CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Bayesian Networks and Decision Graphs
Bayesian Networks and Decision Graphs
Machine Learning
Distributed Systems: Principles and Paradigms
Distributed Systems: Principles and Paradigms
A Modular Software Architecture for Real-Time Video Processing
ICVS '01 Proceedings of the Second International Workshop on Computer Vision Systems
Scalable Independent Multi-level Distribution in Multimedia Content Analysis
IDMS/PROMS 2002 Proceedings of the Joint International Workshops on Interactive Distributed Multimedia Systems and Protocols for Multimedia Systems: Protocols and Systems for Interactive Distributed Multimedia
Real-time Hypothesis Driven Feature Extraction on Parallel Processing Architectures
PDPTA '02 Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications - Volume 2
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Audio-Visual Speaker Detection Using Dynamic Bayesian Networks
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Bayesian Framework for Video Surveillance Application
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Supporting timeliness and accuracy in distributed real-time content-based video analysis
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Techniques for parallel execution of the particle filter
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
A generic approach to simultaneous tracking and verification in video
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Extraction of features from images, followed by pattern classification, is a promising approach to automatic video analysis. However, a parallel processing environment is typically required for real-time performance. Still, single-CPU Bayesian network systems for hypothesis driven feature extraction have been able to classify image content real-time --- the expected information value and processing cost of features are measured, and only efficient features are extracted. The goal in this paper is to combine the processing benefits of parallel and hypothesis driven approaches. We use dynamic Bayesian networks to specify video analysis tasks and the particle filter (PF) for approximate inference, i.e., feature selection and classification. The inference accuracy of any given PF is determined by the number of particles it maintains. To increase the number of particles maintained without reducing the processing rate, we apply multiple PFs distributed in a LAN, and a pooling system to coordinate their output. Our resulting multi-PF architecture supports three video frame processing phases: a parallelized feature selection phase, followed by a parallelized feature extraction- and classification phase. Unfortunately, we observe a loss of inference accuracy when splitting a single PF into multiple independent PFs. To reduce this loss, we let the pooled PFs exchange particles across the LAN. An object tracking simulation demonstrates the ability of our architecture to select efficient features as well as the effectiveness of our particle exchange scheme --- we observe a significant increase in inference accuracy compared to the tested non-parallel PF.