3D Szenenfluss – bildbasierte Schätzung dichter Bewegungsfelder

Der 3D Szenenfluss (scene flow) ist eine dichte Beschreibung der Geometrie und des Bewegungsfeldes einer dynamischen Szene. Entsprechend ist die Bestimmung des Szenenflusses aus binokularen Videosequenzen eine Generalisierung zweier klassischer Aufgaben der bildbasierten Messtechnik, der Schatzung von Stereokorrespondenz und optischem Fluss. Im folgenden wird ein Modell vorgestellt, in dem die dynamische 3D Szene durch eine Menge von planaren Segmenten reprasentiert wird, wobei jedes Segment eine Starrkorperbewegung (Translation und Rotation) ausfuhrt. Die (Uber-)Segmentierung in starre, ebene Segmente wird gemeinsam mit deren 3D Geometrie und 3D Bewegung geschatzt. Das beschriebene Modell ist wesentlich kompakter als die konventionelle pixelweise Reprasentation, verfugt aber dennoch uber genugend Flexibilitat, um reale Szenen mit mehreren unabhangigen Bewegungen zu beschreiben. Daruber hinaus erlaubt es, a-priori Annahmen uber die Szene einzubinden und Verdeckungen zu berucksichtigen, und ermoglicht den Einsatz robuster diskreter Optimierungsmethoden. Weiters ist das Modell, in Kombination mit einem dynamischen Modell, direkt auf mehrere aufeinanderfolgende Zeitschritte anwendbar. Dazu wird fur die einzelnen Bilder jeweils eine eigene Reprasentation instanziiert. Entsprechende Bedingungen stellen sicher, dass die Schatzung uber verschiedene Ansichten und verschiedene Zeitpunkte konsistent ist. Das beschriebene Modell verbessert die Genauigkeit und Zuverlassigkeit der Szenenfluss-Schatzung speziell bei ungunstigen Aufnahmebedingungen.

[1]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[2]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  David W. Murray,et al.  Scene Segmentation from Visual Motion Using Global Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Michael J. Black,et al.  Robust dynamic motion estimation over time , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[6]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[7]  Takeo Kanade,et al.  Three-dimensional scene flow , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  Hai Tao,et al.  Global matching criterion and color segmentation based stereo , 2000, Proceedings Fifth IEEE Workshop on Applications of Computer Vision.

[9]  Kiriakos N. Kutulakos,et al.  Multi-View Scene Capture by Surfel Sampling: From Video Streams to Non-Rigid 3D Motion, Shape and Reflectance , 2002, International Journal of Computer Vision.

[10]  Thomas Brox,et al.  High Accuracy Optical Flow Estimation Based on a Theory for Warping , 2004, ECCV.

[11]  Frederic Devernay,et al.  Multi-Camera Scene Flow by Tracking 3-D Points and Surfels , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[13]  Alfred M. Bruckstein,et al.  Over-Parameterized Variational Optical Flow , 2007, International Journal of Computer Vision.

[14]  Frederic Devernay,et al.  A Variational Method for Scene Flow Estimation from Stereo Sequences , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  Vladimir Kolmogorov,et al.  Optimizing Binary MRFs via Extended Roof Duality , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  H. Hirschmüller Stereo Processing by Semiglobal Matching and Mutual Information , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Carsten Rother,et al.  FusionFlow: Discrete-continuous optimization for optical flow estimation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Daniel Cremers,et al.  Efficient Dense Scene Flow from Sparse or Dense Stereo Data , 2008, ECCV.

[19]  T. Vaudrey,et al.  Differences between stereo and motion behaviour on synthetic and real-world stereo sequences , 2008, 2008 23rd International Conference Image and Vision Computing New Zealand.

[20]  Jean Ponce,et al.  Dense 3D motion capture from synchronized video streams , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Daniel Cremers,et al.  High resolution motion layer decomposition using dual-space graph cuts , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Enric X. Martín,et al.  Refining 3D Recovering by Carving through View Interpolation and Stereovision , 2003, IbPRIA.

[23]  Daniel Cremers,et al.  Anisotropic Huber-L1 Optical Flow , 2009, BMVC.

[24]  Joachim Weickert,et al.  Joint Estimation of Motion, Structure and Geometry from Stereo Sequences , 2010, ECCV.

[25]  Uwe Franke,et al.  Dense, Robust, and Accurate Motion Field Estimation from Stereo Image Sequences in Real-Time , 2010, ECCV.

[26]  Yael Moses,et al.  Multi-view scene flow estimation: A view centered variational approach , 2010, CVPR.

[27]  Andrew Blake,et al.  Fusion Moves for Markov Random Field Optimization , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Paria Mehrani,et al.  Superpixels and Supervoxels in an Energy Optimization Framework , 2010, ECCV.

[29]  Michael J. Black,et al.  Layered image motion with explicit occlusions, temporal consistency, and depth ordering , 2010, NIPS.

[30]  Pushmeet Kohli,et al.  Surface stereo with soft segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[31]  Pushmeet Kohli,et al.  Object stereo — Joint stereo matching and object segmentation , 2011, CVPR 2011.

[32]  Uwe Franke,et al.  Feature- and depth-supported modified total variation optical flow for 3D motion field estimation in real scenes , 2011, CVPR 2011.

[33]  Konrad Schindler,et al.  3D scene flow estimation with a rigid motion prior , 2011, 2011 International Conference on Computer Vision.

[34]  Takeo Kanade,et al.  A Head-Wearable Short-Baseline Stereo System for the Simultaneous Estimation of Structure and Motion , 2011, MVA.

[35]  Henning Zimmer,et al.  Modeling temporal coherence for optical flow , 2011, 2011 International Conference on Computer Vision.

[36]  Jitendra Malik,et al.  Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Horst Bischof,et al.  Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  In-So Kweon,et al.  A Tensor Voting Approach for Multi-view 3D Scene Flow Estimation and Refinement , 2012, ECCV.

[39]  Tamir Hazan,et al.  Continuous Markov Random Fields for Robust Stereo Estimation , 2012, ECCV.

[40]  Bernd Jähne,et al.  Outdoor stereo camera system for the generation of real-world benchmark data sets , 2012 .

[41]  Li Xu,et al.  Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles , 2013, International Journal of Computer Vision.

[42]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[43]  Konrad Schindler,et al.  Piecewise Rigid Scene Flow , 2013, 2013 IEEE International Conference on Computer Vision.

[44]  Raquel Urtasun,et al.  Robust Monocular Epipolar Flow Estimation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[45]  Konrad Schindler,et al.  An Evaluation of Data Costs for Optical Flow , 2013, GCPR.

[46]  Michael J. Black,et al.  A Fully-Connected Layered Model of Foreground and Background Flow , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[47]  Lena Gorelick,et al.  Submodularization for Binary Pairwise Energies , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[48]  Konrad Schindler,et al.  View-Consistent 3D Scene Flow Estimation over Multiple Frames , 2014, ECCV.

[49]  Ron Kimmel,et al.  Affine Invariant Geometry for Non-rigid Shapes , 2014, International Journal of Computer Vision.

[50]  Raquel Urtasun,et al.  Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation , 2014, ECCV.

[51]  Konrad Schindler,et al.  3D Scene Flow Estimation with a Piecewise Rigid Scene Model , 2015, International Journal of Computer Vision.