PROJECT TITLE :
Hierarchical Suppression Method for Hyperspectral Target Detection
Target detection is an important application in the hyperspectral image processing field, and several detection algorithms have been proposed in the past decades. Some traditional detectors are designed based on the statistical information of the target and background spectra, and their performances have a tendency to be affected by the spectral quality. Some previous ways address this problem by refining the target spectra to create the detector strong. In this paper, instead of doing similar to this, we tend to propose a replacement hierarchical method to suppress the backgrounds whereas preserving the target spectra, with the purpose of boosting the performance of ancient hyperspectral target detector. The proposed method consists of various layers of classical constrained energy minimization (CEM) detectors. In each layer of detection, the CEM's output of every spectrum is reworked by a nonlinear suppression perform and then thought-about as a coefficient to impose on this spectrum for the subsequent round of iteration. To our data, such hierarchical structure is proposed for the primary time. Theoretically, we prove the convergence of the proposed algorithm, and we have a tendency to additionally provide a theoretical clarification on why we will acquire the gradually increasing detection performance through the hierarchical suppression method. Experimental results on 2 real hyperspectral pictures and one artificial image counsel that our technique significantly improves the performance of the first CEM detection algorithm and additionally outperforms alternative classical and recently proposed hyperspectral target detection algorithms.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here