Centralized and Distributed Multi-view Correspondence

A probabilistic algorithm is presented for finding correspondences across multiple images in systems with large numbers of cameras and considerable overlap. The algorithm employs the theory of random graphs to provide an efficient probabilistic algorithm that performs Wide-baseline Stereo (WBS) comparisons on a small number of image pairs, and then propagates correspondence information among the cameras. A concrete mathematical analysis of its performance is given. The algorithm is extended to handle false-positive and false-negative failures of the WBS computations. We characterize the detectability of the existence of such failures, and propose an efficient method for this detection. Based on this, we propose a heuristic method for discarding false matches, and demonstrate its effectiveness in reducing errors.Since in many multi-camera applications cameras are attached to processors that handle local processing and communication, it is natural to consider distributed solutions that make use of the local processors and do not use a central computer. Our algorithm is especially suited to run in a distributed setting. If the local processors are sufficiently powerful, this allows an order of magnitude increase in computational efficiency. More importantly, a distributed implementation provides strong robustness guarantees, and eliminates the existence of a single point of failure that is inherent when the application is coordinated by a central computer. We show how to efficiently overcome processor crashes and communication failures with a minimal reduction in the quality of the algorithm’s results.

[1]  L. Davis,et al.  M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene , 2003, International Journal of Computer Vision.

[2]  Sape Mullender,et al.  Distributed systems , 1989 .

[3]  Luc Van Gool,et al.  Wide-baseline multiple-view correspondences , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Yoram Moses,et al.  Probabilistic Multi-view Correspondence in a Distributed Setting with No Central Server , 2004, ECCV.

[5]  Luc Van Gool,et al.  Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions , 2000, BMVC.

[6]  Andrew W. Fitzgibbon,et al.  Bundle Adjustment - A Modern Synthesis , 1999, Workshop on Vision Algorithms.

[7]  Robert T. Collins,et al.  Calibration of an outdoor active camera system , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[9]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[10]  Takeo Kanade,et al.  Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

[11]  Deborah Estrin,et al.  Cyclops, image sensing and interpretation in wireless networks , 2004, SenSys '04.

[12]  Christopher R. Wren,et al.  Self-configuring, Lightweight Sensor Networks for Ubiquitous Computing , 2003 .

[13]  Dmitry Chetverikov,et al.  Periodic Textures as Distinguished Regions for Wide-Baseline Stereo Correspondence , 2002 .

[14]  Barry Brumitt,et al.  Ubiquitous computing and the role of geometry , 2000, IEEE Wirel. Commun..

[15]  Andrew S. Tanenbaum,et al.  Distributed systems: Principles and Paradigms , 2001 .

[16]  Isaac Cohen,et al.  Continuous multi-views tracking using tensor voting , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[17]  Andrew Zisserman,et al.  Viewpoint invariant texture matching and wide baseline stereo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  Andrew Zisserman,et al.  Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?" , 2002, ECCV.

[19]  Michael Werman,et al.  The viewing graph , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[20]  Jake K. Aggarwal,et al.  Automatic tracking of human motion in indoor scenes across multiple synchronized video streams , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[21]  Béla Bollobás,et al.  Random Graphs: Preface to the Second Edition , 2001 .

[22]  Béla Bollobás,et al.  Random Graphs: Notation , 2001 .

[23]  Takeo Kanade,et al.  Virtualized reality: concepts and early results , 1995, Proceedings IEEE Workshop on Representation of Visual Scenes (In Conjunction with ICCV'95).

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

[25]  Andrew Zisserman,et al.  Wide baseline stereo matching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[26]  Edward M. Riseman,et al.  A Fault-Tolerant Distributed Vision System Architecture for Object Tracking in a Smart Room , 2001, ICVS.

[27]  Avrim Blum,et al.  Correlation Clustering , 2004, Machine Learning.

[28]  B. Bollobás,et al.  Random Graphs of Small Order , 1985 .

[29]  Takeo Kanade,et al.  A System for Video Surveillance and Monitoring , 2000 .

[30]  Seif Haridi,et al.  Distributed Algorithms , 1992, Lecture Notes in Computer Science.

[31]  Diego López-de-Ipiña,et al.  TRIP: A Low-Cost Vision-Based Location System for Ubiquitous Computing , 2002, Personal and Ubiquitous Computing.

[32]  Adam Baumberg,et al.  Reliable feature matching across widely separated views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).