Obstacle recongnition method applied to automatic traveling device and automatic traveling device

Abstract

An obstacle recognition method applied to an automatic traveling device may include the steps of: obtaining an image of an environment in a traveling direction of an automatic traveling device; separating out a chrominance channel image and a luminance channel image based on the image; performing pre-processing and edge processing on the luminance channel image to obtain an edge image; performing histogram statistics on the chrominance channel image to obtain a number of pixels with a maximum color proportion within a preset chrominance interval range, denoted as max H; performing segmentation and contour processing on the chrominance channel image to obtain a chrominance segmentation threshold and a contour image; performing contour detection on the contour image to obtain a contour block; collecting statistics on feature values corresponding to the contour block in the edge image and the contour image; and comparing the max H and the feature values with preset obstacle recognition and determination conditions to obtain recognition results. The disclosure is also directed to a related automatic traveling device and readable storage medium.