Mixed Pixel Resolution by Evolutionary Algorithm: A Survey
Er. Mittu Mittal1, Er. Gagandeep Kaur2
1Er. Mittu Mittal, M.Tech, CSE Department of CSE, RIMT Institutions, Mandi Gobindgarh, Punjab, India.
2Er. Gagandeep Kaur, Department of CSE, RIMT Mandi Gobindgarh, Punjab, India.
Manuscript received on May 19, 2013. | Revised Manuscript received on June 10, 2013. | Manuscript published on June 30, 2013. | PP: 197-199 | Volume-2, Issue-5, June 2013. | Retrieval Number: E1782062513/2013©BEIESP
Open Access | Ethics and Policies | Cite
© 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: Now a day’s Remote Sensing is a mature research area. Remote sensing is defined as a technique for acquiring the information about an object without making physical contact with that image via remote sensors. But the major problem of remotely sensed images is mixed pixel which always degrades the image quality. Mixed pixels are usually the biggest reason for degrading the success in image classification and object recognition. Another major problem is the decomposition of mixed pixels precisely and effectively. Remote sensing data is widely used for the classification of types of features such as vegetation, water body etc but the problem occurs in tagging appropriate class to mixed pixels. In this paper we attempted to present an approach for resolving the mixed pixels by using optimization algorithm i.e. Biogeography based optimization. The main idea is to tag the mixed pixel to a particular class by finding the best suitable class for it using the BBO parameters i.e. Migration and Mutation.
Keywords: Biogeography based optimization, Evolutionary algorithms, mixed pixel, Migration, Mutation, Remote Sensing.