CN112444256A - Method for time shortest path based on road traffic flow - Google Patents
Method for time shortest path based on road traffic flow Download PDFInfo
- Publication number
- CN112444256A CN112444256A CN201910798661.6A CN201910798661A CN112444256A CN 112444256 A CN112444256 A CN 112444256A CN 201910798661 A CN201910798661 A CN 201910798661A CN 112444256 A CN112444256 A CN 112444256A
- Authority
- CN
- China
- Prior art keywords
- road
- point
- vehicle
- time
- shortest path
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims 2
- 230000007797 corrosion Effects 0.000 claims 2
- 230000007547 defect Effects 0.000 abstract 1
- 238000007619 statistical method Methods 0.000 abstract 1
- 238000005530 etching Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for a time shortest path based on road traffic flow. The core of the path analysis is to solve for the best path and the shortest path. From the perspective of the network model, the best path solution is to find a path with the minimum obstruction strength between two nodes in the designated network. In the invention, for the defects of the traditional Floyd algorithm and Dijkstra algorithm, the Dijkstra algorithm is improved, a traffic flow statistical method based on computer vision is added, vehicles passing through a road port camera are firstly counted to obtain the number of the real-time vehicles on each road, then the road congestion weight is increased according to the number of the real-time vehicles on the road, the time length of a road network combined with congestion is calculated when the resistance value of each road section is set, and finally the time shortest path between two points is obtained through the Dijkstra algorithm.
Description
Technical Field
The invention relates to the technical fields of graph theory, geographic information, computer vision, pattern recognition and the like, in particular to a method for a time shortest path based on road vehicle flow.
Background
With the development of social economy and the improvement of urbanization level, urban traffic networks are increasingly complex, vehicles running on roads are gradually increased, the congestion condition of urban traffic tends to be serious, the life experience of people is seriously influenced by dense population and traffic congestion caused by a large amount of traffic flows, and great inconvenience is brought to urban travel. Therefore, how to reasonably plan the running route of urban trip, avoid the road with traffic congestion, realize the optimal path selection to improve the trip experience is needed to be considered in the road running planning.
At present, the problem of solving the optimal path mainly adopts a classic Dijkstra algorithm, and each path in a road network is given corresponding weight according to the length and width of the road, the road condition and other information, so as to solve the optimal weight path. However, this method can only give static weight to the road, and cannot model and depict the traffic flow changing in real time in the road. In the actual driving process, the change of the road traffic flow often has great influence on the driving time, and is a non-negligible factor.
Disclosure of Invention
The invention aims to provide a method for the time shortest path based on road traffic flow, which is better in route planning, saves time operation cost and is more suitable for actual scenes on the premise of accessibility of a target point when a traveler needs to consider the shortest time.
In order to solve the above object, the technical scheme adopted by the present invention is realized by the following steps, referring to fig. 1, the technical scheme is composed of the following four steps:
step 1, counting vehicles passing through a road port camera based on computer vision;
step 2, establishing a model of a traffic road network;
and 4, obtaining the shortest path through a Dijkstra shortest path algorithm based on the time length of the road.
The step 1 is realized by the following scheme:
(1) moving object detection
The moving object detection is a process for detecting a running vehicle, and mainly comprises the following steps:
1) inputting a test sequence;
2) constructing H, S, V an observation matrix with three components spread in rows and spread in columns;
3) establishing an RPCA model of the observation matrix, and solving;
4) h, S, V foreground parts of the three components are combined to obtain a foreground image;
5) shadow removal is carried out on the foreground image based on HSV color;
6) carrying out image binarization;
7) etching first of AB=Post-expansion AB=Performing an opening operation, firstly expanding AB=Post-etching AB=Performing a closed operation to effectively remove image noise;
(2) input of foreground images
Acquiring a well-processed foreground image for the result detected in the step (1);
(3) setting double virtual detection lines;
setting double virtual detection lines at the same position of the middle lower part of each frame of foreground image to form a virtual detection area;
(4) converting the vehicle information of the detection area into a one-dimensional function according to the following formula:
(5) correction of vehicle information
In order to eliminate false information in the detection area, the horizontal width of a high level and the distance between adjacent high levels are required to be judged to correct vehicle information;
(6) counting
The vehicle counting is mainly to compare the vehicle information of the double detection line areas of the continuous image frames and judge whether the vehicle passes through. According to the vehicle counting rule, when the vehicle exits the virtual detection area, the number of vehicles is increased by 1 if the vehicle is entering the road, and the number of vehicles is decreased by 1 if the vehicle is exiting the road. The recorded vehicle number is the real-time vehicle number of the road;
(7) in the same manner, the real-time vehicle number of other roads is acquired.
The step 2 is realized by the following scheme:
road network is generally abstracted as a "graph" in graph theory, and a road network model can be constructed as follows:
G(V, E, W)
wherein V represents a set of nodes; e represents an edge set, an<,>And<,>belong to different edges; w represents a set of weights, different criteria may be selected as weights, set first as the physical distance between two points,representing the physical distance between node i and node j. For an actual road network, traffic information in two directions of the same road segment is generally not the same, so that the actual road network is expressed using a directed graph, and a distance (travel time) in an undrawn direction in a one-way road can be set to a maximum value.
The step 3 is realized by the following scheme:
the congestion of a road is related to the setting time of the traffic lights at the exit of the road, and the factors to be considered for the setting time of the traffic lights mainly include the traffic flow, the road width and the like;
in the invention, the pedestrian flow is solved by means of an overpass, the width of main roads in a city is the same, and the influence of traffic light factors is not considered (namely the time spent on turning the roads is not considered), and the main considered factor is the traffic flow;
let us assume that when a vehicle travels on a city road without other vehicles, the road length is l, the maximum vehicle speed is v, and the time t = l/v required to pass through the road, 1 is added to the congestion of the road every time another vehicle is added to the road, and when there is no other vehicle on the road, the congestion of the road is 0. Thus, the time spent on the road is given by the following formula, wherein l represents the length of the road, v represents the maximum driving speed when no other vehicles exist, according to the regulations of the implementation of the road traffic safety laws of the people's republic of China, the road with only 1 motor lane in the same direction is provided, the urban road is 50 kilometers per hour, v =50km/h, k is a constant of 2, and Cong represents the congestion of the road, namely the number of vehicles on the current road:
t = l/v + k*Cong
according to this method, a time-weighted road network for each road in consideration of the traffic flow is obtained as shown in the following figure, in which the decimal is rounded.
The Dijkstra shortest path algorithm is implemented by the following scheme:
assuming that each point has a corresponding label: (,). Wherein,is the length of the shortest path from source point s to target point j;it is the point before point j in the shortest path from s to j. The basic process of solving the shortest path algorithm from the origin point s to the point j is implemented as follows:
(1) and (5) initializing. The origin point is set as: 1)=0,is empty; 2) All other points:=,is empty; 3) marking an origin point s, keeping k = s, and setting all other points as unmarked;
(2) checking the distance from all marked points k to their directly connected unmarked points j;
(4) Selecting the next point;
(5) selecting from all unmarked node sets MThe smallest one of i: selecting the point i as one point in the shortest path and setting the point i as marked;
(6) find a point before point i. Finding, from the marked points, a point j directly connected to point i as the previous point, setting: i = j;
(7) marking a point i;
(8) and whether all the points are marked or not, and if all the points are marked, exiting. If not, marking k = i, and returning to the step (2) to repeat the steps (2) - (8).
Drawings
FIG. 1 is a flow chart of the disclosed solution;
FIG. 2 is a vehicle statistical chart of an embodiment of the present invention;
FIG. 3 is a model diagram of a traffic network according to an embodiment of the present invention;
FIG. 4 is a time weight network according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are described below clearly and completely, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments that can be obtained by a person skilled in the art based on the embodiments of the present invention without any creative effort belong to the protection scope of the present invention.
Referring to fig. 2, the number of vehicles per road is shown, specifically by step 1.
Step 1: statistics of vehicles passing through road junction camera based on computer vision
(1) Moving object detection
The moving object detection is a process for detecting a running vehicle, and mainly comprises the following steps:
1) inputting a test sequence;
2) constructing H, S, V an observation matrix with three components spread in rows and spread in columns;
3) establishing an RPCA model of the observation matrix, and solving;
4) h, S, V foreground parts of the three components are combined to obtain a foreground image;
5) shadow removal is carried out on the foreground image based on HSV color;
6) carrying out image binarization;
7) etching first of AB=Post-expansion AB=Performing an opening operation, firstly expanding AB=Post-etching AB=And performing closed operation, thereby effectively removing image noise.
(2) Input of foreground images
Acquiring a well-processed foreground image for the result detected in the step (1);
(3) setting double virtual detection lines;
setting double virtual detection lines at the same position of the middle lower part of each frame of foreground image to form a virtual detection area;
(4) converting the vehicle information of the detection area into a one-dimensional function according to the following formula:
(5) correction of vehicle information
In order to eliminate false information in the detection area, the horizontal width of a high level and the distance between adjacent high levels are required to be judged to correct vehicle information;
(6) counting
The vehicle counting is mainly to compare the vehicle information of the double detection line areas of the continuous image frames and judge whether the vehicle passes through. According to the vehicle counting rule, when the vehicle exits the virtual detection area, the number of vehicles is increased by 1 if the vehicle is entering the road, and the number of vehicles is decreased by 1 if the vehicle is exiting the road. The recorded vehicle number is the real-time vehicle number of the road;
(7) in the same manner, the real-time vehicle number of the other roads is obtained, and the vehicle number on the road between the nodes 1 and 2 is 68.
Referring to fig. 3, the establishment of the traffic road map is realized through step 2;
step 2: model for building traffic road network
Road network is generally abstracted as a "graph" in graph theory, and a road network model can be constructed as follows:
G(V, E, W)
wherein V represents a set of nodes; e represents an edge set, an<,>And<,>belong to different edges; w represents a set of weights, different criteria may be selected as weights, set first as the physical distance between two points,representing the physical distance between node i and node j. For an actual road network, traffic information in two directions of the same road segment is not the same in general, and therefore, the actual road network is expressed using a directed graph, a distance in an undrawn direction (travel time) in a one-way road can be set to a maximum value,
referring to fig. 4, the time weighted road network for each road considering the traffic flow is embodied by step 3, in which the decimal is rounded.
And step 3: increasing the congestion weight of the road, and calculating the time length of the road by combining the congestion:
the congestion of a road is related to the setting time of the traffic lights at the exit of the road, and the factors to be considered for the setting time of the traffic lights mainly include the flow rate of people, the flow rate of vehicles, the width of the road and the like. In the invention, the pedestrian flow is supposed to be solved by means of an overpass, the width of main roads in a city is supposed to be the same, and the influence of traffic light factors is not considered (namely, the time spent on turning the roads is not considered), and the main considered factor is the traffic flow. Let us assume that when a vehicle travels on a city road without other vehicles, the road length is l, the maximum vehicle speed is v, and the time t = l/v required to pass through the road, 1 is added to the congestion of the road every time another vehicle is added to the road, and when there is no other vehicle on the road, the congestion of the road is 0. Thus, the time spent on the road is given by the following formula, wherein l represents the length of the road, v represents the maximum driving speed when no other vehicles exist, according to the regulations of the implementation of the road traffic safety laws of the people's republic of China, the road with only 1 motor lane in the same direction is provided, the urban road is 50 kilometers per hour, v =50km/h, k is a constant of 2, and Cong represents the congestion of the road, namely the number of vehicles on the current road:
t = l/v + k*Cong
and 4, step 4: obtaining the shortest path by Dijkstra shortest path algorithm based on the time length of the road
After the passing time lengths of all roads are obtained in the step 3, the shortest path is obtained through a Dijkstra shortest path algorithm; the basic idea of the Dijkstra algorithm is as follows: assuming that each point has a corresponding label: (,). Wherein,is the length of the shortest path from source point s to target point j;it is the point before point j in the shortest path from s to j. The basic process of solving the shortest path algorithm from the origin point s to the point j is implemented as follows:
(1) initializing; the origin point is set as: 1)=0,is empty; 2) all other points:=,is empty; 3) marking an origin point s, keeping k = s, and setting all other points as unmarked;
(2) checking the distance from all marked points k to their directly connected unmarked points j;
(4) Selecting the next point;
(5) selecting from all unmarked node sets MThe smallest one of i: selecting the point i as one point in the shortest path and setting the point i as marked;
(6) find a point before point i. Finding, from the marked points, a point j directly connected to point i as the previous point, setting: i = j;
(7) marking a point i;
(8) and whether all the points are marked or not, and if all the points are marked, exiting. If not, marking k = i, returning to the step (2), and repeating the steps (2) - (8);
finally, the shortest time path from the node 1 to the node 9 is obtained as follows: 1- > 2- > 3- > 6- > 9.
Claims (5)
1. The invention discloses a method for a time shortest path based on road traffic flow, which is characterized by comprising the following four steps:
step 1, counting vehicles passing through a road port camera based on computer vision;
step 2, establishing a model of a traffic road network;
step 3, increasing the congestion weight of the road, and calculating the time length of the road by combining the congestion;
and 4, obtaining the shortest path through a Dijkstra shortest path algorithm based on the time length of the road.
2. The method for shortest time path based on road traffic flow according to claim 1, wherein the step 1 is implemented by:
(1) moving object detection
The moving object detection is a process for detecting a running vehicle, and mainly comprises the following steps:
1) inputting a test sequence;
2) constructing H, S, V an observation matrix with three components spread in rows and spread in columns;
3) establishing an RPCA model of the observation matrix, and solving;
4) h, S, V foreground parts of the three components are combined to obtain a foreground image;
5) shadow removal is carried out on the foreground image based on HSV color;
6) carrying out image binarization;
7) carrying out opening operation after corrosion and expansion, and carrying out closing operation after expansion and corrosion, thereby effectively removing image noise;
(2) input of foreground images
Acquiring a well-processed foreground image for the result detected in the step (1);
(3) setting double virtual detection lines;
setting double virtual detection lines at the same position of the middle lower part of each frame of foreground image to form a virtual detection area;
(4) converting the vehicle information of the detection area into a one-dimensional function;
(5) correction of vehicle information
In order to eliminate false information in the detection area, the horizontal width of a high level and the distance between adjacent high levels are required to be judged to correct vehicle information;
(6) counting
The vehicle counting is mainly to compare the vehicle information of the double detection line areas of the continuous image frames and judge whether a vehicle passes through; according to the vehicle counting rule, when the vehicle exits from the virtual detection area, if the vehicle enters the road, the number of the vehicles is increased by 1, and if the vehicle exits from the road, the number of the vehicles is decreased by 1; the recorded vehicle number is the real-time vehicle number of the road;
(7) in the same manner, the real-time vehicle number of other roads is acquired.
3. The method of claim 1, wherein the traffic road network in step 2 is generally abstracted as "graph" in graph theory, and the actual road network is expressed by using a directed graph.
4. The method for shortest time path based on road traffic flow according to claim 1, wherein the step 3 is implemented by:
in the present invention, only traffic flow is considered; assuming that when a city road without other vehicles runs, the road length is l, the maximum vehicle speed is v, the time t = l/v required for passing through the road is t = l/v, when one other vehicle is added to the road, the congestion of the road is increased by 1, and when no other vehicle exists on the road, the congestion of the road is 0; thus, the time taken to travel on the road is expressed by the following equation:
t = l/v + k*Cong
wherein l represents the length of the road, v represents the maximum driving speed when no other vehicle exists, according to the regulations of the implementation of the road traffic safety laws of the people's republic of China, the road with only 1 motor lane in the same direction is provided, the urban road is 50 kilometers per hour, v =50km/h, k is a constant of 2, and Cong represents the congestion of the road;
a time-weighted road network for each road is determined taking into account the traffic flow, wherein the decimal is rounded.
5. The method of claim 1, wherein the Dijkstra shortest path algorithm is implemented by:
assuming that each point has a corresponding label: (, ) (ii) a Wherein,is the length of the shortest path from source point s to target point j;then it is the point before point j in the shortest path from s to j; the basic process of solving the shortest path algorithm from the origin point s to the point j is implemented as follows:
(1) initializing; the origin point is set as: 1)=0,is empty; 2) all other points:=,is empty; 3) marking an origin point s, keeping k = s, and setting all other points as unmarked;
(2) checking the distance from all marked points k to their directly connected unmarked points j;
(4) Selecting the next point;
(5) selecting from all unmarked node sets MThe smallest one of i: selecting the point i as one point in the shortest path and setting the point i as marked;
(6) finding a point before the point i; finding, from the marked points, a point j directly connected to point i as the previous point, setting: i = j;
(7) marking a point i;
(8) whether the points are all marked or not, and if so, quitting; if all the marks are not marked, the mark k = i, the process returns to the step (2), and the steps (2) - (8) are repeated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910798661.6A CN112444256A (en) | 2019-08-27 | 2019-08-27 | Method for time shortest path based on road traffic flow |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910798661.6A CN112444256A (en) | 2019-08-27 | 2019-08-27 | Method for time shortest path based on road traffic flow |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112444256A true CN112444256A (en) | 2021-03-05 |
Family
ID=74741812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910798661.6A Pending CN112444256A (en) | 2019-08-27 | 2019-08-27 | Method for time shortest path based on road traffic flow |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112444256A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113516429A (en) * | 2021-04-08 | 2021-10-19 | 华南理工大学 | Multi-AGV global planning method based on network congestion model |
CN115409256A (en) * | 2022-08-24 | 2022-11-29 | 吉林化工学院 | Route recommendation method for congestion area avoidance based on travel time prediction |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08292052A (en) * | 1995-04-20 | 1996-11-05 | Nissan Motor Co Ltd | Route guiding method for vehicle |
CN101930670A (en) * | 2010-08-12 | 2010-12-29 | 东南大学 | Method for predicting social vehicle running time on bus travel road section |
CN103236170A (en) * | 2013-04-15 | 2013-08-07 | 同济大学 | Novel dynamic-road-network-based traffic guidance method |
CN108648492A (en) * | 2018-06-26 | 2018-10-12 | 深兰科技(上海)有限公司 | A kind of method, apparatus, server and the readable storage medium storing program for executing of vehicle guiding |
-
2019
- 2019-08-27 CN CN201910798661.6A patent/CN112444256A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08292052A (en) * | 1995-04-20 | 1996-11-05 | Nissan Motor Co Ltd | Route guiding method for vehicle |
CN101930670A (en) * | 2010-08-12 | 2010-12-29 | 东南大学 | Method for predicting social vehicle running time on bus travel road section |
CN103236170A (en) * | 2013-04-15 | 2013-08-07 | 同济大学 | Novel dynamic-road-network-based traffic guidance method |
CN108648492A (en) * | 2018-06-26 | 2018-10-12 | 深兰科技(上海)有限公司 | A kind of method, apparatus, server and the readable storage medium storing program for executing of vehicle guiding |
Non-Patent Citations (2)
Title |
---|
李陆浩: "面向无人驾驶汽车的车道级导航研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 10, pages 035 - 109 * |
黄霞: "基于视觉的交通车流量统计", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 03, pages 034 - 923 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113516429A (en) * | 2021-04-08 | 2021-10-19 | 华南理工大学 | Multi-AGV global planning method based on network congestion model |
CN113516429B (en) * | 2021-04-08 | 2024-03-29 | 华南理工大学 | Multi-AGV global planning method based on network congestion model |
CN115409256A (en) * | 2022-08-24 | 2022-11-29 | 吉林化工学院 | Route recommendation method for congestion area avoidance based on travel time prediction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101275841B (en) | Feature information collecting apparatus and feature information collecting method | |
Zhang et al. | Real-time traffic analysis using deep learning techniques and UAV based video | |
CN106781479B (en) | A method of highway operating status is obtained based on mobile phone signaling data in real time | |
CN109410577B (en) | Self-adaptive traffic control subarea division method based on space data mining | |
CN110111574B (en) | Urban traffic imbalance evaluation method based on flow tree analysis | |
CN111652912A (en) | Vehicle counting method and system, data processing equipment and intelligent shooting equipment | |
CN107784835A (en) | Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing | |
CN107644528A (en) | A kind of vehicle queue length detection method based on vehicle tracking | |
CN104613974B (en) | Navigation time acquisition methods, system, air navigation aid and device | |
CN105303831A (en) | Method for determining congestion state of highway based on communication data | |
CN107195180A (en) | A kind of traffic trip track extraction method and device based on the alert data of electricity | |
CN112444256A (en) | Method for time shortest path based on road traffic flow | |
CN106951829A (en) | A kind of notable method for checking object of video based on minimum spanning tree | |
CN107590999A (en) | A kind of traffic state judging method based on bayonet socket data | |
CN113807026A (en) | Passenger flow line optimization and dynamic guide signboard system in subway station and design method | |
KR101123967B1 (en) | Traffic congestion prediction system, prediction method and recording medium thereof | |
CN112418081A (en) | Method and system for air-ground joint rapid investigation of traffic accidents | |
CN114694370A (en) | Method, device, computing equipment and storage medium for displaying intersection traffic flow | |
CN115862331A (en) | Vehicle travel track reconstruction method considering bayonet network topological structure | |
CN106408575A (en) | Time-space image-based vehicle counting method applied to urban traffic scene | |
CN111161545A (en) | Intersection region traffic parameter statistical method based on video | |
CN108171992B (en) | Parallel highway vehicle speed calculation method based on mobile phone signaling big data | |
CN103605960A (en) | Traffic state identification method based on fusion of video images with different focal lengths | |
CN106289036B (en) | A kind of road width measurement method based on floating car data analysis | |
CN108847035B (en) | Traffic flow evaluation method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210305 |
|
RJ01 | Rejection of invention patent application after publication |