Title
Recognition of 48 Human Behaviors from Video
Author
Burghouts, G.J.
Bouma, H.
den Hollander, R.J.M.
van den Broek, S.P.
Schutte, K.
Publication year
2012
Abstract
We have developed a system that recognizes 48 human behaviors from video. The essential elements are (i) inference of the actors in the scene, (ii) assessment of event-related properties of actors and between actors, (iii) exploiting the event properties to recognize the behaviors. The performance of our recognizer approaches human performance, yet the performance for unseen variations of the behaviors needs to be improved.
Subject
Visual pattern recognition
Human behavior
Spatiotemporal features
Events
Classification
Random forest
Tag propagation
High Tech Systems & Materials
Industrial Innovation
Physics & Electronics
II - Intelligent Imaging
TS - Technical Sciences
To reference this document use:
http://resolver.tudelft.nl/uuid:8d386779-8750-43e6-83ca-1e5b42694c38
TNO identifier
446579
Source
OPTRO 2012 - 5th International Symposium on Optronics in Defence and Security, 8-10 February 2012, Paris, France
Document type
conference paper