A Fast Vision-Based Algorithm for Automated Container Pose Measurement System

Addressing the current issues of low accuracy in container positioning and posture recognition, as well as long response times during the port automation loading and unloading process, this paper designs a rapid container target recognition and measurement device and method for automated loading and unloading, thereby optimizing the acquisition of key parameters in automated loading and unloading operations. This method combines advanced convolutional neural networks and traditional image processing algorithms to achieve precise detection and tracking of container corner fittings. Furthermore, this paper proposes a high-speed response method for small target measurement, which integrates minimized deep learning network technology and fuzzy image morphology matching algorithms to enhance the accuracy and stability of corner fitting detection. Through experimental verification, this method effectively improves the speed of single detection and reduces the localization error of small targets.