle re-identification system after the video is captured by the capturing equipment; t (T) B For snap-shooting time series, T B ＝<T B 1,T B 2…,T B m>，T B 1 is the first snapshot time, T B m is the m-th snapshot time; n (N) B To take a candid photograph of the gantry sequence, N B ＝<N B 1,N B 2…,N B m>，N B 1 is a first node of high-speed snapshot on a vehicle, and Nn is an mth node of the vehicle snapshot, namely a last node;
step 3-3, fusing the TradePath and the CapPath to generate fusion Path; the expression for fusion Path is as follows:
FusionPath＝{Plate,VehColor,ReID,T C ,N C ,S}
wherein Plate is a vehicle license Plate number; vehCOlor is vehicle color; the ReID is a unique vehicle identifier identified by a vehicle re-identification system after the video is captured by the capturing equipment; t (T) C To fuse the track time series, T C ＝<T C 1,T C 2…,T C k>，T C 1 is the first portal transit time, T C k is the passing time of the kth portal; n (N) C For passing through the portal sequence N C ＝<N C 1,N C 2…,N C k>，N C 1 is the first node of high-speed traffic on the vehicle, N C k is the last node of the vehicle traffic; s is a sequence of data sources, s=<S1,S2…,Sk>S1 represents N C 1 or T C 1, the data source is the transaction number of the ETC portal or the snapshot data of the ETC portal;
step 3-4, carrying out track matching on the fusion path and the path of the ambiguous vehicle track data B by utilizing a track matching algorithm, matching the running path of the current vehicle, and matching the entrance toll station information of the current standard track to restore the vehicle entrance toll station information; the specific steps of the track matching algorithm are as follows:
step 3-4-1, extracting traffic node information related to fusion path, and matching with paths in the ambiguous vehicle track data B to generate a potential path set PotentialPathSet;
step 3-4-2, calculating Sim (FusionPath, potentialPath) by using the track similarity, and selecting the potential path with the highest similarity;
step 3-4-3, extracting an entrance toll station of the potential path as entrance toll station information of the current track;
step 4, analyzing the vehicle track data and judging whether the current vehicle is an exempt vehicle; if yes, extracting the exit vehicle information from the passing data of the non-sign vehicles and entering a step 5; otherwise, extracting the exit vehicle information from the passing data of the non-symptom-free vehicles and entering a step 8;
step 5, judging whether the ETC vehicle is an ETC vehicle or not through the exit vehicle information; if yes, executing the step 6; otherwise, executing the step 7;
step 6, aiming at the ETC vehicle, comparing whether transaction information of the provincial portal exists in the passing path by utilizing transaction data of the ETC vehicle passing through the ETC portal; if yes, judging that the outer province enters the vehicle and pushing early warning information; otherwise, ending the early warning process;
step 7, extracting vehicle snapshot license plates through collected data of the snapshot equipment for information matching aiming at the non-ETC vehicles, and judging whether license plate information of the vehicles is recognized by the snapshot equipment on the provincial portal frame or not; if yes, judging that the vehicle enters the province, and pushing early warning information; otherwise, ending the early warning process;
step 8, judging whether an entrance toll station of the non-symptom-free vehicle is a provincial toll station; if yes, early warning is carried out; otherwise, ending the early warning process.
2. The expressway holiday non-stop vehicle epidemic situation pre-warning and entrance information recovery method according to claim 1, wherein the method is characterized by comprising the following steps of: the vehicle passing data in the step 3 comprise ETC portal passing data, ETC entrance data, ETC portal snapshot video data and toll station snapshot data.
3. The expressway holiday non-stop vehicle epidemic situation pre-warning and entrance information recovery method according to claim 1, wherein the method is characterized by comprising the following steps of: and 4, the exit vehicle information of the non-sign vehicle comprises license plate information, pass, physical addresses of vehicle-mounted units and path information.
4. The expressway holiday non-stop vehicle epidemic situation pre-warning and entrance information recovery method according to claim 1, wherein the method is characterized by comprising the following steps of: the exit vehicle information of the non-sign vehicle in the step 4 comprises license plate information, passid, entrance toll station, entrance time, physical address of the vehicle-mounted unit and path information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310072943.4A CN116363871B (en) | 2023-01-15 | 2023-01-15 | Expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310072943.4A CN116363871B (en) | 2023-01-15 | 2023-01-15 | Expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoration method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116363871A CN116363871A (en) | 2023-06-30 |
| CN116363871B true CN116363871B (en) | 2024-03-26 |
Family
ID=86916595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310072943.4A Active CN116363871B (en) | 2023-01-15 | 2023-01-15 | Expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116363871B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009059313A (en) * | 2007-09-03 | 2009-03-19 | Hitachi Ltd | Vehicle monitoring apparatus for toll road automatic toll gate |
| KR20090077114A (en) * | 2008-01-10 | 2009-07-15 | 한국도로공사 | System for checking an unpaid car of the toll road and controlling method for the same |
| JP2013072717A (en) * | 2011-09-27 | 2013-04-22 | Navitime Japan Co Ltd | Comparative information providing apparatus, comparative information providing system, server apparatus, terminal apparatus, comparative information providing method, and program |
| CN205721998U (en) * | 2016-02-18 | 2016-11-23 | 华南理工大学 | Turn pike net traffic information collection based on path identifying system and inducible system |
| CN107564117A (en) * | 2017-09-05 | 2018-01-09 | 北京聚利科技股份有限公司 | Compound visa card and ID of trace route path method |
| CN108564669A (en) * | 2018-04-14 | 2018-09-21 | 苏州天为幕烟花科技有限公司 | Vehicle drives into the determination method of high speed |
| KR20190139090A (en) * | 2018-06-07 | 2019-12-17 | 파킹클라우드 주식회사 | Real-time vehicle management system and method on toll road |
| CN111681427A (en) * | 2020-06-16 | 2020-09-18 | 青岛理工大学 | Highway entrance and exit ETC accurate identification method based on artificial intelligence |
| CN111757067A (en) * | 2020-07-08 | 2020-10-09 | 福建省高速公路信息科技有限公司 | Expressway service area cash register inspection system and method based on video AI |
| CN113963550A (en) * | 2020-07-21 | 2022-01-21 | 阿里巴巴集团控股有限公司 | Ambiguous path identification method and device and electronic equipment |
| CN114049612A (en) * | 2021-11-12 | 2022-02-15 | 甘肃紫光智能交通与控制技术有限公司 | Highway vehicle charge auditing system based on graph searching technology and dual-obtaining and checking method for driving path |
| CN114067560A (en) * | 2021-09-30 | 2022-02-18 | 交通运输部公路科学研究所 | Highway epidemic prevention and control non-inductive personnel detection and vehicle trajectory tracking system |
| CN114565982A (en) * | 2022-02-28 | 2022-05-31 | 福建省高速公路信息科技有限公司 | ETC-based vehicle state monitoring method |
| CN114863675A (en) * | 2022-04-08 | 2022-08-05 | 北京工业大学 | Method for predicting position of key vehicle and alarming abnormity based on road police data fusion |
| CN114999181A (en) * | 2022-05-11 | 2022-09-02 | 山东高速建设管理集团有限公司 | ETC system data-based highway vehicle speed abnormity identification method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5123515B2 (en) * | 2006-10-17 | 2013-01-23 | 三菱重工業株式会社 | License plate information system, license plate information utilization method |
| JP4945543B2 (en) * | 2008-10-31 | 2012-06-06 | 株式会社東芝 | Road traffic information providing system and method |
-
2023
- 2023-01-15 CN CN202310072943.4A patent/CN116363871B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009059313A (en) * | 2007-09-03 | 2009-03-19 | Hitachi Ltd | Vehicle monitoring apparatus for toll road automatic toll gate |
| KR20090077114A (en) * | 2008-01-10 | 2009-07-15 | 한국도로공사 | System for checking an unpaid car of the toll road and controlling method for the same |
| JP2013072717A (en) * | 2011-09-27 | 2013-04-22 | Navitime Japan Co Ltd | Comparative information providing apparatus, comparative information providing system, server apparatus, terminal apparatus, comparative information providing method, and program |
| CN205721998U (en) * | 2016-02-18 | 2016-11-23 | 华南理工大学 | Turn pike net traffic information collection based on path identifying system and inducible system |
| CN107564117A (en) * | 2017-09-05 | 2018-01-09 | 北京聚利科技股份有限公司 | Compound visa card and ID of trace route path method |
| CN108564669A (en) * | 2018-04-14 | 2018-09-21 | 苏州天为幕烟花科技有限公司 | Vehicle drives into the determination method of high speed |
| KR20190139090A (en) * | 2018-06-07 | 2019-12-17 | 파킹클라우드 주식회사 | Real-time vehicle management system and method on toll road |
| CN111681427A (en) * | 2020-06-16 | 2020-09-18 | 青岛理工大学 | Highway entrance and exit ETC accurate identification method based on artificial intelligence |
| CN111757067A (en) * | 2020-07-08 | 2020-10-09 | 福建省高速公路信息科技有限公司 | Expressway service area cash register inspection system and method based on video AI |
| CN113963550A (en) * | 2020-07-21 | 2022-01-21 | 阿里巴巴集团控股有限公司 | Ambiguous path identification method and device and electronic equipment |
| CN114067560A (en) * | 2021-09-30 | 2022-02-18 | 交通运输部公路科学研究所 | Highway epidemic prevention and control non-inductive personnel detection and vehicle trajectory tracking system |
| CN114049612A (en) * | 2021-11-12 | 2022-02-15 | 甘肃紫光智能交通与控制技术有限公司 | Highway vehicle charge auditing system based on graph searching technology and dual-obtaining and checking method for driving path |
| CN114565982A (en) * | 2022-02-28 | 2022-05-31 | 福建省高速公路信息科技有限公司 | ETC-based vehicle state monitoring method |
| CN114863675A (en) * | 2022-04-08 | 2022-08-05 | 北京工业大学 | Method for predicting position of key vehicle and alarming abnormity based on road police data fusion |
| CN114999181A (en) * | 2022-05-11 | 2022-09-02 | 山东高速建设管理集团有限公司 | ETC system data-based highway vehicle speed abnormity identification method |
Non-Patent Citations (2)
| Title |
|---|
| 基于ETC大数据的高速公路服务区入区率研究;刘光雄;中国交通信息化(第05期);全文 * |
| 基于车牌识别数据的车辆使用特征研究:以上海市快速路非沪车牌识别数据为例;郭昕;陈川;;综合运输(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116363871A (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243277B (en) | Commuting vehicle space-time trajectory reconstruction method and system based on license plate recognition data | |
| CN106384513B (en) | A kind of fake-licensed car capture system and method based on intelligent transportation | |
| CN104766479A (en) | Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching | |
| CN107301776A (en) | Track road conditions processing and dissemination method based on video detection technology | |
| CN103714697B (en) | A kind of method of recognition and tracking criminal vehicle | |
| CN103235933A (en) | Vehicle abnormal behavior detection method based on Hidden Markov Model | |
| CN106205120B (en) | A kind of method and device for extracting road cross traffic limitation | |
| CN107329977B (en) | A kind of false-trademark vehicle postsearch screening method based on probability distribution | |
| CN107305736A (en) | A kind of intelligent error-checking method of Car license recognition based on car plate rule and space-time accessibility and system | |
| CN106412508A (en) | Intelligent monitoring method and system of illegal line press of vehicles | |
| CN111008574A (en) | Key person track analysis method based on body shape recognition technology | |
| CN112925820B (en) | Method, device and system for identifying vehicle evasion toll | |
| CN114049612A (en) | Highway vehicle charge auditing system based on graph searching technology and dual-obtaining and checking method for driving path | |
| CN105913668A (en) | Directional fake-licensed car detection method based on vast traffic data statistics | |
| Le et al. | Vehicle count system based on time interval image capture method and deep learning mask R-CNN | |
| CN109872541A (en) | A kind of information of vehicles analysis method and device | |
| Xiong et al. | Vehicle re-identification with image processing and car-following model using multiple surveillance cameras from urban arterials | |
| Tian et al. | A vehicle re-identification algorithm based on multi-sensor correlation | |
| CN107635188A (en) | A kind of video frequency vehicle trace analysis method based on Docker platforms | |
| CN116363871B (en) | Expressway holiday non-sign vehicle epidemic situation early warning and entrance information restoration method | |
| Zaman et al. | A robust deep networks based multi-object multi-camera tracking system for city scale traffic | |
| CN108470451A (en) | A kind of intelligent transportation system based on big data | |
| CN112967410A (en) | Method for identifying toll-evasion vehicles based on longest public subsequence | |
| Cruz et al. | Classified counting and tracking of local vehicles in manila using computer vision | |
| Oliveira-Neto et al. | Tracking large trucks in real time with license plate recognition and text-mining techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |