用于深度相机的深度点云矫正方法、系统和深度相机
By using a depth point cloud correction method based on a depth camera, and employing a two-stage judgment process involving depth calculation, correction module, and abnormal point cloud detection module, accurate depth point cloud data is generated. This solves the problem of point cloud data error caused by multipath interference from depth cameras and improves the correction effect.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG SUNNY INTELLIGENT OPTICAL TECH CO LTD
- Filing Date
- 2021-12-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing depth cameras are susceptible to multipath interference and other factors during measurement, resulting in errors in depth point cloud data, and existing correction methods are not ideal.
By acquiring source data from a depth camera, first and second depth point cloud data are generated using a depth calculation module and a depth correction module. An abnormal point cloud detection module performs secondary judgment based on absolute and relative differences to mark abnormal point cloud data. Finally, accurate depth point cloud data is generated through a depth fusion module.
It improves the accuracy of identifying abnormal point clouds and enhances the correction effect of depth point clouds, especially in the case of multipath interference, thereby improving the accuracy of depth point cloud data.
Smart Images
Figure CN116416169B_ABST