Abstract
Hyperspectral image (HSI) classification is an important part of its processing and application. Aiming at the problems of high data dimensionality and high spatial neighborhood correlation in HSI classification, we propose a spatial-spectral joint classification method of HSI with locality and edge preserving in this article. First, the input HSI is normalized, and the feature is extracted by principal component analysis. The first principal component image is taken as the guidance image. Second, guided filtering is used to extract the spatial features of each band separately. Then, the extracted spatial features are superimposed, and low-dimensional embedding is completed through local Fisher discriminant analysis. Finally, the obtained low-dimensional embedded features are input into a random forest classifier to get classification results. The experimental results of two HSI show that the proposed method achieves higher classification accuracy than other related methods. In the case of randomly selecting 10% and 1% samples from each class of ground object as training samples, the overall classification accuracy is improved to 99.57% and 97.79%, respectively. This method effectively uses the spatial and local information of the image in low dimensional embedding, and preserves the boundaries of the ground objects, thus improving the classification effect.
Highlights
H YPERSPECTRAL image (HSI) has ultra-high spectral resolution, which can acquire hundreds of continuous spectral bands of the ground objects, thereby greatly improving the ability of distinguishing different ground objects
On the one hand, many researchers engaged in HSI classification use methods of machine learning for image classification, including support vector machine (SVM) [6], Gaussian mixture model [7], random forest (RF)[8], sparse expression [9], active learning [10], etc
To overcome the aforementioned drawbacks, we proposed a spatial-spectral joint classification method of HSI with locality and edge preserving in this article
Summary
H YPERSPECTRAL image (HSI) has ultra-high spectral resolution, which can acquire hundreds of continuous spectral bands of the ground objects, thereby greatly improving the ability of distinguishing different ground objects. The above methods effectively introduce the spatial features of the image, and the classification accuracy has been improved, but they only use the spatial information between the center pixel and its surrounding pixels in a specific area, or each pixel and its neighbors of the low-dimensional embedding process. The spatial-spectral features extracted by the proposed method make use of the spatial information, local information and preserves the boundaries of the ground objects, and perform classification with a random forest classifier, which improves the classification accuracy and reduces the computational complexity.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have