Research on Compartment Positioning Algorithm for the Intelligent Sampling Control System

Abstract

This paper proposes a new algorithm to position the area of a truck’s compartment in images for the intelligent sampling control system. The goal is to identify a truck’s compartment and assure that some works are done inside it. For example, while a mechanical arm automatically snatches goods carried by a truck, we must ensure that the goods must be obtained inside the truck’s compartment. Firstly, the compartment image is acquired by the camera overhead. Secondly, the Canny operator is used to extract the edge of the image, because it is sensitive to the image texture features. Thirdly, the Canny edge image is transformed to the Hough transform space. The peak points in the Hough parameter space indicate the straight lines which may be the elements of the compartment. The straight lines which meet the conditions of the actual size of the compartment make up the area of the compartment. Finally, converting the image coordinate to the physical compartment coordinate. The experiment result shows that the algorithm is effective and the coordinate conversion error analysis indicates that the converting algorithm is workable.