Abstract
As the demand of an automatic fire detection system is increasing in recent years, a vision-based fire detection system is appealing. However, vision-based fire detection algorithms require tremendous computational performance, limiting their use in real-time applications. This paper proposes a multi-core prototyping system to support these high computational algorithms. The multi-core architecture including 16 processing elements (PEs) is implemented on a vertex 4 FPGA chip of the HUINS SoC Master 3 board. In addition, the performance of a selected four-stage fire detection algorithm is evaluated using the multi-core prototyping system. Experimental results show that the proposed multi-core prototyping system executing at 50 MHz clock frequency supports seven frames per second for a 240 × 200 resolution video. In addition, the proposed multi-core system achieves about 1.87 × speedup over commercial high-performance TI DSP operating at 720 MHz clock frequency.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Celik T, Demirel H (2009) Fire detection in video sequences using a generic color model. Fire Saf J 44(2):147–158
Tao L, Mao Y, Feng P, Haiyang W, Jian D (2013) An efficient fire detection method based on orientation feature. Int J Control Autom Syst 11(5):1038–1045
Chunyu Y, Zhibin M, Xi Z (2013) A real-time video fire flame and smoke detection algorithm. In: The 9th Asia-Oceania symposium on fire science and technology, vol 62, pp 891–898
Çelik T, Özkaramanlı H, Demirel H (2007) Fire and smoke detection without sensors: image processing based approach. In: 15th European signal processing conference, Poland, pp 1794–1798
Chen TH, Wu PH, Chiou YC (2004) An early fire-detection method based on image processing. In: IEEE international conference on image processing, Singapore, vol 3, pp 1707–1710
Toreyin BU, Centin AE (2004) Online detection of fire in video. In: IEEE conference on computer vision and pattern recognition, Washington DC, pp 1–5
Ko BC, Cheong KH, Nam JY (2009) Fire detection based on vision sensor and support vector machines. Fire Saf J 44(3):322–329
Nguyen H, John L (1999) Exploiting SIMD parallelism in DSP and multimedia algorithms using the AltiVec technology. In: Proceedings of international supercomputer conference, New York, pp 11–20
Abbo AA, Kleihorst RP, Choudhary V, Sevat L, Wielage P, Mouy S, Vermeulen B, Heijligers M (2008) Xetal-II: a 107 GOPS, 600 mW massively parallel processor for video scene analysis. IEEE J Solid-State Circuits 43(1):192–201
Chhugani J, Nguyen AD, Lee VW, Macy W, Hagog M, Chen YK, Baransi A, Kumar S, Dubey P (2008) Efficient implementation of sorting on multi-core SIMD CPU architecture. In: Proceedings of 34th international conference very large data bases, New Zealand, pp 1313–1324
Kyo S, Okazaki S, Arai T (2007) An integrated memory array processor for embedded image recognition systems. IEEE Trans Comput 56(5):622–634
Acknowledgments
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (No. NRF-2013R1A2A2A05004566), and by the Leading Industry Development for Economic Region (LeadER) grant funded the MKE (The Ministry of Knowledge Economy), Korea in 2013 (No. R0001220).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media Dordrecht
About this paper
Cite this paper
Park, YH., Kang, M., Kim, JM. (2014). Implementation of a Multi-core Prototyping System for a Video-Based Fire Detection Algorithm. In: Park, J., Zomaya, A., Jeong, HY., Obaidat, M. (eds) Frontier and Innovation in Future Computing and Communications. Lecture Notes in Electrical Engineering, vol 301. Springer, Dordrecht. https://doi.org/10.1007/978-94-017-8798-7_17
Download citation
DOI: https://doi.org/10.1007/978-94-017-8798-7_17
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-017-8797-0
Online ISBN: 978-94-017-8798-7
eBook Packages: EngineeringEngineering (R0)