Abstract
A hyperspectral remote sensing image data cube often contains dozens to hundreds of bands. This creates great difficulties in image data processing and target detection, which is known as “Hughes phenomenon”. Currently, there are great many methods of dimensionality reduction in the field of classification in the hyperspectral remote sensing image, but rarely in target detection. Thus, this paper introduces a new band removed selection (BRS) method to target detection for reducing dimensions in Hyperspectral, which includes the ways of “direct out” and “sort out” on the bad bands. And, a more optimized removed selection method was obtained after the integration of those two ways. This method not only plays the role of dimensionality reduction, but also can effectively improve the effect of target detection. From the experiment, the proposed BRS is proved to be effective and feasible with the actual hyperspectral images.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.