Enhancing Hyperspectral Endmember Extraction Using Clustering and Oversegmentation-Based Preprocessing

Abstract

Spectral mixture analysis (SMA) is an effective tool in recognition of unique spectral signatures of materials called endmembers and estimating their percentage of existence (abundance fractions). Most approaches designed in endmember extraction process are established by applying the spectral information of the dataset and, thus, tend to neglect the existing spatial correlation between adjacent pixels. Although several preprocessing modules have been developed by incorporating both spatial and spectral properties prior to spectral-based endmember extraction algorithms (EEs), they still encounter several challenges. Hence, in this paper, we propose an appropriate clustering and oversegmentation-based preprocessing (COPP) by greatly benefiting from the integration of spatial and spectral information. Moreover, a novel top-down oversegmentation (TDOS) algorithm is developed which can recognize small oversegments with high spatial correlation. Our scheme removes oversegments located at spatial border of cluster regions. Average spectral vectors of determined spatially homogenous oversegments are considered so that their spectral purity scores are calculated. COPP identifies spatially homogenous zones with the greatest spectral purity scores. Pixels of these regions are more likely to be adopted as endmembers by means of subsequent EEs. COPP can take advantage of degrading local spectral variability and noise power. The main contribution of this paper is the enhanced computational performance of EE as well as the precise reconstruction of the original hyperspectral scene besides its appropriate recognition of endmembers' spectral signatures. The effectiveness of our design and its validation are appraised with the state-of-the-art strategies on a synthetic and AVIRIS real hyperspectral datasets.

Comparison of Image Endmember- and Object-Based Classification of Very-High-Spatial-Resolution Unmanned Aircraft System (UAS) Narrow-Band Images for Mapping Riparian Forests and Other Land Covers

“…Mean spectra were calculated from each superpixel, and constrained non-negative matrix factorization was applied to the mean spectra matrix to extract endmembers. Similar approaches are found in [54][55][56][57]. Note that all of these studies utilize different segmentation algorithms to extract homogeneous segments, and they employ different EEAs on those segmentation results to determine endmembers and calculate abundance images.…”

Remote Sensing Satellite Image Processing Techniques for Image Classification: A Comprehensive Survey

“…[25]. It takes low processing and produced high reconstruction accuracy compared to Landweber method but results in low accuracy for duality maps Reconstruction technique based on 2-D truncated singular value decomposition (TSVD) [26] method to enhance spatial features reduces the noise levels (RMSE and r values). It is robust and is compatible for hardware implementation.…”

Interference-Suppressed and Cluster-Optimized Hyperspectral Target Extraction Based on Density Peak Clustering

“…With the development of hyperspectral processing technology, a series of classic endmember extraction algorithms [16][17][18][19][22][23][24][25][27][28][29][30][31][32][33][34] have been proposed successively. In terms of the sequence of endmember extraction, there are mainly parallel endmember extraction and sequential endmember extraction [16].…”