A Performance Analysis of Unsupervised Change Detection Method for Hyper spectral Images

The most significant recent breakthrough in remote sensing has been the development of hyper spectral sensors and software to analyze the resulting image data. Fifteen years ago only the spectral remote sensing experts had access to hyper spectral images or many software tools to take advantage of such images. Over the past decade hyper spectral image analysis has matured into one of the most powerful and fastest growing technologies in the field of remote sensing. The “hyper” in hyper spectral means “over” as in “too many” and refers to the large number of measured wavelength bands. Hyper spectral images are mainly spectrally over determined, which means that they provide ample spectral information to identify and distinguish spectrally unique materials. Hyper spectral imagery provides the potential for more accurate and detailed information extraction than possible with any other type of remotely sensed data. In order to detect the changes that may occur due to various natural hazards like earthquake, floods or many more in several areas, there is an efficient way to identify these changes without visiting the sites by analyzing the changes through remote sensing satellites like Landsat, SPOT etc. which provides digital images of hyper spectral images and through change detection algorithms these changes may become easy to detect. To complete this goal, feature extraction is considered as an essential-weapon to analyze an image properly. In this paper, different digital lesion images have been analyzed based on unsupervised image acquisition, pre-processing, and dimension reduction techniques.. After this, a graphical user interface and independent component analysis has been designed for the probability detection and then a comprehensive discussion has been explored based on the obtained results. Keywords— Hyper spectral image analysis, Image Acquisition, Feature Extraction, Graphical User Interface, target detection, remote sensing, change detection algorithms. __________________________________________________*****_________________________________________________