A support vector data description approach to target detection in hyperspectral imagery

Wesam A. Sakla; Adel A. Sakla; Andrew Chan

doi:10.1117/12.818642

Translator Disclaimer

4 May 2009 A support vector data description approach to target detection in hyperspectral imagery

Wesam A. Sakla, Adel A. Sakla, Andrew Chan

Author Affiliations +

Proceedings Volume 7335, Automatic Target Recognition XIX; 73350C (2009) https://doi.org/10.1117/12.818642
Event: SPIE Defense, Security, and Sensing, 2009, Orlando, Florida, United States

Abstract

Spectral variability remains a challenging problem for target detection and classification in hyperspectral imagery (HSI). In this paper, we have applied the nonlinear support vector data description (SVDD) to perform full-pixel target detection. Using a pure target signature, we have developed a novel pattern recognition (PR) algorithm to train an SVDD to characterize the target class. We have inserted target signatures into an urban hyperspectral (HS) scene with varying levels of spectral variability to explore the performance of the proposed SVDD target detector in different scenarios. The proposed approach makes no assumptions regarding the underlying distribution of the scene data as do traditional statistical detectors such as the matched filter (MF). Detection results in the form of confusion matrices and receiver-operating- characteristic (ROC) curves demonstrate that the proposed SVDD-based algorithm is highly accurate and yields higher true positive rates (TPR) and lower false positive rates (FPR) than the MF.

Citation Download Citation

Wesam A. Sakla, Adel A. Sakla, and Andrew Chan "A support vector data description approach to target detection in hyperspectral imagery", Proc. SPIE 7335, Automatic Target Recognition XIX, 73350C (4 May 2009); https://doi.org/10.1117/12.818642

ACCESS THE FULL ARTICLE