Abnormal driving behavior identification method, device, equipment and medium

By synchronizing roadside sensors and integrating information, abnormal driving behaviors in the autonomous driving environment are identified, and the problems of low detection data accuracy and poor identification accuracy in the prior art are solved, thereby achieving higher data accuracy and 24/7 applicability.

CN114670852BActive Publication Date: 2025-03-25GOSUNCN TECH GRP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202210192029.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-28
Publication Date
2025-03-25
Estimated Expiration
2042-02-28

AI Technical Summary

Technical Problem

During the process of autonomous driving, the prior art has problems such as low accuracy of detection data, missing use and poor accuracy of identification of abnormal driving behaviors.

Method used

By synchronizing time and space between roadside lidar, roadside millimeter-wave radar and roadside cameras, the corresponding radar information and video information are obtained, and the fusion algorithm is adapted to the fusion algorithm, the information of the target operation status is obtained, and abnormal driving behavior is finally identified.

Benefits of technology

It improves the dimension and confidence of the data, enhances the ability to be applicable all-weather, improves the accuracy of target operating status information and the accuracy of abnormal driving behavior recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114670852B_ABST
    Figure CN114670852B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for identifying abnormal driving behavior, including: performing time synchronization and space synchronization on a roadside laser radar, a roadside millimeter-wave radar, and a roadside camera; after completing time synchronization and space synchronization, obtaining first radar information from the roadside laser radar, obtaining second radar information from the roadside millimeter-wave radar, and obtaining video information from the roadside camera; according to an adaptive fusion algorithm for environmental information, using an adaptive fusion algorithm to perform fusion operations on the first radar information, the second radar information, and the video information to obtain target object operation status information; identifying abnormal driving behavior in the target object according to the target object operation status information. The present invention makes the data dimension richer and the data confidence higher through fusion, and is applicable to different fusion algorithms all day long, thereby improving the accuracy of target object operation status information and the accuracy of identifying abnormal driving behavior.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Expressway pre-warning system and method based on radar detection

    CN108510797A

  • V2I-based intelligent networked auxiliary perception streetlamp system for autonomous vehicles

    CN110208787A

  • Unmanned driving sensing method based on all-weather environment monitoring system

    CN112147615A