Research on Container Door Handle Recognition Algorithm Based on Machine Vision

With the development of automated docks, intelligent vision systems for containers have begun to be widely used. This article proposes an automatic positioning and identification method for container door handles to assist the automation and intelligence of large-scale engineering machinery in ports. The method utilizes the saturation feature in the visual image and the relative position relationship of the door parts to quickly and effectively locate the position of the door handle area. Then, the closed door handle is identified and located by statistical analysis and histogram projection. The experimental results show that the method of this paper has excellent recognition rate in the positioning and identification of container door handles, and the detection time is short, meeting the realtime requirements of port automation.