The OD theory of TOD: the use and limits of temporal information for object discovery
作者： Rahul Sukthankar , Brandon C. S. Sanders , Randal C. Nelson
关键词:
摘要: We present the theory behind TOD (the Temporal Object Discoverer), a novel unsupervised system that uses only temporal information to discover objects across image sequences acquired by any number of uncalibrated cameras. The process is divided into three phases: (1) Extraction each pixel's signature, partition observations sets stem from different objects; (2) Construction global schedule explains signatures in terms lifetimes set quasi-static (3) Mapping according signature. Our Global Scheduling (GSched) algorithm provably constructs valid and complete when certain observability criteria are met. Quasi-Static Labeling (QSL) created GSched produce maximally-informative mapping onto they from. Using QSL, ignores distracting motion, correctly deals with complicated occlusions, naturally groups 2D masks recovered suitable for training initialization object recognition tracking systems.
acm.org
sci-hub.st 参考文章(9)
R. Sukthankar, R. C. Nelson, B. S.C. Sanders, Discovering Objects using Temporal Information University of Rochester. ,(2002)
Constantine Papageorgiou, Tomaso Poggio, A Trainable System for Object Detection International Journal of Computer Vision. ,vol. 38, pp. 15- 33 ,(2000) , 10.1023/A:1008162616689
Jianchang Mao, Anil K. Jain, Texture classification and segmentation using multiresolution simultaneous autoregressive models Pattern Recognition. ,vol. 25, pp. 173- 188 ,(1992) , 10.1016/0031-3203(92)90099-5
Yucel Altunbasak, P.Erhan Eren, A.Murat Tekalp, Region-based parametric motion segmentation using color information Graphical Models and Image Processing. ,vol. 60, pp. 13- 23 ,(1998) , 10.1006/GMIP.1997.0453
Bernt Schiele, James L. Crowley, Recognition without Correspondence using MultidimensionalReceptive Field Histograms International Journal of Computer Vision. ,vol. 36, pp. 31- 50 ,(2000) , 10.1023/A:1008120406972
J.Y.A. Wang, E.H. Adelson, Representing moving images with layers IEEE Transactions on Image Processing. ,vol. 3, pp. 625- 638 ,(1994) , 10.1109/83.334981
Jianqing Liu, Yee-Hong Yang, Multiresolution color image segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 16, pp. 689- 700 ,(1994) , 10.1109/34.297949
K. Toyama, J. Krumm, B. Brumitt, B. Meyers, Wallflower: principles and practice of background maintenance international conference on computer vision. ,vol. 1, pp. 255- 261 ,(1999) , 10.1109/ICCV.1999.791228
S. Belongie, C. Carson, H. Greenspan, J. Malik, Color- and texture-based image segmentation using EM and its application to content-based image retrieval international conference on computer vision. pp. 675- 682 ,(1998) , 10.1109/ICCV.1998.710790