A Pixel Cluster CNN and Spectral-Spatial Fusion Algorithm for Hyperspectral Image Classification With Small-Size Training Samples

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 14; pp. 4101 - 4114
• Main Authors: Dong, Shuxian, Quan, Yinghui, Feng, Wei, Dauphin, Gabriel, Gao, Lianru, Xing, Mengdao
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Classification; Classification algorithms; Clustering algorithms; Clusters; Convolutional neural network (CNN); Data mining; Engineering Sciences; Environmental Sciences; Feature extraction; Global Changes; hyperspectral image classification (HSIC); Hyperspectral imaging; Image classification; Neural networks; pixel cluster; Pixels; Signal and Image processing; small training set; Spatial data; Spectra; spectral-spatial fusion (SSF); Support vector machines; Training
• ISSN: 1939-1404; 2151-1535; 2151-1535
• DOI: 10.1109/JSTARS.2021.3068864

Convolutional neural networks (CNNs) can automatically learn features from the hyperspectral image (HSI) data, avoiding the difficulty of manually extracting features. However, the number of training samples for the classification of HSIs is always limited, making it difficult for CNN to obtain effective features and resulting in low classification accuracy. To solve this problem, a pixel cluster CNN and spectral-spatial fusion (SSF) algorithm for hyperspectral image classification with small-size training samples is proposed in this article. First, spatial information is extracted by the gray level co-occurrence matrix. Then, spatial information and spectral information are fused by means of bands superposition, forming spectral-spatial features. To expand the number of training samples, the pixels after SSF are combined into pixel clusters according to a certain rule. Finally, a CNN framework is utilized to extract effective features from the pixel clusters. Experiments based on three standard HSIs demonstrate that the proposed algorithm can get better performance than the conventional CNN and also outperforms other studied algorithms in the case of small training set.