Vision based 3D obstacle detection
using a single camera for robots/UAVs
Vision based 3D obstacle detection using a single camera for robots/UAVs
Shah, Syed Irtiza Ali
Johnson, Eric N.
This thesis aims at detecting obstacles using a single camera in an unknown 3D world for 3D motion of the robot/UAV. Obstacle detection is a pre-requisite for collision-free motion of robots/UAVs. Most of the research in this area has been for 2D motion of the ground robots and with active sensors e.g Laser range finders, Ultrasonic sensors, SONAR, RADAR etc. The passive camera based research has mostly been done either using triangulation/stereo vision (using more than one camera), or, developing an expectation map pre-hand, of the world and comparing it with the new image data. In contrast, this thesis, aims at finding solution of the problem using just a single camera in a perfectly unknown world. This requirement is based on the fact that at least a single camera would be carried by almost all robots/UAVs anyway in foreseeable future. Hence the attempt is to use the same camera for obstacle detection and avoidance task as well, so as to come up with a low cost and light weight solution, in order to facilitate building miniature robots/UAVs.