Occlusion Robust Vehicle Tracking based on SOM (Self-Organizing Map)
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Putting Objects in Perspective
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
AIKED'09 Proceedings of the 8th WSEAS international conference on Artificial intelligence, knowledge engineering and data bases
Hi-index | 0.00 |
This work presents vehicle detecting and tracking system from a sequence of images. The system utilizes ART (Adaptive Resonance Theory) network for segmentation and recognition. By applying log-Gabor filters to the initially detected vehicle, the resulting filtered vehicles are fed into the network which can automatically recognize salient features of vehicles by analyzing theirs principal components. This unsupervised network allows the system to efficiently perform tracking in dynamic environments where shapes and sizes of vehicles are changing all the time. The proposed system can also track multiple vehicles simultaneously. Results and discussions are described.