Variogram Fractal Dimension Based Features for Hyperspectral Data Dimensionality Reduction
- PDF / 281,368 Bytes
- 10 Pages / 547.087 x 737.008 pts Page_size
- 60 Downloads / 199 Views
RESEARCH ARTICLE
Variogram Fractal Dimension Based Features for Hyperspectral Data Dimensionality Reduction Kriti Mukherjee & Jayanta K Ghosh & Ramesh C. Mittal
Received: 19 November 2011 / Accepted: 19 July 2012 / Published online: 4 August 2012 # Indian Society of Remote Sensing 2012
Abstract In this paper a new approach for fractal based dimensionality reduction of hyperspectral data has been proposed. The features have been generated by multiplying variogram fractal dimension value with spectral energy. Fractal dimension bears the information related to the shape or characteristic of the spectral response curves and the spectral energy bears the information related to class separation. It has been observed that, the features provide accuracy better than 90 % in distinguishing different land cover classes in an urban area, different vegetation types belonging to an agricultural area as well as various types of minerals belonging to the same parent class. Statistical comparison with some conventional dimensionality reduction methods validates the fact that the proposed method, having less computational burden than the conventional methods, is able to produce classification statistically equivalent to those of the conventional methods. Keywords Hyperspectral . Fractal . Variogram . Dimensionality reduction . Computational complexity K. Mukherjee (*) : J. K. Ghosh Civil Engineering Department, Indian Institute of Technology, Roorkee, Uttarakhand 247667, India e-mail: [email protected] R. C. Mittal Mathematics Department, Indian Institute of Technology, Roorkee, Uttarakhand 247667, India
Introduction Spectral imaging of the earth using hyperspectral sensors designed on the principle of charged coupled devices (CCD) is a recent advancement of remote sensing. These CCDs are able to detect the energy reflected from moving earth objects in very narrow wavelength bands because of their high signal to noise ratio and very small discharge time. One image is obtained at each band of wavelengths and the total number of images in each scene is equal to the number of bands the sensors are designed with (generally within 10 and 1000). Thus, for each plot on the ground surface that is represented by the spatial resolution of the sensor, intensity values equal to the number of bands, determined by the spectral resolution of the sensor, can be obtained. The detailed spectral response of a pixel assists in providing accurate and precise information of the ground cover under measurement. This makes hyperspectral data useful to study subtly different classes and deal with applications like target recognition, anomaly detection and background characterization. Due to the huge data volume associated with each scene of hyperspectral data, this data type requires more specific attention to the complexity of data receiving, storing, transforming and processing. In particular, due to the high dimensionality of this data the analysis of the images becomes a complex problem. Some researchers studied the characteristics of the high
Data Loading...
