Efficient 3D Object Recognition from Cluttered Point Cloud

Recognizing 3D objects and estimating their postures in a complex scene is a challenging task. Sample Consensus Initial Alignment (SAC-IA) is a commonly used point cloud-based method to achieve such a goal. However, its efficiency is low, and it cannot be applied in real-time applications. This paper analyzes the most time-consuming part of the SAC-IA algorithm: sample generation and evaluation. We propose two improvements to increase efficiency. In the initial aligning stage, instead of sampling the key points, the correspondence pairs between model and scene key points are generated in advance and chosen in each iteration, which reduces the redundant correspondence search operations; a geometric filter is proposed to prevent the invalid samples to the evaluation process, which is the most time-consuming operation because it requires transforming and calculating the distance between two point clouds. The introduction of the geometric filter can significantly increase the sample quality and reduce the required sample numbers. Experiments are performed on our own datasets captured by Kinect v2 Camera and on Bologna 1 dataset. The results show that the proposed method can significantly increase (10–30×) the efficiency of the original SAC-IA method without sacrificing accuracy.

[1]  Jiri Matas,et al.  Matching with PROSAC - progressive sample consensus , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Jan-Michael Frahm,et al.  USAC: A Universal Framework for Random Sample Consensus , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Mohammed Bennamoun,et al.  A Comprehensive Performance Evaluation of 3D Local Feature Descriptors , 2015, International Journal of Computer Vision.

[4]  Nico Blodow,et al.  Aligning point cloud views using persistent feature histograms , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Federico Tombari,et al.  Unique Signatures of Histograms for Local Surface Description , 2010, ECCV.

[6]  Yu Zhong,et al.  Intrinsic shape signatures: A shape descriptor for 3D object recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[7]  Jiri Matas,et al.  Randomized RANSAC with sequential probability ratio test , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[8]  Michael Beetz,et al.  Detecting and segmenting objects for mobile manipulation , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[9]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Weisi Lin,et al.  B-SHOT: A binary feature descriptor for fast and efficient keypoint matching on 3D point clouds , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Jiri Matas,et al.  Optimal Randomized RANSAC , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Shan Wang,et al.  MLESAC Based Localization of Needle Insertion Using 2D Ultrasound Images , 2018 .

[13]  Hongtai Cheng,et al.  RGB-D Camera based 3D Object Pose Estimation and Grasping , 2019, 2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER).

[14]  Eric Brachmann,et al.  Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[15]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[16]  Jiri Matas,et al.  Randomized RANSAC with Td, d test , 2004, Image Vis. Comput..

[17]  Eric Brachmann,et al.  DSAC — Differentiable RANSAC for Camera Localization , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Markus Vincze,et al.  OUR-CVFH - Oriented, Unique and Repeatable Clustered Viewpoint Feature Histogram for Object Recognition and 6DOF Pose Estimation , 2012, DAGM/OAGM Symposium.

[19]  Andrea Marchetti,et al.  Optimal RANSAC-Towards a Repeatable Algorithm for Finding the Optimal Set , 2013, J. WSCG.

[20]  Mohammed Bennamoun,et al.  3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Xiaoming Wang,et al.  3D object recognition and pose estimation for random bin-picking using Partition Viewpoint Feature Histograms , 2019, Pattern Recognit. Lett..

[22]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[23]  Yong-Sheng Chen,et al.  Fast algorithm for robust template matching with M-estimators , 2003, IEEE Trans. Signal Process..

[24]  Jiri Matas,et al.  Locally Optimized RANSAC , 2003, DAGM-Symposium.

[25]  Fei Wang,et al.  An Improved Point Cloud Descriptor for Vision Based Robotic Grasping System , 2019, Sensors.

[26]  Azriel Rosenfeld,et al.  Robust regression methods for computer vision: A review , 1991, International Journal of Computer Vision.

[27]  Philip H. S. Torr,et al.  Bayesian Model Estimation and Selection for Epipolar Geometry and Generic Manifold Fitting , 2002, International Journal of Computer Vision.

[28]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Markus Ulrich,et al.  CAD-based recognition of 3D objects in monocular images , 2009, 2009 IEEE International Conference on Robotics and Automation.

[30]  John Mark Bishop,et al.  NAPSAC: high noise, high dimensional model parameterisation - it's in the bag , 2002 .

[31]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[32]  Mohammed Bennamoun,et al.  Rotational Projection Statistics for 3D Local Surface Description and Object Recognition , 2013, International Journal of Computer Vision.

[33]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[35]  Jiri Matas,et al.  Randomized RANSAC with T(d, d) test , 2002, BMVC.

[36]  Frank Dellaert,et al.  GroupSAC: Efficient consensus in the presence of groupings , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[37]  Wolfram Burgard,et al.  Point feature extraction on 3D range scans taking into account object boundaries , 2011, 2011 IEEE International Conference on Robotics and Automation.

[38]  Markus Vincze,et al.  Ensemble of shape functions for 3D object classification , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.