基于深度学习的物体点云六维位姿估计方法

doi:10.19678/j.issn.1000-3428.0058768

摘要/Abstract

摘要： 物体位姿估计是机器人在散乱环境中实现三维物体拾取的关键技术，然而目前多数用于物体位姿估计的深度学习方法严重依赖场景的RGB信息，从而限制了其应用范围。提出基于深度学习的六维位姿估计方法，在物理仿真环境下生成针对工业零件的数据集，将三维点云映射到二维平面生成深度特征图和法线特征图，并使用特征融合网络对散乱场景中的工业零件进行六维位姿估计。在仿真数据集和真实数据集上的实验结果表明，该方法相比传统点云位姿估计方法准确率更高、计算时间更短，且对于疏密程度不一致的点云以及噪声均具有更强的鲁棒性。

关键词: 点云, 位姿估计, 特征融合, 深度学习, 损失函数

Abstract: Object pose estimation is a key technology required for enabling the robots to pick 3D objects in a cluttered environment. However, most of the existing deep learning methods for pose estimation rely heavily on the RGB information of the scene, which limits their applications. To address the problem, a deep learning-based method for 6D object pose estimation is proposed. A data set for industrial parts is generated from physical simulation, and then the 3D point cloud is mapped to the 2D plane to generate a deep feature map and normal feature map. On this basis, a feature fusion network is used for 6D pose estimation of industrial parts in cluttered environments. Experimental results on the simulation data set and the real data set show that the proposed method improves the accuracy of pose estimation and reduces time consumption compared with traditional point cloud pose estimation methods. In addition, the method displays high robustness to the point clouds with different density and noises.

Key words: point cloud, pose estimation, feature fusion, deep learning, loss function

中图分类号:

TP391

李少飞, 史泽林, 庄春刚. 基于深度学习的物体点云六维位姿估计方法[J]. 计算机工程, 2021, 47(8): 216-223.

LI Shaofei, SHI Zelin, ZHUANG Chungang. Deep Learning-Based 6D Object Pose Estimation Method from Point Clouds[J]. Computer Engineering, 2021, 47(8): 216-223.

http://www.ecice06.com/CN/Y2021/V47/I8/216

图/表 13

20210819201040

20210819201044

20210819201048

20210819201053

20210819201057

20210819201101

20210819201105

20210819201110

20210819201114

20210819201118

20210819201122

20210819201127

20210819201131

参考文献

[1] TEKIN B, SINHA S N, FUA P.Real-time seamless single shot 6D object pose prediction[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:292-301.
[2] ZAKHAROV S, SHUGUROV I, ILIC S.DPOD:6D pose object detector and refiner[C]//Proceedings of 2019 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:1941-1950.
[3] LI Z, WANG G, JI X.CDPN:coordinates-based disentangled pose network for real-time RGB-based 6-DoF object pose estimation[C]//Proceedings of 2019 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:7678-7687.
[4] KEHL W, MANHARDT F, TOMBARI F, et al. SSD-6D:making RGB-based 3D detection and 6D pose estimation great again[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:1521-1529.
[5] RAD M, LEPETIT V.BB8:a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:3828-3836.
[6] PENG S, LIU Y, HUANG Q, et al. PVNet:pixel-wise voting network for 6DoF pose estimation[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:4561-4570.
[7] SUNDERMEYER M, MARTON Z C, DURNER M, et al. Implicit 3D orientation learning for 6D object detection from RGB images[C]//Proceedings of 2018 European Conference on Computer Vision.New York, USA:ACM Press, 2018:699-715.
[8] 朱建新, 沈东羽, 吴钪.基于激光点云的智能挖掘机目标识别[J]. 计算机工程, 2017, 43(1): 297-302. ZHU J X, SHEN D Y, WU K.Target recognition for intelligent excavator based on laser point cloud[J]. Computer Engineering, 2017, 43(1): 297-302.(in Chinese)
[9] KRULL A, BRACHMANN E, MICHEL F, et al. Learning analysis-by-synthesis for 6D pose estimation in RGB-D images[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:954-962.
[10] MICHEL F, KIRILLOV A, BRACHMANN E, et al. Global hypothesis generation for 6D object pose estimation[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:462-471.
[11] WOHLHART P, LEPETIT V.Learning descriptors for object recognition and 3D pose estimation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:3109-3118.
[12] KEHL W, MILLETARI F, TOMBARI F, et al. Deep learning of local RGB-D patches for 3D object detection and 6D pose estimation[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:205-220.
[13] WANG C, XU D, ZHU Y, et al. Dense fusion:6D object pose estimation by iterative dense fusion[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:3343-3352.
[14] DROST B, ULRICH M, NAVAB N, et al. Model globally, match locally:efficient and robust 3D object recognition[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2010:998-1005.
[15] JOEL V, CHYI-YEU L, XAVIER L, et al. A method for 6D pose estimation of free-form rigid objects using point pair features on range data[J]. Sensors, 2018, 18(8): 2678-2682.
[16] 龚学健.基于RealSense的散乱零件三维目标识别[D]. 哈尔滨:哈尔滨工业大学, 2018. GONG X J.3D object recognition of scattered parts based on realsense[D]. Harbin:Harbin Institute of Technology, 2018.(in Chinese)
[17] QI C R, SU H, MO K, et al. PointNet:deep learning on point sets for 3D classification and segmentation[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:652-660.
[18] 罗元, 王薄宇, 陈旭.基于深度学习的目标检测技术的研究综述[J]. 半导体光电, 2020, 41(1): 1-10. LUO Y, WANG B Y, CHEN X.Research progresses of target detection technology based on deep learning[J]. Semiconductor Optoelectronics, 2020, 41(1): 1-10.(in Chinese)
[19] QI C R, LIU W, WU C, et al. Frustum PointNets for 3D object detection from RGB-D data[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:918-927.
[20] DYRSTAD J S, BAKKEN M, GROTLI E I, et al. Bin picking of reflective steel parts using a dual-resolution convolutional neural network trained in a simulated environment[C]//Proceedings of 2018 IEEE International Conference on Robotics and Biomimetics.Washington D.C., USA:IEEE Press, 2018:530-537.
[21] MITASH C, BEKRIS K E, BOULARIAS A.A self-supervised learning system for object detection using physics simulation and multi-view pose estimation[C]//Proceedings of 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems.Washington D.C., USA:IEEE Press, 2017:545-551.
[22] WANG X, LIU S, SHEN X, et al. Associatively segmenting instances and semantics in point clouds[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:4096-4105.

选择文件类型/文献管理软件名称

选择包含的内容