YCbCr Color Space Based Image Segmentation Algorithm with Feedback in the Underground Cable Tunnel

In order to solve the problem that the image segmentation is affected by the intensity of illumination in the underground cable tunnel. An image segmentation algorithm with feedback based on YCbCr color space is proposed in this paper. Firstly, the color distribution characteristics of some equipment cables in the YCbCr color space is analyzed, and a threshold selection constraint for image segmentation is proposed. Oriented FAST and Rotated BRIEF (ORB) are used to feedback the matching results of the segmented images to achieve a fast feedback mechanism. Finally, the segmentation threshold is adjusted according to the feedback results, to improve the robustness of the image segmentation algorithm in the underground cable tunnel environment.