An Efficient Visual Saliency Analysis Model for Region-of-Interest Extraction in High-Spatial-Resolution Remote Sensing Images

摘要

Accurate region of interest (ROI) extraction is a hotspot of remote sensing image analysis. In this paper, we propose a novel ROI extraction method based on multi-scale hybrid visual saliency analysis (MHVSA) that can be divided into two sub-models: the frequency feature analysis (FFA) model and the multi-scale region aggregation (MRA) model. In the FFA sub-model, we utilize the human visual sensitivity and the Fourier transform to produce the local saliency map. In the MRA sub-model, saliency maps of various scales are generated by aggregating regions. A tree-structure graphical model is suggested to fuse saliency maps into one global saliency map. We obtain two binary masks by segmenting the local and global saliency maps and perform the logical AND operation on the two masks to acquire the final mask. Experimental results reveal that the MHVSA model provides more accurate extraction results.