Obstacle avoidance based on a monocular camera is still a challenging task because of the deficiency of 3D information for a monocular camera of the quadrotor. In this paper, we present an obstacle avoidance system for quadrotor based on monocular vision and depth estimation. The training data derives from the flight video of the front camera. Based on the depth map, we represent the obstacles in an expansion space, and then apply our motion planning algorithm to avoid the collisions. Real-world experiments verify its high-performance.
Obstacle Avoidance of Monocular Quadrotors with Depth Estimation
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 313 ; 3194-3203
2022-03-18
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
OBSTACLE AVOIDANCE USING A MONOCULAR CAMERA
TIBKAT | 2021
|Obstacle Avoidance Using a Monocular Camera
AIAA | 2021
|Realtime depth estimation and obstacle detection from monocular video
Tema Archiv | 2006
|