In this paper, we propose an incremental object perception model that is based on human-like selective attention. The proposed model integrates an object biased attention scheme with an incremental object representation mechanism. The object biased attention scheme can selectively pay attention to the candidates of an object in dynamic scenes based on a bottom-up selective attention hi conjunction with a top-down biased attention mechanism for a specific object. An incremental principal component analysis (IPCA) is applied to extract efficient feature information for object representation. Also, a generative model based on an incremental Bayesian parameter estimation is used to perceive arbitrary objects in the selected areas. Combining an object biased attention with an incremental object perception model, the developed system can not only pay attention to a specific target object but also memory the characteristics of arbitrary objects by incremental manner. Experimental results show that the developed system generates good performance in successfully focusing on the target objects as well as incrementally perceiving arbitrary objects in natural scenes.
展开▼
