Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Vehicle-road cooperative abnormal driving condition detection method and system, terminal equipment and medium

A detection method and technology for driving conditions, applied in the field of monitoring, can solve the problems of reducing the accuracy of normal pattern extraction and abnormal event detection, and being unusable.

Active Publication Date: 2020-08-11
LANGFANG NORMAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The former automatically extracts road markings and detects abnormal driving events according to the vehicle's line contact, and cannot be used for road sections with unclear markings or no markings in actual engineering
The latter automatically clusters the normal trajectory patterns in traffic flow and then screens out abnormal events, which has higher flexibility and practicability, but the existing methods rigidly divide all trajectories including abnormal driving trajectories into The update of the pattern center in a certain pattern class greatly reduces the accuracy of normal pattern extraction and abnormal event detection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle-road cooperative abnormal driving condition detection method and system, terminal equipment and medium
  • Vehicle-road cooperative abnormal driving condition detection method and system, terminal equipment and medium
  • Vehicle-road cooperative abnormal driving condition detection method and system, terminal equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] like figure 1 As shown, Embodiment 1 of the present invention provides a method for detecting abnormal driving conditions of vehicle-road coordination, including the following steps:

[0068] S1. Determine the number k of normal driving trajectory patterns of the detected road section; for example, for a road section with one-way 3 lanes, the number k of normal driving trajectory patterns is equal to 3;

[0069] S2. Determine the initial value of the center line of each trajectory pattern based on the scene activity diagram, as the initial clustering center of each trajectory pattern;

[0070] The scene activity map, for example, can obtain a section of video on the detected road section; then extract each frame image in the video section, and perform inter-frame difference on adjacent video frame images to extract the moving vehicle in the video; The average value of all video frame differences can be used to obtain the vehicle flow line in the video, and each vehicl...

Embodiment 2

[0122] like Figure 5 The present embodiment shown provides a system for detecting abnormal driving conditions of vehicles and roads, including:

[0123] Acquisition module 10 is configured to collect and detect the vehicle video of road section; Perform temporary observation tasks by changing parameters such as focal length and depression angle offline; in this solution, it does not depend on the parameter settings of the camera, no matter how the parameters of the camera change, it can be detected by acquiring new tracks;

[0124] Trajectory extraction module 20, extracts vehicle driving trajectory information from vehicle video;

[0125] Calculation module 30, configured for the detection method according to embodiment 1:

[0126] Determine the initial value of the center line of each trajectory mode based on the scene activity diagram, as the initial clustering center of each trajectory mode;

[0127] Based on the rough K-means clustering method and the extracted vehicl...

Embodiment 3

[0132] The present application also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the method for detecting abnormal traces as shown in the first embodiment above is realized. step.

[0133] like Image 6 As shown: the terminal device includes a central processing unit (CPU) 801, which can execute various appropriate action and processing. In RAM803, various programs and data necessary for system operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804 .

[0134] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 808 including a ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a vehicle-road cooperative abnormal driving condition detection method and system, terminal equipment and a medium. The method comprises the steps of determining a normal driving trajectory mode class number of a detection road section; determining an initial value of a center line of each trajectory mode based on a scene activity diagram; obtaining a newly added trajectoryset; determining upper and lower approximate set affiliation of the newly added trajectory; based on a rough K-means clustering method, performing incremental learning on the trajectory modes by usingthe newly added trajectory set until the center line of each trajectory mode has no obvious change; carrying out anomaly confirmation and classification on each suspected abnormal trajectory stored in the rough set boundary region of each trajectory mode class by adopting a KNN classifier; and triggering an alarm and outputting the type of the event and the information of the vehicle running abnormally after the abnormal running trajectory is confirmed. According to the method, the adverse effect of the suspected abnormal trajectory on the normal trajectory mode extraction precision is effectively eliminated, and the event detection and classification performance is effectively enhanced.

Description

technical field [0001] The invention relates to the technical field of monitoring, in particular to a method, a system, a terminal device and a medium for detecting abnormal driving conditions of vehicle-road coordination. Background technique [0002] Abnormal driving events such as cross-lane driving, illegal driving on the emergency lane / shoulder, and retrograde traffic seriously affect road traffic safety. Based on advanced technical means, the estimation of the state of vehicles and roads on the monitored road section and the effective detection of abnormal driving events can not only provide support for violation detection, but also provide support for the rationality evaluation and optimization of road and facility design. In recent years, video-based automatic detection of abnormal driving events has been extensively studied. Among them, the method of manually setting a virtual detection line or detection area is simple and efficient, and is suitable for a fixed-par...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G08G1/01G06K9/62
CPCG08G1/0125G08G1/0129G08G1/0137G06F18/23213G06F18/24
Inventor 张玲娟任建强王宁冯越
Owner LANGFANG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com