CN111598069A - Highway vehicle lane change area analysis method based on deep learning - Google Patents
Highway vehicle lane change area analysis method based on deep learning Download PDFInfo
- Publication number
- CN111598069A CN111598069A CN202010729116.4A CN202010729116A CN111598069A CN 111598069 A CN111598069 A CN 111598069A CN 202010729116 A CN202010729116 A CN 202010729116A CN 111598069 A CN111598069 A CN 111598069A
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- lane change
- area
- deep learning
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a highway vehicle lane change area analysis method based on deep learning, which comprises the steps of firstly carrying out structural modeling on lanes and lane lines of a road; simultaneously detecting the outer frame of the vehicle in the high-definition monitoring video of the highway; tracking the vehicle track in the video according to the detection result of the vehicle in each frame of image; combining the vehicle track with the road structured data, identifying the vehicle lane change according to the lane area where the vehicle passes, and detecting the vehicle lane change position according to the intersection position of the vehicle frame and the lane line; and finally, carrying out clustering analysis on the lane changing positions of the vehicles passing through in different time periods to obtain the lane changing hot spot areas of the vehicles on the expressway in different time periods. The method has the advantages of simple steps and accurate result, detects the lane changing behavior of the vehicle and analyzes the lane changing area by using the camera data in the expressway, and provides powerful support for the fine traffic management and lane design of the expressway.
Description
Technical Field
The invention relates to the field of driving behavior detection, in particular to a highway vehicle lane change area analysis method based on deep learning.
Background
With the rapid development of economic society, the demand of people on transportation and travel is continuously increased, especially the demand of long-distance travel. According to statistics, the number of the domestic automobiles at the end of 2019 is 26150 thousands, and 2122 thousands of automobiles are added compared with the number of the domestic automobiles at the end of the last year. The conflict between the increase in traffic demand and the existing road conditions is increasingly prominent. Highways are used as the main artery of traffic between cities, and the traffic pressure of the highways is increasing. Reasonable traffic management can effectively reduce the occurrence of traffic jam. In order to improve the traffic management level, the driving behavior of vehicles on the expressway needs to be accurately analyzed.
Lane changing of vehicles on a highway is the most common driving behavior, and lane changing refers to driving behavior of vehicles on a road to change lanes as required. The reasonable lane change on the expressway can improve the speed of the whole traffic flow, relieve traffic pressure and improve road traffic capacity, but the instability of the traffic flow can be increased by the frequent lane change and the unreasonable lane change, and the traffic danger is increased. In recent years, lane changing of vehicles has become an important cause of traffic accidents, and people have to pay attention to safety problems. Therefore, in order to ensure driving safety and fully and reasonably utilize road resources of the expressway, the lane changing behavior of vehicles on the expressway needs to be detected and analyzed.
The existing research is analyzed, the data collected by the highway at present mainly comprises traffic flow, vehicle speed, lane occupancy and the like, the data are macroscopic state data of traffic, and more microscopic traffic data are needed in traffic fine management. The lane change information is the very important microscopic traffic data. In conventional vehicle lane change detection, vehicle lane change parameters are typically acquired using onboard GPS positioning data. The method is limited by the positioning precision of the GPS, and simultaneously, not all vehicles carry the GPS, which causes the inaccuracy and incompleteness of the detection of the lane changing behavior of the highway vehicles, thereby providing the analysis method of the lane changing area of the highway vehicles based on deep learning.
Disclosure of Invention
In order to solve the problems, the invention provides a method for analyzing a lane change area of a highway vehicle based on deep learning, and aims to detect the lane change behavior of the vehicle based on the deep learning method by adopting cameras widely distributed on the highway and analyze based on a detection result so as to provide support for refined traffic management and lane design. To achieve the purpose, the invention provides a highway vehicle lane change area analysis method based on deep learning, which comprises the following steps:
(1) extracting a road background according to a monitoring video of the expressway, and dividing lane areas according to lanes and lane lines in the road background to obtain road structured data;
(2) detecting the vehicle in each frame of image of the monitoring video by adopting a target detection model based on deep learning to obtain the outer frame of the vehicle;
(3) tracking the vehicle track in the monitoring video according to the detection result of the vehicle in each frame of image;
(4) combining the vehicle track with the road structured data, identifying the vehicle lane change according to the lane area where the vehicle passes, and detecting the vehicle lane change position according to the intersection position of the outer frame of the vehicle and the lane line;
(5) and carrying out clustering analysis on the lane changing positions of the vehicles passing through in different time periods to obtain the lane changing hot spot areas of the vehicles on the expressway in different time periods.
As a further improvement of the present invention, the step (1) comprises the following substeps:
(1.1) for the monitoring video on the expressway, selecting continuous T frame video pictures, superposing and summing the collected pictures, and then solving an average value as a road background, wherein the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,Pthe picture is a background picture of the road,I i is as followsiThe number of frames of a picture is,Tis a continuous frame number;
(1.2) loading a road background, drawing a road lane line and lane areas on the road background, calculating the minimum external rectangles of all the lane areas as the lane areas, and storing all the result data in a json format to obtain road structured data;
as a further improvement of the invention, the step (2) comprises the following steps:
the step (2) comprises the following substeps:
(2.1) cutting out a lane area image from the video frame image according to the lane area obtained in the step (1);
and (2.2) inputting the lane area image into a trained target detection model based on deep learning, calculating and outputting the outer frame of the vehicle in the picture, wherein the target detection model is EfficientDet, and training by using the manually marked vehicle detection frame data.
As a further improvement of the invention, in the step (3), the vehicle track in the monitoring video is tracked by adopting an SORT method.
As a further improvement of the present invention, the step (4) includes the following substeps:
(4.1) newly establishing a variable D = { key, value }, and recording the lane number of the vehicle, wherein key is the vehicle number, and value is the lane number;
(4.2) traversing all vehicles according to the track result of each frame of picture, calculating the lane number of the vehicle, and analyzing according to the lane number and the vehicle number:
if the lane number does not exist, directly analyzing the next vehicle;
if the vehicle number is not in the key of the variable D, adding the vehicle number and the lane number where the current vehicle is located into the variable D;
and if the vehicle number is already in the key of the variable D, further judging whether the lane number is changed: if the lane number is not changed, directly analyzing the next vehicle, and if the lane number is changed, considering that lane change occurs;
and (4.3) for the vehicle with the lane change, performing intersection calculation by using the edge of the lower edge of the outer frame of the vehicle and the lane line to obtain intersection point coordinates on the lane line, and taking the point as a lane change position point.
As a further improvement of the present invention, in the step (4.2), the lane number where the vehicle is located is calculated by the following specific method:
using trisection points A and B of the lower edge of an outer frame of the vehicle as judgment points of a lane where the vehicle is located, and judging whether the point A and the point B are in a polygon of a lane area by adopting a ray method; if both A and B are in the same lane area, the vehicle is considered to be in the lane.
As a further improvement of the present invention, said step (5) comprises the sub-steps of:
(5.1) dividing each lane line into N equal parts, selecting lane change position data of vehicles in a time period of t1-t2, and counting lane change times in equal segments of each lane;
(5.2) smoothing the number of conversion passes in each lane equal segment by using Gaussian filtering;
and (5.3) constructing a three-dimensional analysis space of the lane change region by using three elements of time, lane change position and lane change number, and performing visual analysis on the lane change region.
Compared with the prior art, the method for analyzing the lane change area of the highway vehicles based on deep learning has the following technical effects:
(1) the invention applies the efficient and accurate target detection method in the deep learning field to the detection of vehicles on the expressway, and simultaneously adopts a lightweight front-end interaction means to model the road lane line and the lane area, thereby greatly improving the convenience and the accuracy of vehicle lane change detection by combining the two methods, reducing the use of other sensors such as a GPS and the like, and belonging to the interdisciplinary application of the deep learning algorithm in the intelligent traffic field.
(2) By carrying out cluster analysis on lane change positions, the method can obtain the hot spot areas of the lane change of the vehicles on the expressway in different time periods, solve the problem that the lane change of the vehicles is difficult to analyze in the traditional method, and provide data support for refined traffic management.
Drawings
FIG. 1 is a general flow diagram of the process of the present invention;
FIG. 2 is a drawing showing the frames of a video frame;
FIG. 3 is a road background view;
FIG. 4 is a plot of lane lines and lane areas;
fig. 5 is a diagram showing a result of vehicle detection.
Detailed Description
The invention is described in further detail below with reference to the following figures and embodiments:
the invention provides a method for analyzing a lane change area of a highway vehicle based on deep learning, which aims to detect the lane change behavior of the vehicle by adopting cameras widely distributed on the highway based on the deep learning method, and simultaneously analyze based on a detection result so as to provide support for refined traffic management and lane design.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As an embodiment, a surveillance video on a certain highway is selected as a data source, and fig. 2 is a picture of 9 consecutive frames in the video.
As shown in fig. 1, a method for analyzing a lane change area of a highway vehicle based on deep learning includes the following steps:
(1) for the high-definition monitoring video on the expressway, extracting a road background, and performing structured modeling on lanes and lane lines of the road by using front-end interaction, namely dividing lane areas; the method specifically comprises the following substeps:
(1.1) for the monitored video frames, continuous 100 frames of video frames are selected, and preferably, no vehicle exists in the continuous 100 frames of video frames. The collected pictures are superposed and summed, then an average value is obtained as a road background, and the obtained result is shown in fig. 3, wherein the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,Pthe picture is a background picture of the road,I i is as followsiThe number of frames of a picture is,Tfor the number of consecutive frames, 100 is taken in this example.
(1.2) loading a road background picture on a front page, drawing a road lane line and a lane area on the road background picture, wherein the drawing result is shown in figure 4, meanwhile, calculating the minimum external rectangles of all the lane areas as the lane areas, and storing all the result data in a json format.
(2) The method comprises the following steps of detecting vehicles in each frame of image of a high-definition monitoring video of the expressway by adopting a target detection model based on deep learning, and acquiring an outer frame (Bounding box) of the vehicles, wherein the method comprises the following substeps:
(2.1) cutting out an image of the lane area from the video frame image according to the lane area obtained in the step (1.2) so as to reduce the calculation amount of target detection and the data amount of data transmission;
(2.2) inputting the lane area image into a vehicle detection model based on EfficientDet, and outputting the outer frame of the vehicle in the picture after calculation, wherein the vehicle detection model is trained in advance by using manually marked vehicle detection frame data, the model can provide a calling interface for the outside in an API (application programming interface) mode, and the detection result is shown in FIG. 5; the vehicle detection model is not limited to the EfficientDet, and models such as SSD, Yolo, Faster RCNN and the like can be adopted.
(3) And tracking the vehicle track in the video by using an SORT method according to the detection result of the vehicle in each frame of image, wherein the SORT method mainly comprises the steps of acquiring an adjacency matrix, simply matching, Hungary matching, updating the state and the like. Further, Deep SORT and the like can be used.
(4) The method combines the vehicle track with the road structured data, identifies the vehicle lane change according to the lane area where the vehicle passes, and detects the vehicle lane change position according to the intersection position of the outer frame of the vehicle and the lane line, and comprises the following substeps:
(4.1) creating a variable D = { key, value } with the type as a dictionary, and recording the lane number where the vehicle is located, wherein the key is the vehicle number and is obtained by the vehicle detection time number in the step (2), and the value is the lane number;
(4.2) traversing all vehicles according to the track result of each frame of picture, calculating the lane number of the vehicle, analyzing according to the lane number and the vehicle number, directly analyzing the next vehicle if the lane number does not exist, adding the vehicle number and the lane number where the current vehicle is located into a variable D if the vehicle number is not in the key of the variable D, and further judging whether the lane number is changed if the vehicle number is in the key of the variable D: and if the lane number is not changed, directly analyzing the next vehicle, and if the lane number is changed, considering that lane change occurs. The lane number calculation of the vehicle can adopt the following method: using trisection points A and B of the lower edge of an outer frame of the vehicle as judgment points of a lane where the vehicle is located, judging whether the point A and the point B are in a polygon of a lane area by adopting a ray method, namely making a horizontal ray from the point, if an odd number of intersection points exist in the polygon of the lane area, the point A and the point B are in the lane area, otherwise, the point A and the point B are not in the lane area, and if the point A and the point B are in the same lane area, the vehicle is considered to be in the lane.
And (4.3) for the vehicle with the lane change, performing intersection calculation by using the edge of the lower edge of the outer frame of the vehicle and the lane line to obtain intersection point coordinates on the lane line, and taking the point as a lane change position point.
(5) Clustering analysis is carried out on the lane changing positions of the vehicles passing through in different time periods to obtain highway vehicle lane changing hot spot areas in different time periods, and the method comprises the following substeps:
(5.1) dividing each lane line into N equal parts, selecting vehicle lane change position data in a time period t1-t2, and counting lane change times in each lane equal section. For example, each lane line is divided into 10 equal parts, and a time slot 8 is selected: calculating lane change position data of vehicles between 00 and 10:00, counting the number of lane change in each lane equal segment in every 10 minutes, and obtaining the results of lane change statistics between lanes 1 and 2 as shown in table 1;
TABLE 1 statistical table of the number of passes
(5.2) smoothing the number of conversion passes in each lane equal segment by using Gaussian filtering, wherein the formula is as follows:
where x is a random variable (in this embodiment, the index of the position of the gaussian kernel), μ is the expected value of the gaussian distribution, and σ is the standard deviation of the gaussian distribution.
Selecting 1 x 3 Gaussian kernels in the smoothing, wherein mu is 0, sigma is 0.8, the obtained Gaussian kernels are [0.239,0.522 and 0.239], and the result of statistical smoothing of lane change of lane lines before lanes 1 and 2 is shown in table 2;
TABLE 2 statistics Gaussian smoothing Table for number of passes
And (5.3) constructing a three-dimensional analysis space of the lane change area by using three elements of time, lane line position of lane change and lane change number, and carrying out visual analysis on the lane change area, so that the lane change area is more visual.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made according to the technical spirit of the present invention are within the scope of the present invention as claimed.
Claims (7)
1. A highway vehicle lane change area analysis method based on deep learning is characterized by comprising the following specific steps:
(1) extracting a road background according to a monitoring video of the expressway, and dividing lane areas according to lanes and lane lines in the road background to obtain road structured data;
(2) detecting the vehicle in each frame of image of the monitoring video by adopting a target detection model based on deep learning to obtain the outer frame of the vehicle;
(3) tracking the vehicle track in the monitoring video according to the detection result of the vehicle in each frame of image;
(4) combining the vehicle track with the road structured data, identifying the vehicle lane change according to the lane area where the vehicle passes, and detecting the vehicle lane change position according to the intersection position of the outer frame of the vehicle and the lane line;
(5) and carrying out clustering analysis on the lane changing positions of the vehicles passing through in different time periods to obtain the lane changing hot spot areas of the vehicles on the expressway in different time periods.
2. The method for analyzing the lane change area of the highway vehicle based on the deep learning of claim 1, wherein the method comprises the following steps: the step (1) comprises the following substeps:
(1.1) for the monitoring video on the expressway, selecting continuous T frame video pictures, superposing and summing the collected pictures, and then solving an average value as a road background, wherein the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,Pthe picture is a background picture of the road,I i is as followsiThe number of frames of a picture is,Tis a continuous frame number;
and (1.2) loading a road background, drawing a road lane line and lane areas on the road background, and calculating the minimum circumscribed rectangle of all the lane areas as the lane areas.
3. The method for analyzing the lane change area of the highway vehicle based on the deep learning of claim 1, wherein the method comprises the following steps: the step (2) comprises the following substeps:
(2.1) cutting out a lane area image from the video frame image according to the lane area obtained in the step (1);
and (2.2) inputting the lane area image into a trained target detection model based on deep learning, calculating and outputting the outer frame of the vehicle in the picture, wherein the target detection model is EfficientDet, and training by using the manually marked vehicle detection frame data.
4. The method for analyzing the lane change area of the highway vehicle based on the deep learning of claim 1, wherein the method comprises the following steps: in the step (3), the vehicle track in the monitoring video is tracked by adopting an SORT method.
5. The method for analyzing the lane change area of the highway vehicle based on the deep learning of claim 1, wherein the method comprises the following steps: the step (4) comprises the following substeps:
(4.1) newly establishing a variable D = { key, value }, and recording the lane number of the vehicle, wherein key is the vehicle number, and value is the lane number;
(4.2) traversing all vehicles according to the track result of each frame of picture, calculating the lane number of the vehicle, and analyzing according to the lane number and the vehicle number:
if the lane number does not exist, directly analyzing the next vehicle;
if the vehicle number is not in the key of the variable D, adding the vehicle number and the lane number where the current vehicle is located into the variable D;
and if the vehicle number is already in the key of the variable D, further judging whether the lane number is changed: if the lane number is not changed, directly analyzing the next vehicle, and if the lane number is changed, considering that lane change occurs;
and (4.3) for the vehicle with the lane change, performing intersection calculation by using the edge of the lower edge of the outer frame of the vehicle and the lane line to obtain intersection point coordinates on the lane line, and taking the point as a lane change position point.
6. The method for analyzing the lane change area of the highway vehicle based on the deep learning of claim 1, wherein the method comprises the following steps: in the step (4.2), the lane number where the vehicle is located is calculated, and the specific method is as follows:
using trisection points A and B of the lower edge of an outer frame of the vehicle as judgment points of a lane where the vehicle is located, and judging whether the point A and the point B are in a polygon of a lane area by adopting a ray method; if both A and B are in the same lane area, the vehicle is considered to be in the lane.
7. The method for analyzing the lane change area of the highway vehicle based on the deep learning of claim 1, wherein the method comprises the following steps: the step (5) comprises the following substeps:
(5.1) dividing each lane line into N equal parts, selecting lane change position data of vehicles in a time period of t1-t2, and counting lane change times in equal segments of each lane;
(5.2) smoothing the number of conversion passes in each lane equal segment by using Gaussian filtering;
and (5.3) constructing a three-dimensional analysis space of the lane change region by using three elements of time, lane change position and lane change number, and performing visual analysis on the lane change region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010729116.4A CN111598069B (en) | 2020-07-27 | 2020-07-27 | Highway vehicle lane change area analysis method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010729116.4A CN111598069B (en) | 2020-07-27 | 2020-07-27 | Highway vehicle lane change area analysis method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598069A true CN111598069A (en) | 2020-08-28 |
| CN111598069B CN111598069B (en) | 2020-11-06 |
Family
ID=72186756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010729116.4A Active CN111598069B (en) | 2020-07-27 | 2020-07-27 | Highway vehicle lane change area analysis method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598069B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112092815A (en) * | 2020-09-02 | 2020-12-18 | 北京航空航天大学 | Vehicle track changing tracking control method based on model prediction |
| CN113128382A (en) * | 2021-04-06 | 2021-07-16 | 青岛以萨数据技术有限公司 | Method and system for detecting lane line at traffic intersection |
| CN113469075A (en) * | 2021-07-07 | 2021-10-01 | 上海商汤智能科技有限公司 | Method, device and equipment for determining traffic flow index and storage medium |
| CN116110230A (en) * | 2022-11-02 | 2023-05-12 | 东北林业大学 | Vehicle lane crossing line identification method and system based on vehicle-mounted camera |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014180986A (en) * | 2013-03-21 | 2014-09-29 | Toyota Motor Corp | Lane change assist system |
| CN106981202A (en) * | 2017-05-22 | 2017-07-25 | 中原智慧城市设计研究院有限公司 | A kind of vehicle based on track model lane change detection method back and forth |
| CN107146415A (en) * | 2017-07-05 | 2017-09-08 | 廊坊师范学院 | A kind of traffic incidents detection and localization method |
| CN110136447A (en) * | 2019-05-23 | 2019-08-16 | 杭州诚道科技股份有限公司 | Lane change of driving a vehicle detects and method for distinguishing is known in illegal lane change |
-
2020
- 2020-07-27 CN CN202010729116.4A patent/CN111598069B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014180986A (en) * | 2013-03-21 | 2014-09-29 | Toyota Motor Corp | Lane change assist system |
| CN106981202A (en) * | 2017-05-22 | 2017-07-25 | 中原智慧城市设计研究院有限公司 | A kind of vehicle based on track model lane change detection method back and forth |
| CN107146415A (en) * | 2017-07-05 | 2017-09-08 | 廊坊师范学院 | A kind of traffic incidents detection and localization method |
| CN110136447A (en) * | 2019-05-23 | 2019-08-16 | 杭州诚道科技股份有限公司 | Lane change of driving a vehicle detects and method for distinguishing is known in illegal lane change |
Non-Patent Citations (2)
| Title |
|---|
| 万子健 等: "车辆轨迹数据提取道路交叉口特征的决策树模型", 《测绘学报》 * |
| 史颖 等: "基于视频检测的车辆变道轨迹识别方法研究", 《交通科技与经济》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112092815A (en) * | 2020-09-02 | 2020-12-18 | 北京航空航天大学 | Vehicle track changing tracking control method based on model prediction |
| CN113128382A (en) * | 2021-04-06 | 2021-07-16 | 青岛以萨数据技术有限公司 | Method and system for detecting lane line at traffic intersection |
| CN113469075A (en) * | 2021-07-07 | 2021-10-01 | 上海商汤智能科技有限公司 | Method, device and equipment for determining traffic flow index and storage medium |
| CN116110230A (en) * | 2022-11-02 | 2023-05-12 | 东北林业大学 | Vehicle lane crossing line identification method and system based on vehicle-mounted camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598069B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111598069B (en) | Highway vehicle lane change area analysis method based on deep learning | |
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| CN109410577B (en) | Self-adaptive traffic control subarea division method based on space data mining | |
| KR102124955B1 (en) | Method and server for identifying the cause of traffic congestion using visual analytics | |
| CN103116987B (en) | Traffic flow statistic and violation detection method based on surveillance video processing | |
| CN111554105B (en) | Intelligent traffic identification and statistics method for complex traffic intersection | |
| CN109615862A (en) | Road vehicle movement of traffic state parameter dynamic acquisition method and device | |
| CN103235933A (en) | Vehicle abnormal behavior detection method based on Hidden Markov Model | |
| CN107067781B (en) | GIS road black spot map generation method for advanced driving assistance system application | |
| CN104978567A (en) | Vehicle detection method based on scenario classification | |
| CN103198300B (en) | Parking event detection method based on double layers of backgrounds | |
| CN102867415B (en) | Video detection technology-based road jam judgement method | |
| CN102902983B (en) | A kind of taxi identification method based on support vector machine | |
| Cai et al. | Applying machine learning and google street view to explore effects of drivers’ visual environment on traffic safety | |
| CN110443142B (en) | Deep learning vehicle counting method based on road surface extraction and segmentation | |
| Kim et al. | Visual extensions and anomaly detection in the pNEUMA experiment with a swarm of drones | |
| CN111986235A (en) | Method for extracting vehicle track characteristic motion mode | |
| Mijić et al. | Traffic sign detection using yolov3 | |
| Zhang et al. | Vehicle detection in UAV aerial images based on improved YOLOv3 | |
| CN113516853A (en) | Multi-lane traffic flow detection method for complex monitoring scene | |
| CN111145551A (en) | Intersection traffic planning system based on CNN detection follows chapter rate | |
| Noh et al. | SafetyCube: Framework for potential pedestrian risk analysis using multi-dimensional OLAP | |
| CN114820931B (en) | Virtual reality-based CIM (common information model) visual real-time imaging method for smart city | |
| CN115690787A (en) | Semantic segmentation method, image processing apparatus, and computer-readable storage medium | |
| CN109063675B (en) | Traffic density calculation method, system, terminal and computer readable storage medium |
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 |