基于图匹配的无人驾驶平板车与门机智能对位方法及系统
By using a graph matching-based method, 3D point cloud and 2D image data are fused and processed to identify and correct alignment errors, solving the problems of low efficiency and high safety risks in traditional alignment methods, and achieving high-precision alignment between unmanned flatbed trucks and gantry cranes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 广州南沙海港集装箱码头有限公司
- Filing Date
- 2026-03-11
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, the traditional manual driving or third-party-reliant unmanned flatbed truck and gantry crane alignment methods have problems such as low efficiency, high safety risks and poor alignment consistency, especially in the final stage where it is difficult to achieve high-precision and stable alignment.
A graph matching-based method is adopted to acquire 3D point cloud and 2D image data of the gantry crane and its surroundings through IGV, perform preprocessing and registration fusion, call the pre-stored standard feature map of the gantry crane for graph matching to obtain a first alignment point, and correct the preset reference point through the repair factor to achieve accurate alignment repair.
Without relying on third-party facilities and gantry crane position information, it significantly improves the stability and adjustability of alignment, reduces error amplification and collision risk, and improves alignment accuracy and efficiency.
Smart Images
Figure CN121810808B_ABST