The visual analysis of human movement: a survey
Computer Vision and Image Understanding
Parameterized modeling and recognition of activities
Computer Vision and Image Understanding
Human motion analysis: a review
Computer Vision and Image Understanding
Machine Learning
Computer Vision: Three-Dimensional Data from Images
Computer Vision: Three-Dimensional Data from Images
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Recognition of human body motion using phase space constraints
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
| Hi-index | 0.00 |
In this project, we propose a strategy to recognize behaviors of a fly from a sequence of features extracted from 3D scenes. Three dimensional (3D) level features and gray-level images of the object are extracted, creating vectors with the features along a sequence of fly images, representing particular activities (walking, feeding, drinking, flying, ovipositing, courting and resting). A stereo vision system was used to extract the sequence of 3D features and gray-level values obtained from the sequence of visible images. Three methods were proposed to use both kinds of information for recognition process. In the first method it is used 3D features, the second method is based on data level fusion and the third on a decision level fusion. This work will contribute to the study of lifespan behavior in insects and has the potential to contribute to our knowledge and understanding of age-specific dependant behaviors, general principles on disablement, and in general, the aging process of the insect. The Mexican fruit fly, a pest of economic importance, represents a good animal model for this purpose.