Unsupervised Object Discovery and Segmentation of RGBD-images

In this paper we introduce a system for unsupervised object discovery and segmentation of RGBD-images. The system models the sensor noise directly from data, allowing accurate segmentation without sensor specific hand tuning of measurement noise models making use of the recently introduced Statistical Inlier Estimation (SIE) method. Through a fully probabilistic formulation, the system is able to apply probabilistic inference, enabling reliable segmentation in previously challenging scenarios. In addition, we introduce new methods for filtering out false positives, significantly improving the signal to noise ratio. We show that the system significantly outperform state-of-the-art in on a challenging real-world dataset.

[1]  Antoine Vacavant,et al.  A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos , 2014, Comput. Vis. Image Underst..

[2]  John Folkesson,et al.  Adaptive Cost Function for Pointcloud Registration , 2017, ArXiv.

[3]  Nico Blodow,et al.  General 3D modelling of novel objects from a single view , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Olga Sorkine-Hornung,et al.  Object detection and classification from large‐scale cluttered indoor scans , 2014, Comput. Graph. Forum.

[6]  John Folkesson,et al.  Probabilistic Primitive Refinement algorithm for colored point cloud data , 2015, 2015 European Conference on Mobile Robots (ECMR).

[7]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Rares Ambrus,et al.  Meta-rooms: Building and maintaining long term spatial models in a dynamic world , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Frank Dellaert,et al.  Planar Segmentation of RGBD Images Using Fast Linear Fitting and Markov Chain Monte Carlo , 2012, 2012 Ninth Conference on Computer and Robot Vision.

[10]  Sven Behnke,et al.  Approximate triangulation and region growing for efficient segmentation and smoothing of range images , 2014, Robotics Auton. Syst..

[11]  Dieter Fox,et al.  Toward object discovery and modeling via 3-D scene comparison , 2011, 2011 IEEE International Conference on Robotics and Automation.

[12]  Marc Hanheide,et al.  Long-term topological localisation for service robots in dynamic environments using spectral maps , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[14]  John J. Leonard,et al.  Toward lifelong object segmentation from change detection in dense RGB-D maps , 2013, 2013 European Conference on Mobile Robots.

[15]  Vladimir Kolmogorov,et al.  Object cosegmentation , 2011, CVPR 2011.

[16]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[17]  K. Lingemann,et al.  The 3D Hough Transform for plane detection in point clouds: A review and a new accumulator design , 2011 .

[18]  Henrik I. Christensen,et al.  Efficient Organized Point Cloud Segmentation with Connected Components , 2013 .

[19]  Siddhartha S. Srinivasa,et al.  HerbDisc: Towards lifelong robotic object discovery , 2015, Int. J. Robotics Res..

[20]  Nassir Navab,et al.  Coloured signed distance fields for full 3D object reconstruction , 2014, BMVC.

[21]  Wolfram Burgard,et al.  Unsupervised learning of 3D object models from partial views , 2009, 2009 IEEE International Conference on Robotics and Automation.

[22]  Jari Saarinen,et al.  Conditional transition maps: Learning motion patterns in dynamic environments , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Markus Vincze,et al.  RGB-D object modelling for object recognition and tracking , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[25]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Rares Ambrus,et al.  Unsupervised learning of spatial-temporal models of objects in a long-term autonomy scenario , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

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

[28]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Eduardo Ros,et al.  Background Subtraction Based on Color and Depth Using Active Sensors , 2013, Sensors.

[30]  Erkki Oja,et al.  A new curve detection method: Randomized Hough transform (RHT) , 1990, Pattern Recognit. Lett..

[31]  Achim J. Lilienthal,et al.  Has somethong changed here? Autonomous difference detection for security patrol robots , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[32]  Wolfram Burgard,et al.  Learning compact 3D models of indoor and outdoor environments with a mobile robot , 2003, Robotics Auton. Syst..

[33]  Dieter Fox,et al.  RGB-D object discovery via multi-scene analysis , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[34]  Sven Behnke,et al.  Real-Time Plane Segmentation Using RGB-D Cameras , 2012, RoboCup.

[35]  Martin Thoma,et al.  A Survey of Semantic Segmentation , 2016, ArXiv.

[36]  Jari Saarinen,et al.  Independent Markov chain occupancy grid maps for representation of dynamic environment , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.