Power Line Recognition and Foreign Objects Detection Based on Image Processing

In order to improve the efficiency of power line inspection, this paper uses the power line image collected, through the method of image processing, to identify power lines and detect foreign bodies. First, the Canny operator is improved by using Otsu adaptive acquisition of double thresholds for edge extraction of power line images. Then an improved Hough transform is used to detect straight lines in edge images for improving the accuracy of power line detection. Furthermore, a local contour detection method without considering the relationship between power lines and foreign objects is proposed to extract foreign objects on power lines, which can realize decoupling of power line recognition and fault detection. Through the simulation test of the collected power lines, the accuracy of the proposed method for power line extraction and foreign objects detection in the image is verified.