Obstacle avoidance of aerial vehicle based on monocular vision

Collision-free autonomous navigation is extremely important for quadcopter and other flying robots. The implementation of autonomic moving capabilities can contribute significantly to their promotion and usage in fields such as goods delivering, aerial photos shooting, and monitoring. In order to realize the autonomous flight without crash, the obstacle avoidance problem demands a prompt solution. Also, with the concern of cost and endurance, using only single camera to perform this task would be a better choice for low-cost flying robots. Thus, this paper focuses on achieving quadcopter's collision avoidance in unknown stable (rarely changes, such as high sky or inner room) environment only by single camera. The algorithm proposed by this paper is composed of PTAM (Parallel Tracking and Mapping), DTAM (Dense Tracking and Mapping in Real-Time) algorithm and CNN (Convolutional Neural Network). PTAM is used to create the 3D map of the environment. DTAM is used to obtain the depth map of those image frames. And the CNN is used to train and get a model used for automatically avoidance. Finally, this algorithm is proved to be valid by an experiment.