The obstacle recognition approach for a power line inspection robot

The obstacles measurement and recognition from the complex background is the first step for a power transmission line inspection robot to negotiate obstacles autonomously with high reliability. This paper introduces the research and application situations of the inspection robot and analyses the features of the typical obstacles in the real power line. The configuration of control system of the inspection robot is described. The emphasis of this paper is placed on the algorithm of obstacle recognition for those structure-restrained obstacles. Approaches based on straight line, circle and ellipse extraction are used to recognize the typical obstacles-counterweights, insulators, suspending clamps and so on. The experiment results achieved in both laboratory tests and field applications show the high accurate and efficient result of this approach.