A Deep Learning-Based Hyperspectral Object Classification Approach via Imbalanced Training Samples Handling

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 14; p. 3532
• Main Authors: Islam, Md Touhid, Islam, Md Rashedul, Uddin, Md Palash, Ulhaq, Anwaar
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2023
• Subjects: Accuracy; Algorithms; Artificial intelligence; batch normalization; Classification; Comparative analysis; Data compression; Datasets; Deep learning; dimensionality reduction; Environmental monitoring; Feature selection; Hyperspectral imaging; Image classification; Image segmentation; imbalanced data handling; Machine learning; Methods; Multispectral photography; Neural networks; non-negative matrix factorization; object classification; Redundancy; Remote sensing; Subgroups; Technology application; Bangladesh
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15143532

Object classification in hyperspectral images involves accurately categorizing objects based on their spectral characteristics. However, the high dimensionality of hyperspectral data and class imbalance pose significant challenges to object classification performance. To address these challenges, we propose a framework that incorporates dimensionality reduction and re-sampling as preprocessing steps for a deep learning model. Our framework employs a novel subgroup-based dimensionality reduction technique to extract and select the most informative features with minimal redundancy. Additionally, the data are resampled to achieve class balance across all categories. The reduced and balanced data are then processed through a hybrid CNN model, which combines a 3D learning block and a 2D learning block to extract spectral–spatial features and achieve satisfactory classification accuracy. By adopting this hybrid approach, we simplify the model while improving performance in the presence of noise and limited sample size. We evaluated our proposed model on the Salinas scene, Pavia University, and Kennedy Space Center benchmark hyperspectral datasets, comparing it to state-of-the-art methods. Our object classification technique achieves highly promising results, with overall accuracies of 99.98%, 99.94%, and 99.46% on the three datasets, respectively. This proposed approach offers a compelling solution to overcome the challenges of high dimensionality and class imbalance in hyperspectral object classification.