Share Email Print

Journal of Applied Remote Sensing

Region of interest extraction based on multiscale visual saliency analysis for remote sensing images
Author(s): Yinggang Zhang; Libao Zhang; Xianchuan Yu
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Region of interest (ROI) extraction is an important component of remote sensing image processing. However, traditional ROI extraction methods are usually prior knowledge-based and depend on classification, segmentation, and a global searching solution, which are time-consuming and computationally complex. We propose a more efficient ROI extraction model for remote sensing images based on multiscale visual saliency analysis (MVS), implemented in the CIE L*a*b* color space, which is similar to visual perception of the human eye. We first extract the intensity, orientation, and color feature of the image using different methods: the visual attention mechanism is used to eliminate the intensity feature using a difference of Gaussian template; the integer wavelet transform is used to extract the orientation feature; and color information content analysis is used to obtain the color feature. Then, a new feature-competition method is proposed that addresses the different contributions of each feature map to calculate the weight of each feature image for combining them into the final saliency map. Qualitative and quantitative experimental results of the MVS model as compared with those of other models show that it is more effective and provides more accurate ROI extraction results with fewer holes inside the ROI.

Paper Details

Date Published: 6 October 2015
PDF: 15 pages
J. Appl. Rem. Sens. 9(1) 095050 doi: 10.1117/1.JRS.9.095050
Published in: Journal of Applied Remote Sensing Volume 9, Issue 1
Show Author Affiliations
Yinggang Zhang, Beijing Normal Univ. (China)
Libao Zhang, Beijing Normal Univ. (China)
Xianchuan Yu, Beijing Normal Univ. (China)

© SPIE. Terms of Use
Back to Top