Image Enhancement Method for Detection in Logistics Loading and Unloading Robots

Abstract

This paper presents a novel method in the field of robotic vision, specifically designed to operate effectively under various lighting conditions. We propose an Image Enhancement Method for parcel loading status recognition, which addresses the challenge of insufficient lighting inside freight trucks without requiring lighting adjustments. Our approach integrates GAN and YOLO v5 into an end-to-end structure, where the detection network’s outputs influence the training of the generative network. Unlike traditional methods that focus solely on enhancing low-light image visibility, our method is optimized to maximize detection accuracy. To demonstrate the superiority of our approach, we constructed a setup resembling a freight truck, collected a dataset under varying lighting conditions, and conducted extensive experiments. The latter sections of the paper review relevant studies on vision data control in computer vision, provide a detailed explanation of our method, describe the experimental setup and database acquisition process, and discuss the results and analyses. The conclusion is presented in Section 6.