Region of Interest Extraction based on Hybrid Salient Detection for Remote Sensing Image
J. Maheswarreddy1, S.A.K. Jilani2
1J. Maheswarreddy, Research Scholar, Department of ECE, Rayalaseema University, Kurnool (A.P), India.
2Dr. S.A.K. Jilani, Professor, Department of ECE, Madanapalli Institute of Technology & Science, (A.P), India.
Manuscript received on 05 February 2019 | Revised Manuscript received on 18 February 2019 | Manuscript Published on 04 March 2019 | PP: 80-86 | Volume-7 Issue-5S2 January 2019 | Retrieval Number: ES2010017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Remote sensing images have huge amount of information in it due to use of high resolution cameras and sensors. Region of interest (ROI) is defined as the regions which draw the attention of viewer at first sight and they are the focal point of the image. ROI selection in remote sensing images allows the viewer to search for specific objects in the region. Traditional approaches for ROI selection are computationally complex and inaccurate. In this work, a hybrid approach which combines the best of frequency domain analysis and Super pixel based spatially weighted intensity contrasting is proposed for selecting the ROI in remote sensing images. Compared to previous methods the proposed hybrid ROI selection is able to extract the ROI accurately.
Keywords: ROI, Saliency Map, Gaussian Pyramid, Frequency Domain Analysis, Quaternion.
Scope of the Article: Remote Sensing