Integrating and employing multiple levels of zoom for activity recognition

Authors:
Paul Smith;Mubarak Shah;Niels da Vitoria Lobo
Affiliations:
Computer Vision Laboratory School of Computer Science, University of Central Florida, Orlando, FL;Computer Vision Laboratory School of Computer Science, University of Central Florida, Orlando, FL;Computer Vision Laboratory School of Computer Science, University of Central Florida, Orlando, FL
Venue:
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Year:
2004

Citing 11
Cited 3

Determining the Epipolar Geometry and its Uncertainty: A Review

International Journal of Computer Vision
The visual analysis of human movement: a survey

Computer Vision and Image Understanding
Human motion analysis: a review

Computer Vision and Image Understanding
Tracking Human Motion in Structured Environments Using a Distributed-Camera System

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
The Space of All Stereo Images

International Journal of Computer Vision - Marr Prize Special Issue
M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene

International Journal of Computer Vision
Markov Random Fields with Efficient Approximations

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Finding skin in color images

FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Focus of Attention for Face and Hand Gesture Recognition Using Multiple Cameras

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Activity monitoring and summarization for an intelligent meeting room

HUMO '00 Proceedings of the Workshop on Human Motion (HUMO'00)

Integrating multiple levels of zoom to enable activity analysis

Computer Vision and Image Understanding
Learning, detection and representation of multi-agent events in videos

Artificial Intelligence
Survey and analysis of multimodal sensor planning and integration for wide area surveillance

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

To facilitate activity recognition, analysis of the scene at multiple levels of detail is necessary. Required prerequisites for our activity recognition are tracking objects across frames and establishing a consistent labeling of objects across cameras. This paper makes several innovative uses of the epipolar constraint in the context of activity recognition. We first demonstrate how we track heads and hands using the epipolar geometry. Next we show how the detected objects are labeled consistently across cameras and zooms by employing epipolar, spatial, trajectory, and appearance properties. Finally we show how our method, utilizing the multiple levels of detail, is able to answer activity recognition problems which are difficult to answer with a single level of detail.