A Model of Target Detection in Variegated Natural Scene Based on Visual Attention

Abstract:

Less of edge and texture information existed in traditional visual attention model in target detection due to extract only the color, brightness, directional characteristics, as well as direct sum fusion rule ignoring the difference in each characteristic. A improved model is proposed by introduced the edge, texture and the weights in fusion rules in visual computing model. First of all, DOG is employed in extracting the edge information on the basis of obtained brightness feature with multi-scale pyramid using the ITTI visual computing model; the second, the non-linear classification is processing in the six parameters of the mean and standard deviation of the gray contrast, relativity and entropy based on the GLCM; finally, the fusion rule of global enhancement is employed for combination of multi-feature saliency maps. The comparison experimental results on variegated natural scene display, relative to the ITTI calculation model, there is more effective with the application of the model in this paper, the interested area and the order to shift the focus are more in line with the human visual perception, the ability of target detection is strengthening in variegated natural scene. Further shows that the proposed edge and texture features introduced in the primary visual features to be effective, the introduction of each feature significant weighting factor is reasonable in the feature map integration phase.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1213-1218
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1213
• Online since: July 2013
• Authors: Zhan Feng Wang, Hai Tao Su, Hong Shu Chen, Zhi Yi Hu, Jie Liang Wang
• Keywords: Feature Extraction, Support Vector Machine (SVM), Target Detection, Texture Feature, Visual Attention

References

[1] L. Itti,C. Koch, and E. Niebur: IEEE Trans. on PA MI. 1998, 20(11): 1254-1259.

[2] L. Itti and C. Koch: Nature Reviews: Neuroscience, Volume 2, March 2001: 1-11.

[3] L. Itti and C. Koch:J. of Electronic Imaging, 2001, 10(1): 161-169.

[4] L. Itti and C. Koch: In Proc. RTO/SCI-12 on S. and T. A., Netherlands, 1999: 3. 1-3. 10.

[5] L. Itti,C. Gold,C. Koch: http: /ilab. usc. edu/publications/bu/html.

[6] YU Ying. Researches on Computational Modeling of Visual Attention and Its Applications. SHANGHAI: FUDAN Uni., 2010, 7-9(in Chinese).

[7] Zhao Cairong. reature Extraction Based on Graph Embedding and Visual Atention. Nanjing: Uni. of Sci. and Tech., 2011, 52-53(in Chinese).

[8] Li Jie. Research on Directional Multi-scale Image Analysis and its Applications. Chengdu: Uni. of Elec. Sci. and Tech., 2007, 77-85(in Chinese).

[9] Li Wenyan. Target Detection Method Based on Visual Attention Mechanism. Chongqing: Chongqing Uni., 2010, 22-24(in Chinese).

[10] Robert,M. Haralick,K. Shanmugam, et al: IEEE Trans. on Sys. Man. and Cyb., 1973, 610-621.

[11] V. Vapnik: IEEE Trans. on Neural Networks, 1999, 10(5): 988-999.

[12] V. Vapnik: I. Sym. on Cir. and Sys., 2000, 28-31.

[13] P.C. Fernando,B. Olivier: IEEE Sig. Proc. Mag., 2004, vol. 5: 57-66.

[14] Xie Chunlan. Study on Visual Attention Model and Its Application in Target Detection. Chongqing: Chongqing Uni., 2009(in Chinese).