Map-guided Hyperspectral Image Superpixel Segmentation Using Proportion Maps
This is an incremental improvement for hyperspectral image analysis, addressing segmentation accuracy in remote sensing applications.
The paper tackled hyperspectral image superpixel segmentation by developing a map-guided method that adapts SLIC, uses map information, and incorporates sPM-LDA, resulting in outperformance over existing methods on two real datasets as shown by quantitative metrics.
A map-guided superpixel segmentation method for hyperspectral imagery is developed and introduced. The proposed approach develops a hyperspectral-appropriate version of the SLIC superpixel segmentation algorithm, leverages map information to guide segmentation, and incorporates the semi-supervised Partial Membership Latent Dirichlet Allocation (sPM-LDA) to obtain a final superpixel segmentation. The proposed method is applied to two real hyperspectral data sets and quantitative cluster validity metrics indicate that the proposed approach outperforms existing hyperspectral superpixel segmentation methods.