【摘要】 为了提高集装箱装卸效率，实现装卸自动化，基于单目视觉，结合深度学习和图像处理算法，提出了一种吊具与集装箱的自动对位技术。以单目相机拍摄的集装箱吊装工况图像为研究对象，分析角件区域特征。针对角件在高分辨率图像中像素占比低的问题，提出“粗定位-精分割”的处理方法。然后，基于分割结果检测关键特征点，构建2D-3D点对，通过L-M算法完成位姿估计。最后，在实验室AUBO-i10机械臂对位平台上开展自动对位实验，验证所提算法的有效性。实验结果表明，在实验室环境和真实场景下，集装箱角件的检测精度mAP值均达到95%以上，角件分割精度mIoU值分别达到98.15%和93.89%，相比原模型SegFormer-B0分别提高1.24%和1.64%，模型计算量下降约23.2%；在相机距离集装箱角件2 m左右的情况下，对位位置瞄准误差小于1.0 mm，在X,Y,Z 3个轴上自动对位的对位平移绝对误差小于5.0 mm，旋转绝对误差小于0.5°。结果证明，本文所提算法精度可靠，满足单角件自动对位需求。更多还原

【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, integrating 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 pixel proportion of corner regions in high-resolution images, a two-stage "coarse positioning-fine segmentation" 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-Marquardt algorithm. Validation was conducted on an AUBO-i10 manipulator alignment platform in laboratory settings. Experimental results demonstrate that the mean average precision(mAP) for detection of container corner components exceeds 95% in both laboratory and real-scene environments. Mean intersectionover-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 approximately 23. 2%. At a camera-to-corner distance of about 2 m, the aiming error of the alignment position 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 reliable accuracy and satisfies the requirements for automatic alignment of single-angle components.更多还原