Multi-scale hybrid saliency analysis for region of interest detection in very high resolution remote sensing images
作者：
Highlights：
• Novel multi-scale frequency analysis is proposed for intensity feature analysis.
• Multi-scale analysis is introduced to extract color and orientation features.
• Spectral information content is proposed for spectral feature analysis.
• Propose a novel weight multi-scale feature fusion method
• Synthesize frequency and space domain features in proposed algorithm frame.
摘要
•Novel multi-scale frequency analysis is proposed for intensity feature analysis.•Multi-scale analysis is introduced to extract color and orientation features.•Spectral information content is proposed for spectral feature analysis.•Propose a novel weight multi-scale feature fusion method•Synthesize frequency and space domain features in proposed algorithm frame.
论文关键词：Computer vision,Remote sensing image processing,Region of interest,Visual attention,Saliency analysis
论文评审过程：Received 11 October 2013, Revised 21 September 2014, Accepted 22 December 2014, Available online 29 December 2014.
论文官网地址：https://doi.org/10.1016/j.imavis.2014.12.002
