The Application of Visual Attention Mechanism in Road Disaster Identification and early Warning System

Abstract:

Visual attention mechanism is introduced into the traditional road disaster monitoring and early warning system. In this system, the disaster region is the focus of attention (FOA), which happens to be the object needed to process. Ittis algorithm [1]was used to extract the saliency map, then quickly located the regions which may contain disaster according to saliency. The recognition and early warning of disaster can be completed, quickly. This method was tested snowstorms and rolling stones are simulated, and gave the corresponding experimental results. Experiment results show the correctness and efficiency of introducing visual attention mechanism into road disaster monitor and early warning system. It is of great significance and practical value for reducing the computation and improving real-time performance of the total system.

• Periodical: Applied Mechanics and Materials (Volumes 385-386)
• Pages: 523-526
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.385-386.523
• Online since: August 2013
• Authors: Shu Yue Hua, Nan Feng Xiao
• Keywords: Disaster Recognition, Itti, ROI, Saliency Map, Visual Attention Mechanism

References

[1] Itti L, Koch C. Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.

DOI: 10.1109/34.730558

[2] LI Qun-bin, HUANG Hao-feng, XIAO Nan-feng. The design and implementation of video-image-based alarm system of road disaster [J]. Computer Engineering and Design, 2011, Vol. 32, NO. 10: 3442-3445. (in Chinese).

[3] XU Shi, WEN Han, XIAO Nan-feng. Based on the wireless video transmission road disaster monitoring system [J]. Journal of Chong qing University of Science and Technology (Natural Science). Vol. 25, NO. 10: 46-53, Oct. 2011. (in Chinese).

[4] TIAN Ming-hui. Visual attention mechanism modeling and the study of its application [D]. Hefei: University of Science and Technology of China. 2010. (in Chinese).

[5] J. -K. Tsotos, S. Culhane, W. -Y. Wai, Y. Lai, N. Davis and F. Nuflo. Modeling visual attention via selective tuning [J]. Artificial Intelligence, vol. 78, no 1, pp.507-545, Oct. (1995).

DOI: 10.1016/0004-3702(95)00025-9

[6] L. Itti. Models of bottom-up and top-down visual attention. Ph.D. dissertation, California Institute of Technology Pasadena, (2000).

[7] Koch C, Ullman S. Shift in selective visual attention: towards the underlying neural circuity [J]. Human Neurobiology, 1985, 4(4): 219-227.

[8] FENG Song-he, XU De, YANG Xu, WU Ai-min. A novel region-based image retrieval algorithm using selective visual attention model. In: Proc. of Int. Conf. on Advanced Concepts for Intelligent Vision-System (ACIVS'05), Antwerp, Belgium, Sep. 2005, LNCS 3708, 235-242.

DOI: 10.1007/11558484_30

[9] L Itti, C Koch. Computational modeling of visual attention. Nature Reviews Neuroscience, 2001, 1(3): 194-230.