基于what和where信息的目标检测方法  

Object Detection Method Based on"What"and"Where"Information

作　　者：田媚[1] 罗四维[1] 廖灵芝[1] 

机构地区：[1]北京交通大学计算机与信息技术学院,北京100044

出　　处：《电子学报》2007年第11期2055-2061,共7页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60373029);国家教育部博士点基金(N0.20050004001)

摘　　要：根据视觉系统两条通路理论,提出了一种基于what和where信息的目标检测方法.采用以环境为中心的where信息进行自顶向下的注意控制,指导what信息驱动的自底向上的注意.自顶向下的注意包括预注意和集中注意两个阶段,预注意依据where信息为特定目标出现与否提供先验,做出是否继续搜索的判定.集中注意的结果与what信息相结合,将注意指向目标最有可能出现的图像区域,并得到一系列样本显著区域.应用于多幅自然图像的实验结果证明了算法的有效性.Inspired by the theory of two visual pathways,a novel model for object detection is proposed based on＂what＂and＂where＂information.Context-centered＂where＂information is used to control top-down attention,and guide bottom-up attention which is driven by＂what＂information.The procedure of top-down attention can be divided into two stages：pre-attention and focus attention.In the stage of pre-attention,＂where＂information can be used to provide the prior knowledge of presence or absence of objects which decides whether search operation is followed.By integrating the result of focus attention with＂what＂information,attention is directed to the region that is most likely to contain the object and series of salient regions for samples are detected.Experimental results with natural images demonstrate its effectiveness.

关 键 词：自顶向下的注意 where信息 what信息 目标检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]