IEEE Computer Graphics and Applications
Real-time audio-visual tracking for meeting analysis
Proceedings of the 6th international conference on Multimodal interfaces
Unsupervised scene analysis: a hidden Markov model approach
Computer Vision and Image Understanding
Determining activity patterns in retail spaces through video analysis
MM '08 Proceedings of the 16th ACM international conference on Multimedia
High-level goal recognition in a wireless LAN
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Unsupervised scene analysis: A hidden Markov model approach
Computer Vision and Image Understanding
Proceedings of the 2010 conference on Biologically Inspired Cognitive Architectures 2010: Proceedings of the First Annual Meeting of the BICA Society
Proceedings of the Fourth International Conference on Learning Analytics And Knowledge
| Hi-index | 0.00 |
Location-based context is important for many applications.Previous systems offered only coarse room-level featuresor used manually specified room regions to determinefine-scale features. We propose a location context mechanismbased on activity maps, which defineregions of similarcontext based on observations of 3-D patterns of locationand motion in an environment. We describe an algorithmfor obtaining activity maps using the spatio-temporal clusteringof visual tracking data. We show how the recoveredmaps correspond to regions for common tasks in the environmentand describe their use in some applications.