Hybrid hierarchical learning from dynamic scenes

Authors:
Prithwijit Guha;Pradeep Vaghela;Pabitra Mitra;K. S. Venkatesh;Amitabha Mukerjee
Affiliations:
Department of Electrical Engineering, Indian Institute of Technology, Kanpur, Kanpur, UP, India;Department of Electrical Engineering, Indian Institute of Technology, Kanpur, Kanpur, UP, India;Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur, Kanpur, UP, India;Department of Electrical Engineering, Indian Institute of Technology, Kanpur, Kanpur, UP, India;Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur, Kanpur, UP, India
Venue:
PReMI'05 Proceedings of the First international conference on Pattern Recognition and Machine Intelligence
Year:
2005

Citing 4
Cited 0

W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning variable-length Markov models of behavior

Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Acquisition and Use of Interaction Behavior Models

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The work proposes a hierarchical architecture for learning from dynamic scenes at various levels of knowledge abstraction. The raw visual information is processed at different stages to generate hybrid symbolic/sub-symbolic descriptions of the scene, agents and events. The background is incrementally learned at the lowest layer, which is used further in the mid-level for multi-agent tracking with symbolic reasoning. The agent/event discovery is performed at the next higher layer by processing the agent features, status history and trajectory. Unlike existing vision systems, the proposed algorithm does not assume any prior information and aims at learning the scene/agent/event models from the acquired images. This makes it a versatile vision system capable of performing in a wide variety of environments.