Can Saliency Map Models Predict Human Egocentric Visual Attention?
The validity of using conventional saliency map models to predict human attention was investigated for video captured with an egocentric camera. Since conventional visual saliency models do not take into account visual motion caused by camera motion, high visual saliency may be erroneously assigned to regions that are not actually visually salient. To evaluate the validity of using saliency map models for egocentric vision, an experiment was carried out to examine the correlation between visual saliency maps and measured gaze points for egocentric vision. The results show that conventional saliency map models can predict visually salient regions better than chance for egocentric vision and that the accuracy decreases significantly with an increase in visual motion induced by egomotion, which is presumably compensated for in the human visual system. This latter finding indicates that a visual saliency model is needed that can better predict human visual attention from egocentric videos.
KeywordsVisual Attention Visual Saliency Gaussian Pyramid Egocentric Perspective Scene Camera
Unable to display preview. Download preview PDF.
- 2.Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Human neurobiology 4, 219–227 (1985)Google Scholar
- 4.Itti, L., Dhavale, N., Pighin, F., et al.: Realistic avatar eye and head animation using a neurobiological model of visual attention. In: SPIE 48th AnnualInternational Symposiumon Optical Science and Technology, vol. 5200, pp. 64–78 (2003)Google Scholar
- 6.Cerf, M., Harel, J., Einhäuser, W., Koch, C.: Predicting human gaze using low-level saliency combined with face detection. Advances in Neural Information Processing Systems 20, 241–248 (2008)Google Scholar
- 7.Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. Advances in Neural Information Processing Systems 19, 545–552 (2006)Google Scholar
- 8.Costa, L.: Visual saliency and atention as random walks on complex networks. ArXiv Physics e-prints (2006)Google Scholar
- 9.Wang, W., Wang, Y., Huang, Q., Gao, W.: Measuring visual saliency by site entropy rate. In: IEEE Computer Vision and Pattern Recognition, pp. 2368–2375 (2010)Google Scholar
- 16.Greenspan, H., Belongie, S., Goodman, R., Perona, P., Rakshit, S., Anderson, C.: Overcomplete steerable pyramid filters and rotation invariance. In: IEEE Computer Vision and Pattern Recognition, pp. 222–228 (1994)Google Scholar
- 17.nac Image Technology Inc.: EMR-9 (2008), http://www.nacinc.com/products/Eye-Tracking-Products/EMR-9/
- 18.Howard, I.: The optokinetic system. The Vestibulo-ocular Reflex and Vertigo, 163–184 (1993)Google Scholar