by Vinay D. Shet, David Harwood, Larry S. Davis
In ECCV, pages IV: 119–132
http://www.umiacs.umd.edu/~vinay/papers/eccv06.pdf
Add To MetaCart
Abstract:
Abstract. Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent “atomic ” events. It also requires the capacity to robustly track individuals and maintain their identities across single as well as multiple camera views. Identity maintenance is a primary source of uncertainty for activity recognition and has been traditionally addressed via different appearance matching approaches. However these approaches, by themselves, are inadequate. In this paper, we propose a prioritized, multivalued, default logic based framework that allows reasoning about the identities of individuals. This is achieved by augmenting traditional appearance matching with contextual information about the environment and self identifying traits of certain actions. This framework also encodes qualitative confidence measures for the identity decisions it takes and finally, uses this information to reason about the occurrence of certain predefined activities in video. ⋆ We thank the U.S.Government for supporting the research described in this paper. 2 1
Citations
|
277
|
Real-Time American Sign Language Recognition Using Desk and Wearable Computer Based Video
– Starner, Pentland, et al.
- 1998
|
|
120
|
Multivalued logics: A uniform approach to reasoning in artificial intelligence
– Ginsberg
- 1988
|
|
104
|
Recognition of visual activities and interactions by stochastic parsing
– Ivanov, Bobick
- 2000
|
|
86
|
Multi-camera multi-person tracking for EasyLiving
– Krumm, Harris, et al.
- 2000
|
|
62
|
Adding Priorities and Specificity to Default Logic
– Brewka
- 1994
|
|
53
|
A framework for recognizing multi-agent action from visual evidence
– Intille, Bobick
- 1999
|
|
47
|
Recognition and interpretation of parametric gesture
– Wilson, Bobick
- 1998
|
|
39
|
R.: Probabilistic recognition of human faces from video. Computer Vision and Image Understanding 91
– Zhou, Krueger, et al.
- 2003
|
|
39
|
Advanced Visual Surveillance using Bayesian Networks
– Buxton, Gong
- 1995
|
|
20
|
Video-based event recognition: activity representation and probabilistic recognition methods
– Hongeng, Nevatia, et al.
|
|
17
|
Motion-based recognition of people in eigengait space, in: Automatic Face and Gesture Recognition 2002
– Ben-Abdelkader, Cutler, et al.
- 2002
|
|
17
|
Automatic video interpretation: A novel algorithm for temporal scenario recognition
– VU, BREMOND, et al.
- 2003
|
|
17
|
Building qualitative event models automatically from visual input
– Fernyhough, Cohn, et al.
- 1998
|
|
15
|
Artificial Intelligence, Logic and Formalizing Common Sense 15
– McCarthy
- 1989
|
|
15
|
Activity Recognition from Video Sequences Using Declarative Models
– Rota, Thonnat
- 2000
|
|
11
|
Towards an architecture for cognitive vision using qualitative spatio-temporal representations and abduction
– Cohn, Magee, et al.
- 2003
|
|
7
|
Skepticism and floating conclusions
– Horty
- 2002
|
|
5
|
A context representation for surveillance systems
– Bremond
- 1996
|
|
5
|
A Logic for Default Reasoning in Readings in Nonmonotonic Reasoning, Edited by
– Reiter
- 1987
|
|
4
|
Vidmap: video monitoring of activity with prolog
– Shet, Harwood, et al.
- 2005
|
|
1
|
T.: Full-body person recognition system. Pattern Recognition 36
– Nakajima, Pontil, et al.
- 2003
|
|
1
|
A.: Multiple-camera people localization in a cluttered environment
– Wei, Petrushin, et al.
- 2004
|
