Vision Based Obstacle Recognition Approach of a Power Line Inspection Robot

Abstract

This paper introduces the research and application situations of the power transmission line inspection robot. It describes the architecture of two–arm rotary mechanism robot and the configuration of control system. The emphasis of this paper is placed on the algorithm of object recognition for those structure-restrained obstacles such as suspending clamps, counterweights, insulators and so on. The experiments of laboratory tests and field applications show that the proposed image recognition approach can achieve accurate results with less memory and computation cost.