Comparative Assessment of Some Target Detection Algorithms for Hyperspectral Images

Manoj K. Arora; Shweta Bansal; Sangeeta Khare; Kiran Chauhan

doi:10.14429/dsj.63.3764

Manoj K. Arora Indian Institute of Technology Roorkee, Roorkee
Shweta Bansal Indian Institute of Technology Roorkee, Roorkee
Sangeeta Khare Defence Electronics Applications Laboratory, Dehradun
Kiran Chauhan Defence Electronics Applications Laboratory, Dehradun

DOI: https://doi.org/10.14429/dsj.63.3764

Keywords: Hyperspectral images, target detection receiver operating characteristic

Abstract

Target detection is of particular interest in hyperspectral image analysis as many unknown and subtle signals (spectral response) unresolved by multispectral sensors can be discovered in hyperspectral images. The detection of signals in the form of small objects and targets from hyperspectral sensors has a wide range of applications both civilian and military. It has been observed that a number of target detection algorithms are in vogue; each has its own advantages and disadvantages and assumptions. The selection of a particular algorithm may depend on the amount of information available as per the requirement of the algorithm, application area, the computational complexity etc. In the present study, three algorithms, namely, orthogonal subspace projection (OSP), constrained energy minimization (CEM) and a nonlinear version of OSP called kernel orthogonal subspace projection (KOSP), have been investigated for target detection from hyperspectral remote sensing data. The efficacy of algorithms has been examined over two different hyperspectral datasets which include a synthetic image and an AVIRIS image. The quality of target detection from these algorithms has been evaluated through visual interpretation as well as through receiver operating characteristic (ROC) curves. The performance of OSP algorithm has been found to be better than or comparable to CEM algorithm. However, KOSP out performs both the algorithms.

Defence Science Journal, 2013, 63(1), pp.53-62, DOI:http://dx.doi.org/10.14429/dsj.63.3764

Author Biographies

Manoj K. Arora, Indian Institute of Technology Roorkee, Roorkee

Prof. Manoj K. Arora obtained his BE (Civil Engineering) from PEC Chandigarh, ME (Survey and Photogrammetry) from University of Roorkee and PhD (Remote Sensing) from University of Wales Swansea (UK) in 1984, 1986 and 1996 respectively. Currently working as Professor of Geomatics Engineering in the Department of Civil Engineering. He has published about 180 research papers in reputed journals and conference proceedings. He has guided 11 Doctoral and 50 Master’s theses, has published two books. His research interests include: Remote sensing and GIS, digital image processing, land cover mapping and disaster management applications.

Shweta Bansal, Indian Institute of Technology Roorkee, Roorkee

Ms Shweta Bansal graduated in computer science and engineering from VIET in 2008 and MTech (Civil) from IIT Roorkeein 2010. Currently she is working as a software engineer at EDA company Atrenta Pvt Limited, Noida. Her research interests include: Multispectral and hyperspectral image analysis, image processing, detection of small and rare objects using hyperspectral remote sensing.

Sangeeta Khare, Defence Electronics Applications Laboratory, Dehradun

Dr Sangeeta Khare received her MSc (Mathematics) from Allahabad University and PhD (Mathematics) from Indian Institute of Technology Kanpur. She is working currently as Scientist ‘G’ in Image Analysis Center of Defence Electronics Applications Laboratory, Dehradun. Her current research interest include development of techniques and software for Hyper spectral data processing and high level analysis of satellite images as well as application of soft computing in image analysis.