Research on Visual Navigation Marker Detection Algorithm Based on Multi-Constraints
- Resource Type
- Conference
- Authors
- Li, Huaijian; Wan, Linlin; Chen, Hong; Du, Xiaojing
- Source
- 2021 IEEE International Conference on Unmanned Systems (ICUS) Unmanned Systems (ICUS), 2020 3rd International Conference on. :80-84 Oct, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Robotics and Control Systems
Location awareness
Visualization
Costs
Navigation
Error analysis
Face recognition
Conferences
Multi-constraints
Marker Detection
Visual Navigation
Coplanar Feature Points
Circle Detection
- Language
An algorithm for detecting markers in monocular vision navigation was designed. Circular patterns feature good geometric characteristics and are easy to measure when their attitude changes. Therefore, a topological marker of the coplanar feature points is designed to assist the numbering and localization of circular patterns. A multi-constraint detection process is constructed to improve the efficiency of detection in complex background, and to ensure the processing speed and accuracy of the extraction of circle centers. Experimental results show that the algorithm is accurate even in a distant range.