Object Detection Method Based on"What"and"Where"Information
Lingzhi Liao · Dianzi xuebao · 2007
Inspired by the theory of two visual pathways,a novel model for object detection is proposed based onwhatandwhereinformation.Context-centeredwhereinformation is used to control top-down attention,and guide bottom-up attention which is driven bywhatinformation.The procedure of top-down attention can be divided into two stages:pre-attention and focus attention.In the stage of pre-attention,whereinformation 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 withwhatinformation,at- tention is directed to the region that is most likely to contain the object and series of salient regions for samples are detected.Experi- mental results with natural images demonstrate its effectiveness.