Ground Stereo Vision-based Navigation for Autonomous Take-off and Landing of UAVs: A Chan-Vese Model Approach

• Main Authors: Tang, Dengqing, Hu, Tianjiang, Shen, Lincheng, Zhang, Daibing, Kong, Weiwei, Low, Kin Huat
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2016
• Subjects: UAV; Localization
• Online Access: https://hdl.handle.net/10356/84706; http://hdl.handle.net/10220/41954
• Institution: Nanyang Technological University

This article aims at flying target detection and localization of a fixed-wing unmanned aerial vehicle (UAV) autonomous take-off and landing within Global Navigation Satellite System (GNSS)-denied environments. A Chan-Vese model–based approach is proposed and developed for ground stereo vision detection. Extended Kalman Filter (EKF) is fused into state estimation to reduce the localization inaccuracy caused by measurement errors of object detection and Pan-Tilt unit (PTU) attitudes. Furthermore, the region-of-interest (ROI) setting up is conducted to improve the real-time capability. The present work contributes to real-time, accurate and robust features, compared with our previous works. Both offline and online experimental results validate the effectiveness and better performances of the proposed method against the traditional triangulation-based localization algorithm.