Research on Extraction Method of Navigation Line of Substation Wheeled Inspection Robot Based on Machine Vision

Aiming at the problem of different roads for intelligent inspection robots in substations, a navigation line extraction method suitable for three types of road conditions is proposed. First, extract the region of interest from the acquired image, perform grayscale processing and median filter denoising. Use Otsu method to binarize the denoised image, and morphological processing is used to reduce the noise of the image twice. In order to effectively filter out false edges and extract edge features better, an improved Canny edge detection algorithm is proposed. The algorithm uses the horizontal, vertical, 45 degrees and 135 degrees gradient templates to calculate the image gradient; At the same time, the interpolation method in non-maximum suppression is improved, and Otsu method is used to determine the high and low thresholds of the image. The algorithm optimizes the Canny edge extraction effect, and finally uses a line fitting algorithm to extract the navigation line.