Obstacles detection and depth estimation from monocular vision for inspection robot of high voltage transmission line

Abstract

Obstacles detection and distance estimation play an important role in vision navigation for inspection robot for high-voltage transmission lines which walks along the overhead ground wire. In view of images from inspection site, Harris corners matching is used to detect background motion caused by camera jitter to eliminate the motion through motion compensation and a method for selecting the effective matching point pairs is proposed in the paper. Then the frame difference image and binary image are processed together and complete moving objects are segment. On the basis of the obstacles detection an algorithm for distance estimation of them is put forward. The relation between the distance to be estimated and coordinate difference of both edges of the ground wire in image where the objects lie is obtained, so the distance can be acquired, by use of the pose of the camera relative to the wire, as well as the pin-hole imaging model. Experiments for distance estimation show that the method can achieve the estimation precision with less than 5% error within 500 cm, and it has many advantages such as easy implementation, fast processing speed, high estimation accuracy and robustness, etc.