ROS-RM - Session IV Print

Session IV: 3D Object Recognition in Clutter with the Point Cloud Library

(15:00-16:30, July 23, 2014)

Dr. Federico Tombari (University of Bologna-Italy, Italy / Open Perception, Inc., USA)

 

Abstract

The Point Cloud Library (PCL) is a large scale, open project for 2D/3D image and point cloud processing currently catered by the Open Perception Foundation. Among the several modules available in PCL, this talk will focus on those aimed at the task of 3D object recognition in clutter. To this goal, it will address several related aspects such as 3D keypoint detection and description, correspondence grouping and hypothesis verification: while highlighting the theoretical background regarding current state-of-the-art techniques, we will also have a look at design choices and code snippets. Moreover, we will go over a code tutorial explaining how to assemble together the introduced methodologies within a complete object recognition pipeline.

Speaker short bio

Federico Tombari holds an appointment as an Assistant Professor at the University of Bologna, after obtaining from the same institution a Ph.D in 2009. His current research activity concerns computer and robot vision, and it encompasses co-authoring more than 50 refereed papers on peer-reviewed international conferences and journals, mainly focused on visual data representation, object recognition, stereo vision, video analysis for surveillance and 3D perception. In 2004 he has been visiting student at University of Technology, Sydney, while in 2008 he has been an intern at Willow Garage, California. He is a Senior Scientist volunteer for the Open Perception foundation and a developer for the Point Cloud Library, contributing also in terms of dissemination and mentoring for code sprints sponsored by private companies (Google, Trimble, Honda). In 2014 he serves as administrator and mentor for PCL in the Google Summer of Code. He is member of IEEE and IAPR-GIRPR. He is the recipient of the "Best Paper Award Runner-up” of the International Conference on 3D Imaging, Modeling, Processing and Visualization Technologies (3DIMPVT 2011).

Relevant references

3D detectors and descriptors:

F. Tombari, S. Salti, L. Di Stefano, “Unique signatures of Histograms for local surface description”, 11th European Conference on Computer Vision (ECCV 10), 2010.

A. Aldoma, F. Tombari, R.B. Rusu, M. Vincze, “OUR-CVFH: Oriented, Unique and Repeatable Clustered Viewpoint Feature Histogram for Object Recognition and 6DOF Pose Estimation”, Joint DAGM-OAGM Pattern Recognition Symposium (DAGM-OAGM 2012), 2012.

F. Tombari, S. Salti, L. Di Stefano, “Performance Evaluation of 3D Keypoint Detectors”, International Journal of Computer Vision (IJCV), Vol. 102, n. 1-3, pp. 198-220, 2013.

Object Recognition approaches:

A. Aldoma, Z.C. Marton, F. Tombari, W. Wohlkinger, C. Potthast, B. Zeisl, R.B. Rusu, S. Gedikli, M. Vincze, “Point Cloud Library: Three-Dimensional Object Recognition and 6 DOF Pose Estimation”, IEEE Robotics and Automation Magazine (RAM), Vol. 19, n. 3, pp. 80-91, September 2012.

F. Tombari, L. Di Stefano, “Hough voting for 3D object recognition under occlusion and clutter”, IPSJ Trans. on Computer Vision and Applications (CVA), vol. 4, pp 20-29, March 2012.

A. Aldoma, F. Tombari, L. Di Stefano, M. Vincze, “A global hypothesis verification method for 3D object recognition”, 12th European Conference on Computer Vision (ECCV 2012), 2012.

A. Aldoma, F. Tombari, J. Prankl, A. Richtsfeld, L. Di Stefano, M. Vincze, “Multimodal Cue Integration through Hypotheses Verification for RGB-D Object Recognition and 6DOF Pose Estimation”, IEEE International Conference on Robotics and Automation (ICRA), 2013.

Speaker's website: http://vision.deis.unibo.it/fede/