A method for detecting remaining vehicles on a highway section

By constructing vehicle trajectory data and road network topology for highway sections and dynamically optimizing the road network topology, the problem of accuracy in vehicle detection under complex road networks was solved, and efficient vehicle screening under dynamically changing conditions was achieved.

CN121725633BActive Publication Date: 2026-06-19ZHEJIANG ZHIJIANG INTELLIGENT TRANSPORTATION TECH CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG ZHIJIANG INTELLIGENT TRANSPORTATION TECH CO LTD
Filing Date
2026-02-25
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing methods for detecting vehicles remaining on highways are insufficient to accurately detect vehicle presence when the road network is dynamically changing, and cannot meet the requirements of dynamic changes in complex road networks.

Method used

By acquiring multi-source vehicle traffic data and integrating them using vehicle identifiers, vehicle trajectory data is constructed, and candidate road network topologies are built. Abnormal road segments and events are identified, the road network topology is dynamically optimized, and candidate retained, missed, and accident-stuck vehicles are selected.

Benefits of technology

In complex road networks and situations involving changes in road network structure, it can accurately screen out vehicles that remain, thus improving the accuracy of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121725633B_ABST
    Figure CN121725633B_ABST
Patent Text Reader

Abstract

This application provides a method for detecting vehicles remaining on highway sections, relating to the field of data processing technology. The method includes: acquiring multi-source vehicle traffic data in a target spatiotemporal scenario; fusing the multi-source vehicle traffic data using vehicle identifiers to obtain vehicle trajectory data; constructing a candidate road network topology based on the vehicle trajectory data; identifying abnormal road segments and abnormal events in the candidate road network topology; optimizing the candidate road network topology based on the identification results to obtain a local road network topology; selecting a target detection time window based on the detection time; determining candidate remaining vehicles, missed detection vehicles, and accident-damaged vehicles on the road segment to be detected within the target detection time window; and determining the final remaining vehicles based on the candidate remaining vehicles, missed detection vehicles, and accident-damaged vehicles. By adopting the above method for detecting vehicles remaining on highway sections, the road network topology can be dynamically updated, and remaining vehicles can be detected under the updated road network topology, thus improving the accuracy of vehicle detection on highway sections.
Need to check novelty before this filing date? Find Prior Art