Quantitative Analysis of Mixed Pixels in Hyperspectral Image Using Fractal Dimension Technique
- PDF / 1,414,470 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 100 Downloads / 154 Views
RESEARCH ARTICLE
Quantitative Analysis of Mixed Pixels in Hyperspectral Image Using Fractal Dimension Technique Ajay Kumar Patel1
•
Jayanta Kumar Ghosh1
Received: 8 April 2019 / Accepted: 12 August 2020 Ó Indian Society of Remote Sensing 2020
Abstract In this paper, a novel approach for identification of the components of a mixed pixel along with the quantitative analysis of the determined components of hyperspectral data has been proposed. The overall method is divided into three phases. First, the spectral sensitivity curves (SSCs) of the identified endmembers soil, water and vegetation using N-FINDR algorithm are generated. Next, the percentage of the mixture of the endmembers is computed for calculating the fractal dimension (FD). Afterward, the FD of SSCs is utilized for determining the mathematical model of the obtained curve. In order to verify that the adjacent pixels belong to the class identified using N-FINDR algorithm, two algorithms, i.e., spectral angle mapper and spectral information divergence, are employed for determining the spectral similarity of the mixed pixel with the reference spectrum. Lastly, the quantitative analysis of the SSC of the mixed pixel is performed by using the corresponding calculated FD in the derived mathematical model. The performance of the mathematical model is evaluated on the airborne visible infrared imaging spectrometer image data, and the outcome shows that the proposed framework achieves very promising results with a small number of mixed pixel samples. Keywords Fractal dimension Hyperspectral image Mixed pixel quantification Spectral unmixing Spectral sensitivity curve
Introduction Hyperspectral imaging technique plays a vital role in several remote sensing applications such as object identification, urban mapping, mineral detection, environment monitoring and defense purposes. The classification of mixed pixel in hyperspectral image is a key issue. Over the decades, the classification of mixed pixels of hyperspectral data has been an active topic of research. The phenomena of mixing of endmembers rely on several factors such as the spectral properties of materials, resolution of the sensors and how the real earth objects react with incident light. However, these problems can be resolved using the spectral unmixing techniques for identifying the endmember & Ajay Kumar Patel [email protected] Jayanta Kumar Ghosh [email protected] 1
Geomatics Engineering Group, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand 247667, India
spectral components along with their abundance fractions (Keshava and Mustard 2002). In general, the process of unmixing can be carried out either sequentially or simultaneously (Bioucas-Dias et al. 2012) and categorized into linear mixture model (LMM) or nonlinear mixture model (NLMM) (Heylen et al. 2014). The LMM is often relevant due to its competence and is well found in most classification techniques. Conventional endmember extraction techniques include the pixel purity index (Boardman et al. 1995), the
Data Loading...
