Bayesian Visual Inference and Attention
Jieyu Zhao, You Jian · 2009
The massive amount of visual inputs could easily go beyond the systempsilas computational limit. Visual attention provides an efficient way to discard the trivial inputs and achieve good performance. In this paper we develop a unified and consistent theoretical framework for the visual attention and inference with Bayesian decision theory. A visual attention scheme is simulated with an artificial retina mimicking biological ones. We test our model on a real world video clip. The experimental results indicate the promise of this visual attention model in complicated vision applications.