Obstacle avoidance with optic flow

[摘要] ENGLISH ABSTRACT: In order to determine the potential of using optical flow as an instrument forquadcopter navigation, a real-time depth estimation system was created. Thesystem was programmed in Python and made use of: FAST algorithm to detectkey points, Lucas-Kanade pyramid algorithm to calculate the optical flow,different geometrical relationships to calculate depth from translation and Eulerangles to negate the effects of rotation. A simulated testing environment created inthe Unity game engine was used to successfully test the overall performance,accuracy and robustness of the system. The positive results from the system andcomponent tests proved that there is potential in using optical flow in quadcopternavigation.

[发布机构] Stellenbosch University