Building detection based on human visual cognition mechanism using PolSAR images

Abstract

A building detection method for PolSAR image, which is based on the human's visual cognition mechanism, is proposed in this paper. Study on human's visual cognition mechanism is done and it is found that human's visual cognition system is efficient and intelligent in target detection due to efficient processing units and structure, as well as complete experience and knowledge. Considering both the human's visual cognition mechanism and PolSAR image characteristics, the proposed building detection method selects appropriate primary features from PolSAR image, integrates primary features to derive interest map under the guidance of priori knowledge, and then detects building areas based on the interest map. Scale filter and shape judgment are also utilized to remove false alarms. The EMISAR L-band PolSAR data is used to validate the proposed method and the results show that the proposed method can effectively detect building areas from PolSAR images.