基于点云的类级别物体姿态估计

doi:10.11959/j.issn.2096-6652.202227

智能科学与技术学报 ›› 2022, Vol. 4 ›› Issue (2): 246-254.doi: 10.11959/j.issn.2096-6652.202227

• 专题：自主智能体灵巧精准操作学习 • 上一篇下一篇

基于点云的类级别物体姿态估计

栗仁武¹^,², 张凌霄¹^,², 高林¹^,², 李淳芃¹^,², 蒋浩¹^,²

¹ 中国科学院计算技术研究所，北京 100190
² 中国科学院大学，北京 100049

出版日期:2022-06-15 发布日期:2022-06-01
作者简介:栗仁武（1998− ），男，中国科学院计算技术研究所、中国科学院大学硕士生，主要研究方向为点云处理和几何深度学习
张凌霄（1995− ），男，中国科学院计算技术研究所助理工程师，主要研究方向为计算机图形学和几何处理
高林（1987− ），男，博士，中国科学院计算技术研究所副研究员，主要研究方向为计算机图形学和几何处理
李淳芃（1980− ），男，博士，中国科学院计算技术研究所副研究员，主要研究方向为虚拟现实、人机交互和计算机图形学
蒋浩（1982− ），男，博士，中国科学院计算技术研究所副研究员，主要研究方向为群体行为模拟
基金资助:
科技创新2030—“新一代人工智能”重大项目(2018AAA0103002);中科院科技服务网络计划(KFJ-STS-QYZD-129)

Category-level object pose estimation from depth point cloud

Renwu LI¹^,², Lingxiao ZHANG¹^,², Lin GAO¹^,², Chunpeng LI¹^,², Hao JIANG¹^,²

¹ Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
² University of Chinese Academy of Sciences, Beijing 100049, China

Online:2022-06-15 Published:2022-06-01
Supported by:
The National Key Research and Development Program of China(2018AAA0103002);Science and Technology Service Network Initiative, CAS(KFJ-STS-QYZD-129)

摘要/Abstract

摘要：

针对类级别的物体姿态估计问题，提出一种仅将深度相机扫描的点云作为输入，在仅知道目标物体点云类别的情况下，准确估计目标物体三维位姿的方法。该方法不需要依赖大量的带标签的人工标注数据集，仅使用虚拟仿真技术模拟生产的数据，即可在真实数据集上取得较高的精度。该方法首先对输入点云进行背景噪声过滤，之后通过中心预测模块对点云做标准归一化，再使用基于对应类别模板点云变形的方法预测其标准坐标系坐标，最后通过最小二乘法获得目标物体的三维位姿。实验结果表明，该方法在真实数据上具有更好的泛化性能和更高的精度。

关键词: 姿态估计, 点云处理, 深度学习, 模式识别

Abstract:

Aiming at the problem of category-level object pose estimation, a method was proposed to accurately estimate the pose of the target object by only taking the point cloud scanned by the depth camera as the input, with knowing the category of input point cloud only.The method did not reply on a huge amount of labeled dataset, but used virtual data produced by simulation instead, which achieved better accuracy on real-world dataset.This method first filtered the background noise of the input point cloud.Then standardized the point cloud through the well-designed center prediction module.After that, the normalized object coordinate space would be estimated through a shape template deformation module.Finally, the pose would be obtained from least squares.Experiments on real-world dataset demonstrates that the method achieve higher accuracy and better generalization ability.

Key words: pose estimation, point cloud processing, deep learning, pattern recognition

中图分类号:

TP391

栗仁武, 张凌霄, 高林, 等. 基于点云的类级别物体姿态估计[J]. 智能科学与技术学报, 2022, 4(2): 246-254.

Renwu LI, Lingxiao ZHANG, Lin GAO, et al. Category-level object pose estimation from depth point cloud[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(2): 246-254.

图/表 4

图1

图2

图3

表1

本文方法与NOCS方法、SPD方法的姿态估计精度"

方法	3D₅₀	3D₇₅	5°2 cm	5°5 cm	10°2 cm	10°5 cm
NOCS	$78 . 0 %$	30.1%	7.2%	10.0%	13.8%	25.2%
SPD	70%	37.9%	11.2%	12.9%	32.2%	41.3%
本文方法	61.2%	$42 . 6 %$	$23 . 3 %$	$29 . 7 %$	$41 . 8 %$	$58 . 1 %$

表1

参考文献 32

[1]	HINTERSTOISSER S , HOLZER S , CAGNIART C ,et al. Multimodal templates for real-time detection of textureless objects in heavily cluttered scenes[C]// Proceedings of 2011 International Conference on Computer Vision.[S.l.:s.n.], 2011.
[2]	HINTERSTOISSER S , CAGNIART C , ILIC S ,et al. Gradient response maps for real-time detection of textureless objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(5): 876-888.
[3]	HINTERSTOISSER S , LEPETIT V , ILIC S ,et al. Model based training,detection and pose estimation of texture-less 3D objects in heavily cluttered scenes[C]// Proceedings of the Asian Conference on Computer Vision.[S.l.:s.n.], 2013.
[4]	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. Piscataway:IEEE Press, 2010: 998-1005.
[5]	CHOI C , CHRISTENSEN H I . 3D pose estimation of daily objects using an RGB-D camera[C]// Proceedings of 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway:IEEE Press, 2012: 3342-3349.
[6]	CHOI C , TREVOR A J B , CHRISTENSEN H I . RGB-D edge detection and edge-based registration[C]// Proceedings of 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway:IEEE Press, 2013: 1568-1575.
[7]	VIDAL J , LIN C Y , LLADó X , ,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.
[8]	GUO J W , XING X J , QUAN W Z ,et al. Efficient center voting for object detection and 6D pose estimation in 3D point cloud[J]. IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society, 2021,30: 5072-5084.
[9]	XIANG Y , SCHMIDT T , NARAYANAN V ,et al. PoseCNN:a convolutional neural network for 6D object pose estimation in cluttered scenes[C]// Proceedings of Robotics:Science and Systems XIV. Robotics:Science and Systems Foundation, 2018.
[10]	LI Y , WANG G , JI X Y ,et al. DeepIM:deep iterative matching for 6D pose estimation[J]. International Journal of Computer Vision, 2020,128(3): 657-678.
[11]	XU D F , ANGUELOV D , JAIN A . PointFusion:deep sensor fusion for 3D bounding box estimation[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 244-253.
[12]	WANG C , XU D F , ZHU Y K ,et al. DenseFusion:6D object pose estimation by iterative dense fusion[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2019: 3338-3347.
[13]	HE Y S , SUN W , HUANG H B ,et al. PVN3D:a deep point-wise 3D keypoints voting network for 6DoF pose estimation[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2020: 11629-11638.
[14]	HE Y S , HUANG H B , FAN H Q ,et al. FFB6D:a full flow bidirectional fusion network for 6D pose estimation[C]// Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2021: 3002-3012.
[15]	ARUN K S , HUANG T S , BLOSTEIN S D . Least-squares fitting of two 3-D point sets[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987,9(5): 698-700.
[16]	LEPETIT V , MORENO-NOGUER F , FUA P . EPnP:an accurate O(n)solution to the PnP problem[J]. International Journal of Computer Vision, 2008,81(2): 155-166.
[17]	BESL P J , MCKAY N D . Method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992,14(2): 239-256.
[18]	LABBé Y , CARPENTIER J , AUBRY M ,et al. CosyPose:consistent multi-view multi-object 6D pose estimation[J]. arXiv preprint,2020,arXiv:2008.08465.
[19]	PARK K , PATTEN T , VINCZE M . Pix2Pose:pixel-wise coordinate regression of objects for 6D pose estimation[C]// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE Press, 2019: 7667-7676.
[20]	LI Z G , WANG G , JI X Y . CDPN:coordinates-based disentangled pose network for real-time RGB-based 6-DoF object pose estimation[C]// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE Press, 2019: 7677-7686.
[21]	K?NIG R , DROST B . A hybrid approach for 6DoF pose estimation[J]. arXiv preprint,2020,arXiv:2011.05669.
[22]	HODA? T , BARáTH D , MATAS J . EPOS:estimating 6D pose of objects with symmetries[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2020: 11700-11709.
[23]	HAGELSKJ?R F , BUCH A G . PointVoteNet:accurate object detection and 6 DOF pose estimation in point clouds[C]// Proceedings of 2020 IEEE International Conference on Image Processing. Piscataway:IEEE Press, 2020: 2641-2645.
[24]	SUNDERMEYER M , DURNER M , PUANG E Y ,et al. Multi-path learning for object pose estimation across domains[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2020: 13913-13922.
[25]	SAHIN C , KIM T K . Category-level 6D object pose recovery in depth images[C]// Proceedings of the European Conference on Computer Vision. Cham:Springer, 2019.
[26]	WANG H , SRIDHAR S , HUANG J W ,et al. Normalized object coordinate space for category-level 6D object pose and size estimation[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2019: 2637-2646.
[27]	UMEYAMA S . Least-squares estimation of transformation parameters between two point patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991,13(4): 376-380.
[28]	FISCHLER M A , BOLLES R C . Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981,24(6): 381-395.
[29]	CHEN D S , LI J , WANG Z ,et al. Learning canonical shape space for category-level 6D object pose and size estimation[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2020: 11970-11979.
[30]	AN J , CHO S . Variational autoencoder based anomaly detection using reconstruction probability[J]. Special Lecture on IE, 2015,2(1): 1-18.
[31]	TIAN M , ANG M H , LEE G H . Shape prior deformation for categorical 6D object pose and size estimation[C]// Proceedings of the European Conference on Computer Vision. Cham:Springer, 2020: 530-546.
[32]	CHARLES R Q , HAO S , MO K C ,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. Piscataway:IEEE Press, 2017: 77-85.

基于点云的类级别物体姿态估计

Category-level object pose estimation from depth point cloud

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 32

相关文章 15

Metrics

推荐阅读 0

[1]	黄哲, 王永才, 李德英. 3D目标检测方法研究综述[J]. 智能科学与技术学报, 2023, 5(1): 7-31.
[2]	卢经纬, 程相, 王飞跃. 求解微分方程的人工智能与深度学习方法：现状及展望[J]. 智能科学与技术学报, 2022, 4(4): 461-476.
[3]	张俊, 许沛东, 陈思远, 高天露, 戴宇欣, 张科, 赵杭, 高杰迈, 白昱阳, 李金星, 张浩然, 李湘, 陈玖香. 物理-数据-知识混合驱动的人机混合增强智能系统管控方法[J]. 智能科学与技术学报, 2022, 4(4): 571-583.
[4]	陈妍, 罗雪琴, 梁伟, 谢永芳. 基于情感信息融合注意力机制的抑郁症识别[J]. 智能科学与技术学报, 2022, 4(4): 600-609.
[5]	段俊伟, 许林灿, 全渝娟, 陈龙, 陈俊龙. 基于图正则化的贝叶斯宽度学习系统[J]. 智能科学与技术学报, 2022, 4(1): 109-117.
[6]	李琳辉, 周彬, 任威威, 连静. 行人轨迹预测方法综述[J]. 智能科学与技术学报, 2021, 3(4): 399-411.
[7]	李颖, 陈龙, 黄钊宏, 孙杨, 蔡国榕. 基于多尺度卷积神经网络特征融合的植株叶片检测技术[J]. 智能科学与技术学报, 2021, 3(3): 304-311.
[8]	田庆, 胡蓉, 李佐勇, 蔡远征, 余兆钗. 基于SE-YOLOv5s的绝缘子检测[J]. 智能科学与技术学报, 2021, 3(3): 312-321.
[9]	刘文, 胡琨林, 李岩, 刘钊. 移动目标轨迹预测方法研究综述[J]. 智能科学与技术学报, 2021, 3(2): 149-160.
[10]	张阳, 胡月, 辛东嵘. 一种考虑时空关联的深度学习短时交通流预测方法[J]. 智能科学与技术学报, 2021, 3(2): 172-178.
[11]	刘栋军, 王宇涵, 凌文芬, 彭勇, 孔万增. 基于脑机协同智能的情绪识别[J]. 智能科学与技术学报, 2021, 3(1): 65-75.
[12]	赵亮, 谢志峰, 张坤鹏, 郑玉卿, 付园坤. 无线网络信号传输建模：一种区间二型模糊集成深度学习方法[J]. 智能科学与技术学报, 2020, 2(4): 401-411.
[13]	田思佳,顾强,胡蓉,李锐戈,何顶新. 一种基于深度学习的机械臂分拣方法[J]. 智能科学与技术学报, 2020, 2(3): 268-274.
[14]	王飞跃,曹东璞,魏庆来. 强化学习：迈向知行合一的智能机制与算法[J]. 智能科学与技术学报, 2020, 2(2): 101-106.
[15]	袁小锋,王雅琳,阳春华,桂卫华. 深度学习在流程工业过程数据建模中的应用[J]. 智能科学与技术学报, 2020, 2(2): 107-115.