Time filter

Source Type

Xue Z.,Key Laboratory for Satellite Mapping Technology and Applications | Xue Z.,Nanjing University | Li J.,Sun Yat Sen University | Cheng L.,Key Laboratory for Satellite Mapping Technology and Applications | And 3 more authors.
IEEE Transactions on Geoscience and Remote Sensing | Year: 2015

This paper presents a new spectral-spatial classification method for hyperspectral images via morphological component analysis-based image separation rationale in sparse representation. The method consists of three main steps. First, the high-dimensional spectral domain of hyperspectral images is reduced into a low-dimensional feature domain by using minimum noise fraction (MNF). Second, the proposed separation method is acted on each features to generate the morphological components (MCs), i.e., the content and texture components. To this end, the dictionaries for these two components are built by using local curvelet and Gabor wavelet transforms within the randomly chosen image partitions. Then, sparse coding of one of the MCs and update of the associated dictionary are sequentially performed with the other one fixed. To better direct the separation process, an undecimated Haar wavelet with soft threshold is performed for the content component to make it smooth. This process is repeated until some stopping criterion is met. Finally, a support vector machine is adopted to obtain the classification maps based on the MCs. The experimental results with hyperspectral images collected by the National Aeronautics and Space Administration Jet Propulsion Laboratory's Airborne Visible/Infrared Imaging Spectrometer and the Reflective Optics Spectrographic Imaging System indicate that the proposed scheme provides better performance when compared with other widely used methods. © 2014 IEEE. Source

Xue Z.,Key Laboratory for Satellite Mapping Technology and Applications | Xue Z.,Nanjing University | Du P.,Key Laboratory for Satellite Mapping Technology and Applications | Du P.,Nanjing University | Su H.,Hohai University
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | Year: 2014

A novel hyperspectral image classification approach named as HA-PSO-SVM is proposed by integrating the harmonic analysis (HA), particle swarm optimization (PSO), and support vector machine (SVM). In the combined method, HA is first proposed to transform the pixels from spectral domain into frequency domain expressed by amplitude, phase and residual, yielding more functional and discriminative features for classification purpose. In this step, the original pixel vector can also be reconstructed. Then, PSO is adapted to optimize the penalty parameter C and the kernel parameter γ for SVM, which leads to improved classification performance. Finally, the extracted features are classified with the optimized model. The experimental results with three hyperspectral data sets collected by the airborne visible infrared imaging spectrometer (AVIRIS) and the reflective optics spectrographic imaging system (ROSIS) indicate that the proposed method provides improved classification performance compared with some related techniques in terms of both the classification accuracy and the computational time. © 2014 IEEE. Source

Discover hidden collaborations