Evaluation of visual attention models under 2D similarity transformations

ABSTRACT

The computational models of visual attention, originally proposed as cognitive models of human attention, nowadays are being used as front-ends to some robotic vision systems, like automatic object recognition and landmark detection. However, these kinds of applications have different requirements from those originally proposed. More specifically, a robotic vision system must be relatively insensitive to 2D similarity transformations of the image, as in-plane translations, rotations, reflections, and scales. In this paper several experiments with two visual attention models publicly available are described. The results show that the best known model, called NVT, is extremely sensitive to these 2D similarity transformations. Therefore, a new visual attention model, called NLOOK, is proposed and validated with the same invariance criteria, and the results show that NLOOK is less sensitive to these kind of transformations than the other two models. Besides, NLOOK can select better fixations according to a redundancy criterion. Thus, the proposed model is an excellent tool to be used in robot vision systems.

REFERENCES

• 1: Shigeru Ando, Image Field Categorization and Edge/Corner Detection from Gradient Covariance, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.2, p.179-190, February 2000 [doi>10.1109/34.825756]
• 2: M. Behrmann and C. Haimson. The cognitive neuroscience of visual attention. Current Opinion Neurobiology, 9(2): 158--163, 1999.
• 3: P. J. Burt, T. Hong, and E. H. Adelson. The laplacian pyramid as a compact image code. IEEE Trans. Communications, 31(4): 532--540, Apr. 1983.
• 4: J. G. Daugman. Complete discrete 2-d gabor transforms by neural networs for image analysis and compression. IEEE Trans. Acoustics, Speech, and Signal Processing, 36(7): 1169--1179, July 1988.
• 5: R. Desimone and J. Duncan. Neural mechanisms of selective visual attention. Neuroscience, 18: 193--222, 1995.
• 6: Bruce A. Draper , Albert Lionelle, Evaluation of selective attention under similarity transformations, Computer Vision and Image Understanding, v.100 n.1-2, p.152-171, October 2005 [doi>10.1016/j.cviu.2004.08.006]
• 7: S. Frintrop. VOCUS: A Visual Attention System for Object Detection and Goal-directed Search. Ph.d. thesis, Rheinische Friedrich-Wilhelms-Universitat Bonn, Germany, Jan. 2006.
• 8: S. Greenspan, S. Belongie, R. Goodman, P. Perona, S. Raksh, and C. Anderson. Overcomplete steerable pyramid filters and rotation invariance. In Proc. IEEE Computer Vision Pattern Recognition (CVPR), pages 222--228, Seattle, WA, 1994.
• 9: M. R. Heinen and P. Engel. Visual selective attention model for robot vision. In Proc. 5th IEEE Latin American Robotics Symposium (LARS'08), Salvador, BH, Brazil, Oct. 2008.
• 10: L. Itti. Models of Bottom-Up Attention and Saliency, pages 576--582. Neurobiology of Attention. San Diego, CA, 2005.
• 11: L. Itti and K. Christof. Computational modelling of visual attention. Nature Reviews, 2: 194--203, Mar. 2001.
• 12: Laurent Itti , Christof Koch , Ernst Niebur, A Model of Saliency-Based Visual Attention for Rapid Scene Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.20 n.11, p.1254-1259, November 1998 [doi>10.1109/34.730558]
• 13: R. M. Klein. Inhibition of return. Trends in Cognitive Sciences, 4(4): 138--147, Apr. 2000.
• 14: C. Koch and S. Ullman. Shifts in selective visual attention: Toward the underlying neural circuitry. Human Neurobiology, 4(4): 219--227, 1985.
• 15: Y.-H. Liu and X.-J. Wang. Spike-frequency adaptation of a generalized leaky integrate-and-fire model neuron. Journal of Computational Neuroscience, 10: 25--45, 2001.
• 16: David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, v.60 n.2, p.91-110, November 2004 [doi>10.1023/B:VISI.0000029664.99615.94]
• 17: M. C. Mozer and M. Sitton. Computational modeling of spatial attention. Attention, pages 341--395, 1998.
• 18: N. Ouerhani, A. Bur, and H. Hügli. Visual attention-based robot self-localization. In Proc. European Conf. Mobile Robotics (ECMR'05), pages 8--13, Ancona, Italy, Sept. 2005.
• 19: A. M. Treisman and G. Gelade. A feature-integration theory of attention. Cognitive Psychology, 12: 97--136, 1980.
• 20: John K. Tsotsos , Sean M. Culhane , Winky Yan Kei Wai , Yuzhong Lai , Neal Davis , Fernando Nuflo, Modeling visual attention via selective tuning, Artificial Intelligence, v.78 n.1-2, p.507-545, Oct. 1995 [doi>10.1016/0004-3702(95)00025-9]
• 21: A. P. Witkin. Scale-space filtering. In Proc. Int. Joint Conf. Artificial Intelligence, pages 1019--1022, Germany, 1983.