Human Activity Recognition Based on Silhouette Directionality

Recent advances in computer vision and pattern recognition have fueled numerous initiatives that aim to intelligently recognize human activities. In this paper, we propose an algorithm for nonintrusive human activity recognition. We use an adaptive background-foreground separation technique to extra...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2008-09, Vol.18 (9), p.1280-1292
Main Authors: Singh, M., Basu, A., Mandal, M.K.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Cameras
Computer science
control theory
systems
Computer vision
Decisions
Dynamic characteristics
Exact sciences and technology
Functional analysis
Hidden Markov models
Human activity recognition
Human motion
Humans
Indexing
Information theory
Information, signal and communications theory
Infrared sensors
Mathematical analysis
Motion analysis
Pattern recognition
Pattern recognition. Digital image processing. Computational geometry
Recognition
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
silhouette extraction
Telecommunications and information theory
temporal smoothing
vector space analysis
Vectors (mathematics)
Videos
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advances in computer vision and pattern recognition have fueled numerous initiatives that aim to intelligently recognize human activities. In this paper, we propose an algorithm for nonintrusive human activity recognition. We use an adaptive background-foreground separation technique to extract motion information and generate silhouettes (foreground) from the input videos. We then derive directionality-based feature vectors (directional vectors) from the silhouette contours and use the distinct data distribution of directional vectors in a vector space for clustering and recognition. We also exploit the dynamic characteristic of human motion in order to smooth decisions over time and reduce errors in activity recognition. Our approach is monocular, tolerant to moderate view changes, and can be applied to both frontal and lateral views of most activities. Experiments with short and long video sequences show robust recognition under conditions of varying view angles, zoom depths, backgrounds, and frame rates.
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2008.928888