位置确定方法、系统及装置
By fusing camera and radar data and using a preset transformation matrix to convert camera pixel coordinates to radar coordinates, the problem of a single sensor being unable to determine the spatial position of a target vehicle is solved, thus achieving more accurate autonomous driving perception.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JINGWEI HIRAIN TECH CO INC
- Filing Date
- 2023-06-01
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, using a single sensor is insufficient to meet the comprehensiveness and accuracy requirements of autonomous driving systems. Furthermore, when radar space is projected onto the camera plane, the spatial coordinates of the target vehicle are lost, making it impossible to determine the spatial position of the target vehicle by fusing camera and radar data.
By fusing camera and radar data, a preset transformation matrix is used to convert the pixel coordinates collected by the camera to the radar coordinate system. Combined with radar point cloud data, the spatial position of the target vehicle is determined, including the conversion of the pixel coordinates of the center point of the target vehicle's bounding box and key points into spatial coordinates.
It achieves unified data from cameras and radar, accurately determines the spatial location of target vehicles, and improves the robustness and accuracy of the perception module of the autonomous driving system.
Smart Images
Figure CN116758154B_ABST