Dharambhai Shah

In the remotely sensed hyperspectral image, separating pure materials from the mixed pixels and estimating the abundances of each material in the mixing is called hyperspectral unmixing. Hyperspectral unmixing is executed broadly in three steps. The first step is subspace identification which finds the number of endmembers present in the hyperspectral data. The second step is endmember extraction which extracts materials from the data. The last step is abundance estimation which estimates the proportions of each material in the mixing. In these three steps, endmember extraction is very challenging. As per the literature available for endmember extraction, many researchers have used convex geometry to address the endmember extraction. A novel algorithm, Dispersion Index based Endmember Extraction (DIEE) is proposed which applies convex geometry based on the Dispersion Index in this paper. The DIEE algorithm is compared with prevailing algorithms on a real and simulated dataset. It is observed from the simulation that the proposed algorithm is giving a worthy performance on both real datasets and a noisy simulated dataset.

Hyperspectral unmixing is a source separation problem. The spectral unmixing process is simply the composition of the three-step chain (subspace identification, endmember extraction and abundance estimation). A critical step in this chain is endmember extraction which finds endmembers from the image for the estimation of abundances. In this paper, a novel framework is proposed which uses the concept of Pearson's correlation coefficient and convex geometry. The novel framework extracts endmembers from the convex set of the two bands extracted using Pearson's correlation coefficient so it is named as Pearson's correlation coefficient-based convex geometry for endmember extraction (PCGE). This PCGE framework is different from other commonly used frameworks due to only two bands convex geometry. Due to only two bands, the computation time for the proposed framework is less. The proposed framework is applied to a synthetic dataset and four popular real hyperspectral datasets. In the simulation results, the proposed framework is compared with other popular frameworks based on standard evaluation parameters (spectral angle error, spectral information divergence and normalised cross-correlation). It has been observed from the simulation results that the proposed framework outperforms popular frameworks. It has been also observed that the proposed framework takes less time than others for extracting endmembers.

Spectral unmixing is an important problem for remotely sensed hyperspectral data exploitation. Automatic spectral unmixing can be viewed as a three-stage problem, where the first stage is subspace identification, the next one is endmember extraction, and the final one is abundance estimation. In this sequence, endmember extraction is the most challenging problem. Many researchers have attempted to extract endmembers from hyperspectral images using spectral information only. However, it is well known that the inclusion of spatial information can improve the endmember extraction task. In this paper, we introduce a new endmember extraction algorithm that exploits both spectral and spatial information. A main innovation of the proposed algorithm is that spatial information is exploited using entropy, while spectral information is exploited using convex set optimization. In the literature, none of the spatial-spectral algorithms has used entropy as spatial information. The inclusion of this entropy-based spatial information improves the accuracy of the endmember extraction process. The results obtained by the proposed algorithm are compared (using a variety of metrics) with those obtained by other state-of-the-art methods, using both synthetic and real datasets. Our experimental results demonstrate that the proposed algorithm outperforms many available algorithms.

The Journal of Applied Remote Sensing (JARS) is an online journal that optimizes the communication of concepts, information, and progress within the remote sensing community to improve the societal benefit for monitoring and management of natural disasters, weather forecasting, agricultural and urban land-use planning, environmental quality monitoring, ecological restoration, and numerous other commercial and scientific applications.

Due to low spatial resolution, intimate mixing of materials and multiple scattering, pixels are of mixed types in hyperspectral images. Analyzing these mixed pixels using spectral characteristics is Spectral Mixture Analysis (SMA). SMA finds the number of pure endmembers along with their pure signature and fractions of materials in the image. In this analysis, the critical part is extracting pure endmembers from the image itself. There are many attempts by researchers to extract endmembers but none of them are considering the quality of each band. In this paper, a novel Endmember Extraction using Band Quality (EEBQ) is proposed which uses the concept of band quality and convex geometry. The proposed algorithm is examined on synthetic and real benchmark datasets, which demonstrates its worthy performance in terms of spectral angle error, spectral information divergence, and normalized cross-correlation.

Target detection is a challenge to detect and classify objects in hyperspectral images. In this paper, a total of six algorithms broadly classified in type I and type II are used to detect targets such as metal, roof, and dirt. Type I algorithm differs from type II as in type II algorithm both target spectra and non-background spectra are used whereas in type I algorithm only target spectra is used as an external input. Vertex Component Analysis (VCA) is used to generate background spectra in type II algorithm. Two different hyperspectral data set such as Pavia and Urban are used for target detection. Detailed analysis of the output of the six methods shows that the wide range of output score plays an important role in the determination of threshold to detect any target. One of the type II method Orthogonal Subspace Projection (OSP) gives the best wide dynamic range compared to other techniques.