Multi-channel video-based parallel fire detection acceleration method using multi-cores

Authors:
Di Xie;Ruofeng Tong;Hongsen Wu
Affiliations:
Zhejiang University, Hangzhou, China;Zhejiang University, Hangzhou, China;Zhejiang Police College, Hangzhou, China
Venue:
Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
Year:
2009

Citing 7
Cited 0

Parallel depth first search. Part I. implementation

International Journal of Parallel Programming
Scalable load balancing techniques for parallel computers

Journal of Parallel and Distributed Computing
Vision Based Fire Detection

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
The Smoke Detection for Early Fire-Alarming System Base on Video Processing

IIH-MSP '06 Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia
Understanding the Impact of Multi-Core Architecture in Cluster Computing: A Case Study with Intel Dual-Core System

CCGRID '07 Proceedings of the Seventh IEEE International Symposium on Cluster Computing and the Grid
High Performance Global Illumination on Multi-core Architectures

PDP '09 Proceedings of the 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing
Multi-core collision detection between deformable models

2009 SIAM/ACM Joint Conference on Geometric and Physical Modeling

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel fire detection algorithm which uses several temporal and spatial features to recognize fire in video. It also proposes an acceleration strategy for parallel detection. We explore the parallelization from both coarse-grained and fine-grained strategies and try to solve the problem of parallel overhead and load imbalance. Experiment shows that our acceleration method can meet real-time requirement at most 16 channels to be detected together.