Closed-world tracking
作者： S.S. Intille , A.F. Bobick
关键词: Feature (computer vision) 、 Pixel 、 Object detection 、 Context (language use) 、 Computer science 、 Artificial intelligence 、 Domain (software engineering) 、 Object (computer science) 、 Computer vision 、 Video tracking 、 Tracking (particle physics)
摘要: A new approach to tracking weakly modeled objects in a semantically rich domain is presented. We define closed-world as space-time region of an image sequence which the complete taxonomy known, and each pixel should be explained belonging one those objects. Given contextual object information, context-specific features can dynamically selected basis for tracking. feature that has been chosen based upon context maximize chance successful between frames. Our work motivated by goal video annotation-the semi-automatic generation symbolic descriptions action taking place contextually-rich dynamic scene. describe how knowledge "football domain" applied football player present details our implementation. include results on hundreds images demonstrate wide range situations algorithm successfully handles well few examples where fails. >
ieeecomputersociety.org
neu.edu 参考文章(19)
D.D. Fu, K.J. Hammond, M.J. Swain, Vision and navigation in man-made environments: looking for syrup in all the right places Workshop on Visual Behaviors. pp. 20- 26 ,(1994) , 10.1109/VL.1994.365614
T. N. Tan, G. D. Sullivan, K. D. Baker, Pose determination and recognition of vehicles in traffic scenes european conference on computer vision. pp. 501- 506 ,(1994) , 10.1007/3-540-57956-7_56
A. D. Worrall, G. D. Sullivan, K. D. Baker, Pose refinement of active models using forces in 3D european conference on computer vision. pp. 341- 350 ,(1994) , 10.1007/3-540-57956-7_38
P.N. Prokopowicz, R.J. Swain, R.E. Kahn, Task and Environment-Sensitive Tracking, Workshop on Visual Behaviors. pp. 73- 78 ,(1994) , 10.1109/VL.1994.365608
H.-H. Nagel, From image sequences towards conceptual descriptions Image and Vision Computing. ,vol. 6, pp. 59- 74 ,(1988) , 10.1016/0262-8856(88)90001-7
Vincent S.S. Hwang, Tracking feature points in time-varying images using an opportunistic selection approach Pattern Recognition. ,vol. 22, pp. 247- 256 ,(1989) , 10.1016/0031-3203(89)90073-3
Ishwar K. Sethi, Ramesh Jain, Finding Trajectories of Feature Points in a Monocular Image Sequence IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-9, pp. 56- 73 ,(1987) , 10.1109/TPAMI.1987.4767872
Paul L. Rosin, Tim Ellis, Detecting and Classifying Intruders in Image Sequences BMVC91. pp. 293- 300 ,(1991) , 10.1007/978-1-4471-1921-0_37
R. Marslin, G. D. Sullivan, K. D. Baker, Kalman Filters in Constrained Model Based Tracking british machine vision conference. pp. 371- 374 ,(1991) , 10.1007/978-1-4471-1921-0_53
Jon A Webb, Jake K Aggarwal, Visually Interpreting the Motion of Objects in Space IEEE Computer. ,vol. 14, pp. 40- 46 ,(1981) , 10.1109/C-M.1981.220561