Exploring Hierarchical Convolutional Features for Hyperspectral Image Classification

• Published in: IEEE transactions on geoscience and remote sensing Vol. 56; no. 11; pp. 6712 - 6722
• Main Authors: Cheng, Gong, Li, Zhenpeng, Han, Junwei, Yao, Xiwen, Guo, Lei
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-11-2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Classification; Convolutional neural networks (CNNs); Data; deep learning; Feature extraction; Frameworks; hyperspectral image (HSI) classification; Hyperspectral imaging; Image classification; Machine learning; Measurement; Methods; metric learning; Neural networks; Objective function; Pixels; Regularization; Representations; Retraining; Semantics; Spatial data; spectral–spatial feature; State of the art; Support vector machines; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2018.2841823

Hyperspectral image (HSI) classification is an active and important research task driven by many practical applications. To leverage deep learning models especially convolutional neural networks (CNNs) for HSI classification, this paper proposes a simple yet effective method to extract hierarchical deep spatial feature for HSI classification by exploring the power of off-the-shelf CNN models, without any additional retraining or fine-tuning on the target data set. To obtain better classification accuracy, we further propose a unified metric learning-based framework to alternately learn discriminative spectral-spatial features, which have better representation capability and train support vector machine (SVM) classifiers. To this end, we design a new objective function that explicitly embeds a metric learning regularization term into SVM training. The metric learning regularization term is used to learn a powerful spectral-spatial feature representation by fusing spectral feature and deep spatial feature, which has small intraclass scatter but big between class separation. By transforming HSI data into new spectral-spatial feature space through CNN and metric learning, we can pull the pixels from the same class closer, while pushing the different class pixels farther away. In the experiments, we comprehensively evaluate the proposed method on three commonly used HSI benchmark data sets. State-of-the-art results are achieved when compared with the existing HSI classification methods.