Self-organizing maps
Detection of independent motion using directional motion estimation
Computer Vision and Image Understanding
An Intelligent System for False Alarm Reduction in Infrared Forest-Fire Detection
IEEE Intelligent Systems
Efficient region-based motion segmentation for a video monitoring system
Pattern Recognition Letters
Retrieval by shape similarity with perceptual distance andeffective indexing
IEEE Transactions on Multimedia
Brain volumes characterisation using hierarchical neural networks
Artificial Intelligence in Medicine
Hi-index | 0.00 |
A research has been carried out finalised to the definition of a methodology useful to detect and track moving targets in video sequences. Algorithms performing this task have been also developed for real time monitoring and surveillance purposes. Due to deformations occurring in the appearance of the target in the videos, a Hierarchical Artificial Neural Network (HANN) has been used to recognize target occlusion or masking, and to increase the normal tracking performance. Preliminary results are presented regarding both identification and tracking of animal moving at night in an open environment, and the surveillance of known scenes for unauthorized access control.