光学精密工程2025，Vol.33Issue(19)：3150-3161,12.DOI:10.37188/OPE.20253319.3150
基于单目视觉的集装箱角件自动对位
Automatic alignment of container corner based on monocular vision
摘要
Abstract
To enhance the efficiency of container loading and unloading and realize automated operations,this study investigates monocular-vision-based automatic alignment between spreader and container,inte-grating deep learning and image-processing techniques.Monocular images of container hoisting conditions were analyzed with emphasis on the regional characteristics of corner components.To address the low pix-el proportion of corner regions in high-resolution images,a two-stage"coarse positioning-fine segmenta-tion"strategy was proposed.Based on the segmentation results,key feature points were detected,2D-3D point correspondences were established,and pose estimation was performed using the Levenberg-Mar-quardt algorithm.Validation was conducted on an AUBO-i10 manipulator alignment platform in laborato-ry settings.Experimental results demonstrate that the mean average precision(mAP)for detection of con-tainer corner components exceeds 95%in both laboratory and real-scene environments.Mean intersection-over-union(mIoU)for corner segmentation reached 98.15%and 93.89%,respectively-improvements of 1.24%and 1.64%over the baseline SegFormer-B0-while model computational cost was reduced by ap-proximately 23.2%.At a camera-to-corner distance of about 2 m,the aiming error of the alignment posi-tion was below 1.0 mm.Absolute translation errors on the X,Y,and Z axes were all below 5.0 mm,and absolute rotation error was below 0.5°.These results indicate that the proposed method achieves reli-able accuracy and satisfies the requirements for automatic alignment of single-angle components.关键词
单目视觉/集装箱/自动对位/目标识别/位姿估计Key words
monocular vision/containers/automatic alignment/target recognition/pose estimation分类
机械工程引用本文复制引用
张永雷,胡涛,申立群..基于单目视觉的集装箱角件自动对位[J].光学精密工程,2025,33(19):3150-3161,12.基金项目
航天联合基金资助项目(No.Y22144) （No.Y22144）
