Building cognition method based on human images cognition mechanism in high resolution PolSAR images

PolSAR images have been used extensively for various surface features recognition and buildings recognition is an important research topic of PolSAR image interpretation. Traditional methods are only based on PolSAR image characteristics and lack subjective knowledge of human image cognition, making low target recognition rate and algorithm redundancy. To overcome this shortcoming, based on human image cognition mechanism, a new method for buildings recognition in PolSAR images is proposed in this paper. The proposed method utilizes hierarchical cognition model to identify buildings: the first layer is visual cognition and the second layer is logical cognition. In visual cognition, visual sensitive features are extracted and integrated under the guidance of a priori knowledge to derive preliminary recognition results. In logical cognition, based on the results from first process, fuzzy logic theory and Neural Network Model are both utilized to identify buildings precisely. The whole cognition procedure is guided by the knowledge, which is represented in accordance with production rules. Experiments are conducted over the EMISAR L-band PolSAR data, the E-SAR L-band PolSAR data and Convair-SAR C-band PolSAR data. The results show that the proposed method can identify buildings from PolSAR images effectively and precisely.