车道线处理方法及装置

By combining vehicle visual perception and navigation map information, lane line detection is optimized, solving the problem of unstable detection results in multi-sensor fusion methods and achieving accuracy and stability of lane line detection in complex environments.

CN116895061BActive Publication Date: 2026-07-17ANHUI DEEPWAY TECHNOLOGY CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ANHUI DEEPWAY TECHNOLOGY CO LTD
Filing Date
2023-08-08
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing multi-sensor fusion methods are easily affected by factors such as lighting, missing/blurred ground markings, and over-reliance on high-precision maps in lane line detection, leading to unstable detection results.

Method used

By combining vehicle visual perception results and navigation map information, the system determines the current road scenario in which the vehicle is driving and optimizes lane lines based on the scenario, including extending, supplementing, matching, or deleting lane lines, to improve the stability of detection.

Benefits of technology

In situations where visual perception is flawed or there is insufficient reliance on high-precision maps, navigation map information can be used to supplement the detection, ensuring the accuracy and stability of lane line detection, reducing dependence on high-precision maps, and improving computational efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116895061B_ABST
    Figure CN116895061B_ABST
Patent Text Reader

Abstract

本申请公开了一种车道线处理方法及装置,所述方法包括:基于车辆视觉感知结果,得到至少包含车道和车道线的第一车道感知结果;通过导航地图,得到至少包含车道和车道线的第二车道感知结果;根据所述第一车道感知结果以及所述第二车道感知结果,判断车辆当前行驶的道路场景,所述道路场景至少包括如下之一:非路口场景、路口场景;根据车辆所在的车道以及所述车辆当前行驶的道路场景,优化所述车道中的车道线。通过本申请实现了道路场景的判断,并针对不同道路场景中的车道线进行优化,从而保证了车道线检测的结果稳定性。
Need to check novelty before this filing date? Find Prior Art