摘要: A new view-based approach to the representation of action is presented. Our underlying representations are descriptions coarse image motion associated with viewing given actions from particular directions. Using these descriptions, we propose an appearance-based action-recognition strategy comprised two stages: 1) a energy (MEI) computed that grossly describes spatial distribution for view action, and input MEI matched against stored models which span range views known actions; 2) any plausibly match tested coarse, categorical agreement between model parametrization motion. "sitting" as example, using manually placed stick model, develop verification technique collapses temporal variations parameters into single, low-order vector.
sci-hub.se 参考文章(20)
J. Yamato, J. Ohya, K. Ishii, Recognizing human action in time-sequential images using hidden Markov model computer vision and pattern recognition. pp. 379- 385 ,(1992) , 10.1109/CVPR.1992.223161
James R. Bergen, P. Anandan, Keith J. Hanna, Rajesh Hingorani, Hierarchical model-based motion estimation Computer Vision — ECCV'92. pp. 237- 252 ,(1992) , 10.1007/3-540-55426-2_27
J. J. Koenderink, A. J. van Doorn, The internal representation of solid shape with respect to vision Biological Cybernetics. ,vol. 32, pp. 211- 216 ,(1979) , 10.1007/BF00337644
David Hogg, Model-based vision: a program to see a walking person Image and Vision Computing. ,vol. 1, pp. 5- 20 ,(1983) , 10.1016/0262-8856(83)90003-3
Claudette Cédras, Mubarak Shah, Motion-based recognition a survey Image and Vision Computing. ,vol. 13, pp. 129- 155 ,(1995) , 10.1016/0262-8856(95)93154-K
K. Rohr, Towards model-based recognition of human movements in image sequences Cvgip: Image Understanding. ,vol. 59, pp. 94- 115 ,(1994) , 10.1006/CIUN.1994.1006
Koichiro Akita, Image Sequence Analysis of Real World Human Motion Pattern Recognition. ,vol. 17, pp. 73- 83 ,(1984) , 10.1016/0031-3203(84)90036-0
J.M. Rehg, T. Kanade, Model-based tracking of self-occluding articulated objects international conference on computer vision. pp. 612- 617 ,(1995) , 10.1109/ICCV.1995.466882
Yuntao Cui, D.L. Swets, J.J. Weng, Learning-based hand sign recognition using SHOSLIF-M international conference on computer vision. pp. 631- 636 ,(1995) , 10.1109/ICCV.1995.466879
W Eric L Grimson, None, Object Recognition by Computer: The Role of Geometric Constraints ,(1991)