Lane line processing method, device, electronic device and storage medium
By using deep learning models to identify and cluster the vector data of lane lines, the problem of lane line fragmentation in complex road scenes is solved, and the integrity and continuity of lane lines are extracted.
CN114943946BActive Publication Date: 2025-09-23QIANXUN SPATIAL INTELLIGENCE INC
Patent Information
- Application Number
- CN202110183844.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-02-10
- Publication Date
- 2025-09-23
- Estimated Expiration
- 2041-02-10
Smart Images

Figure CN114943946B_ABST
Abstract
The present disclosure discloses a lane line processing method, device, electronic device, and storage medium. The lane line processing method includes: identifying the characteristic vectors of lane lines in a road surface image and extracting the center lines of the characteristic vectors to obtain a vector line dataset of the center lines of the lane lines; using any vector line in the vector line dataset as a reference vector line, and obtaining the adjacent vector lines of the reference vector line based on the adjacent topological relationship of the plane where the reference vector line is located; constructing the adjacent vector lines of each vector line in the vector dataset into an adjacent topological relationship matrix, wherein the adjacent topological relationship includes a left-right direction relationship and / or a front-back direction relationship; when the adjacent vector lines of multiple reference vector lines in the adjacent topological relationship matrix are the same in the same adjacent direction, the multiple reference vector lines are connected. This method connects fragmented lane lines into more practical lane lines, ensuring the integrity of the lane lines.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Method and device for constructing lane-level topology based on structured road
CN110749329A