哈尔滨工业大学 仪器科学与工程学院,黑龙江 哈尔滨 150001
[ "张永雷(2001-),男,山东菏泽人,硕士研究生,2025年于哈尔滨工业大学获得硕士学位,主要从事视觉检测和智能图像处理方面的研究。E-mail: 23S101104@stu.hit.edu.cn" ]
[ "胡 涛(1976-),男,河南许昌人,副教授,硕士生导师,2001年、2006年于哈尔滨工业大学分别获得硕士和博士学位,主要从事图像处理和图像测量方面的算法研究。E-mail: hutao@hit.edu.cn" ]
收稿:2025-06-16,
修回:2025-07-20,
纸质出版:2025-10-10
移动端阅览
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.
ZHANG Yonglei,HU Tao,SHEN Liqun.Automatic alignment of container corner based on monocular vision[J].Optics and Precision Engineering,2025,33(19):3150-3161.
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. DOI: 10.37188/OPE.20253319.3150. CSTR: 32169.14.OPE.20253319.3150.
ZHANG Yonglei,HU Tao,SHEN Liqun.Automatic alignment of container corner based on monocular vision[J].Optics and Precision Engineering,2025,33(19):3150-3161. DOI: 10.37188/OPE.20253319.3150. CSTR: 32169.14.OPE.20253319.3150.
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。
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 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 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.
程国政 . 我国港口集装箱运输发展现状与趋势 [J]. 中国航务周刊 , 2024 ( 30 ): 45 - 47 .
CHENG G ZH . Present situation and trend of container transportation in China’s ports [J]. China Shipping Gazette , 2024 ( 30 ): 45 - 47 . (in Chinese)
南通润邦重机有限公司 , 无锡卡尔曼导航技术有限公司 . 一种结合GPS\INS的集装箱识别定位方法 : 201910905943.1 [P]. 2023-02-21 .
Nantong Runbang Heavy Machinery Co. , Ltd. , Wuxi Kalman Navigation Technology Co. , Ltd . A container identification and positioning method combined with GPS\INS : 201910905943.1 [P]. 2023-02-21 . (in Chinese)
ZHANG L G , ZHANG W , LI Y C , et al . Acquisition method of container lock pin model based on point cloud data [C]. 2022 China Automation Congress (CAC). 25-27,2022 , Xiamen, China. IEEE , 2022 : 490 - 494 . doi: 10.1109/cac57257.2022.10055924 http://dx.doi.org/10.1109/cac57257.2022.10055924
周涛 , 张祥祥 , 陆惠玲 , 等 . 基于LL-GG-LG Net的CT和PET医学图像融合 [J]. 光学 精密工程 , 2023 , 31 ( 20 ): 3050 - 3064 . doi: 10.37188/ope.20233120.3050 http://dx.doi.org/10.37188/ope.20233120.3050
ZHOU T , ZHANG X X , LU H L , et al . CT and PET medical image fusion based on LL-GG-LG Net [J]. Opt. Precision Eng. , 2023 , 31 ( 20 ): 3050 - 3064 . (in Chinese) . doi: 10.37188/ope.20233120.3050 http://dx.doi.org/10.37188/ope.20233120.3050
WANG L , ZHANG X Y , SONG Z Y , et al . Multi-modal 3D object detection in autonomous driving: a survey and taxonomy [J]. IEEE Transactions on Intelligent Vehicles , 2023 , 8 ( 7 ): 3781 - 3798 . doi: 10.1109/tiv.2023.3264658 http://dx.doi.org/10.1109/tiv.2023.3264658
蒋志豪 , 张美香 , 薛卫涛 , 等 . 面向点云分类和分割的形状自适应特征聚合网络 [J]. 光学 精密工程 , 2025 , 33 ( 5 ): 777 - 788 . doi: 10.37188/ope.20253305.0777 http://dx.doi.org/10.37188/ope.20253305.0777
JIANG ZH H , ZHANG M X , XUE W T , et al . Shape adaptive feature aggregation network for point cloud classification and segmentation [J]. Opt. Precision Eng. , 2025 , 33 ( 5 ): 777 - 788 . (in Chinese) . doi: 10.37188/ope.20253305.0777 http://dx.doi.org/10.37188/ope.20253305.0777
QI D L , HAN Y F , ZHOU Z Q , et al . Review of defect detection technology of power equipment based on video images [J]. Journal of Electronics & Information Technology , 2022 , 44 ( 11 ): 3709 - 3720 .
刘玉淇 , 吴一全 . 基于机器视觉的太阳能电池片缺陷检测算法综述 [J]. 光学 精密工程 , 2024 , 32 ( 6 ): 868 - 900 . doi: 10.37188/ope.20243206.0868 http://dx.doi.org/10.37188/ope.20243206.0868
LIU Y Q , WU Y Q . Review of defect detection algorithms for solar cells based on machine vision [J]. Opt. Precision Eng. , 2024 , 32 ( 6 ): 868 - 900 . (in Chinese) . doi: 10.37188/ope.20243206.0868 http://dx.doi.org/10.37188/ope.20243206.0868
WEI L , LEE E . Real-time container shape and range recognition for implementation of container auto-landing system [J]. Journal of Korea Multimedia Society , 2009 , 12 : 794 - 803 .
唐鑫 . 基于深度学习的吊具与集装箱视觉对位技术研究 [D]. 成都 : 西南交通大学 , 2022 .
TANG X . Research on Visual Alignment Technology of Spreader and Container Based on Deep Learning [D]. Chengdu : Southwest Jiaotong University , 2022 . (in Chinese)
ZHANG Y J , MI CH . A Fast Vision - based Algorithm for Automated Container Pose Measurement System [M]. The 8th International Conference on Advances in Construction Machinery and Vehicle Engineering . Singapore : Springer Nature Singapore , 2024 : 817 - 825 . doi: 10.1007/978-981-97-1876-4_64 http://dx.doi.org/10.1007/978-981-97-1876-4_64
李源鑫 , 郭忠峰 , 杨钧麟 . 基于轻量化YOLOv5s的集装箱锁孔识别算法 [J]. 计算机科学 , 2024 , 51 ( S1 ): 524 - 529 .
LI Y X , GUO ZH F , YANG J L . Container lock hole recognition algorithm based on lightweight YOLOv5s [J]. Computer Science , 2024 , 51 ( S1 ): 524 - 529 . (in Chinese)
XIE E Z , WANG W H , YU ZH D , et al ., SegFormer: simple and efficient design for semantic segmentation with transformers [C]. 2021 : 35th Annual Conference on Neural Information Processing Systems (NeurIPS). December 6 -14, 2021, Canada.
LIU S T , HUANG D , WANG Y H . Receptive Field Block Net for Accurate and Fast Object Detection [M]. Computer Vision-ECCV 2018. Cham : Springer International Publishing , 2018 : 404 - 419 . doi: 10.1007/978-3-030-01252-6_24 http://dx.doi.org/10.1007/978-3-030-01252-6_24
ZHANG Y Y , ZHANG M H , ZANG Y X , et al . Efficient video deblurring guided byMotion magnitude and Convolutional block attention module [C]. Artificial Intelligence in China. Singapore : Springer , 2024 : 259 - 267 . doi: 10.1007/978-981-99-7545-7_27 http://dx.doi.org/10.1007/978-981-99-7545-7_27
陈津平 , 吴晓亮 . 参考点共面条件下的稳健相机位姿估计方法 [J]. 激光与光电子学进展 , 2024 , 61 ( 4 ): 147 - 155 .
CHEN J P , WU X L . Robust camera pose estimation method under coplanar reference points condition [J]. Laser & Optoelectronics Progress , 2024 , 61 ( 4 ): 147 - 155 . (in Chinese)
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
