Paper Info
Title
Automatic Learning of Conceptual Knowledge in Image Sequences for Human Behavior Interpretation
Abstract
This work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source is the geometrical data obtained by applying tracking algorithms to an image sequence, which is used to generate conceptual data. The spatial characteristics of the scene are automatically extracted from the resuling tracking trajectories obtained during a training period. Interpretation is achieved by means of a rule-based inference engine called Fuzzy Metric Temporal Horn Logicand a behavior modeling tool called Situation Graph Tree. These tools are used to generate conceptual descriptions which semantically describe observed behaviors.
Year
DOI
Venue
2007
10.1007/978-3-540-72847-4_65
IbPRIA (1)
Keywords
Field
DocType
conceptual data,conceptual description,image sequence,behavior modeling tool,resuling tracking,cognitive vision system,image sequences,human behavior,conceptual knowledge,human behavior interpretation,geometrical data,observed behavior,tracking algorithm,automatic learning,behavior modeling,rule based,computer vision
Computer vision,Graph,Pattern recognition,Computer science,Fuzzy logic,Automatic learning,Inference engine,Artificial intelligence,Image sequence,Machine learning,Cognitive vision
Conference
Volume
ISSN
Citations 
4477
0302-9743
3
PageRank 
References 
Authors
0.51
11
4
Name
Order
Citations
PageRank
Pau Baiget1443.93
Carles Fernández2223.01
Xavier Roca31087.53
Jordi Gonzalez461748.02