Improved Classification Method Based on the Diverse Density and Sparse Representation Model for a Hyperspectral Image

Na Li; Ruihao Wang; Huijie Zhao; Mingcong Wang; Kewang Deng; Wei Wei

doi:10.3390/s19245559

Improved Classification Method Based on the Diverse Density and Sparse Representation Model for a Hyperspectral Image

Sensors (Basel). 2019 Dec 16;19(24):5559. doi: 10.3390/s19245559.

Authors

Na Li¹, Ruihao Wang¹, Huijie Zhao¹, Mingcong Wang¹, Kewang Deng¹, Wei Wei²

Affiliations

¹ School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, China.
² Beijing Mechanical and Electrical Engineering Design Institute, Beijing 100854, China.

Abstract

To solve the small sample size (SSS) problem in the classification of hyperspectral image, a novel classification method based on diverse density and sparse representation (NCM_DDSR) is proposed. In the proposed method, the dictionary atoms, which learned from the diverse density model, are used to solve the noise interference problems of spectral features, and an improved matching pursuit model is presented to obtain the sparse coefficients. Airborne hyperspectral data collected by the push-broom hyperspectral imager (PHI) and the airborne visible/infrared imaging spectrometer (AVIRIS) are applied to evaluate the performance of the proposed classification method. Results illuminate that the overall accuracies of the proposed model for classification of PHI and AVIRIS images are up to 91.59% and 92.83% respectively. In addition, the kappa coefficients are up to 0.897 and 0.91.

Keywords: diverse density; hyperspectral image classification; small sample size; sparse representation.