Obstacle avoidance for small UAVs using monocular vision

Abstract

PurposeThe purpose of this paper is to propose that the three‐dimensional information of obstacles should be identified to allow unmanned aerial vehicles (UAVs) to detect and avoid obstacles existing in their flight path.Design/methodology/approachFirst, the approximate outline of obstacles was detected using multi‐scale‐oriented patches (MOPS). At the same time, the spatial coordinates of feature points that exist in the internal outline of the obstacles were calculated through the scale‐invariant feature transform (SIFT) algorithm. Finally, the results from MOPS and the results from the SIFT algorithm were merged to show the three‐dimensional information of the obstacles.FindingsAs the method proposed in this paper reconstructs only the approximate outline of obstacles, a quick calculation can be done. Moreover, as the outline information is combined through SIFT feature points, detailed three‐dimensional information pertaining to the obstacles can be obtained.Practical implicationsThe proposed approach can be used efficiently in GPS‐denied environments such as certain indoor environments.Originality/valueFor the autonomous flight of small UAVs having a payload limit, this paper suggests a means of forming three‐dimensional information about obstacles with images obtained from a monocular camera.