Performance Evaluation of Hyperspectral Image Classification Methods: A Comparative Study

Performance Evaluation of Hyperspectral Image Classification Methods: A Comparative Study
  IJETT-book-cover           
  
© 2024 by IJETT Journal
Volume-72 Issue-1
Year of Publication : 2024
Author : Tilottama Goswami, Yaksha Kasturi, Kommareddy Anvitha, Kovvur Ram Mohan Rao
DOI : 10.14445/22315381/IJETT-V72I1P121

How to Cite?

Tilottama Goswami, Yaksha Kasturi, Kommareddy Anvitha, Kovvur Ram Mohan Rao, "Performance Evaluation of Hyperspectral Image Classification Methods: A Comparative Study," International Journal of Engineering Trends and Technology, vol. 72, no. 1, pp. 209-218, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I1P121

Abstract
Hyperspectral Images (HSIs) offer an extensive wealth of spectral-spatial information through their numerous contiguous narrow bands. However, selecting relevant spectral-spatial kernel features creates a challenge as it involves dealing with noise and band correlation. The classification of hyperspectral images plays a crucial role in remote sensing, and various methods have been proposed to tackle this challenge. This paper presents a compilation and comparative study of the recent state-of-the-art deep learning architectures for the HSI classification tasks: Attention-Based Adaptive Spectral-Spatial Kernel ResNet (A2S2K-ResNet), Residual Network (ResNet), Contextual CNN, Deep Pyramidal Residual Networks (DPyResNet), and SpectralSpatialRN (SSRN). These methods are evaluated on four datasets: Indian Pines, Salinas, Botswana, and Kennedy Space Center, which are commonly used for land cover classification in hyperspectral imaging. The performance evaluation of the classification methods is based on overall accuracy and computational time efficiency. The A2S2K-ResNet architecture demonstrates superior classification capabilities compared to the others followed by Contextual Net.

Keywords
Deep Learning, Hyperspectral Image (HSI) Classification, Performance Analysis, Residual Network (ResNet), Spectral-Spatial Information.

References
[1] Swalpa Kumar Roy et al., “Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 9, pp. 7831-7843, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Hyungtae Lee, and Heesung Kwon, “Going Deeper with Contextual CNN for Hyperspectral Image Classification,” IEEE Transactions on Image Processing, vol. 26, no. 10, pp. 4843-4855, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mercedes E. Paoletti et al., “Deep Pyramidal Residual Networks for Spectral-Spatial Hyperspectral Image Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 2, pp. 740-754, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Zilong Zhong et al., “Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework,” IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no. 2, pp. 847-858, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Swalpa Kumar Roy et al., “HybridSN: Exploring 3-D-2-D CNN Feature Hierarchy for Hyperspectral Image Classification,” IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 2, pp. 277-281, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Wenjing Lv, and Xiaofei Wang, “Overview of Hyperspectral Image Classification,” Journal of Sensors, vol. 2020, pp. 1-13, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Saad Albawi, Tareq Abed Mohammed, and Saad Al-Zawi, “Understanding of a Convolutional Neural Network,” 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey, pp. 1-6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Qilong Wang et al., “ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 11531-11539, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Hsi-Chin Hsin, and Chien-Kun Su, “Adaptive Pooling for Convolutional Neural Networks with Arbitrary Input Sizes,” IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE), Yunlin, Taiwan, pp. 196-198, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Robert Green et al., “Imaging Spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS),” Remote Sensing of Environment, vol. 65, no. 3, pp. 227-248, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Christian Szegedy et al., “Going Deeper with Convolutions,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 1-9, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Chen-Yu Lee et al., “Deeply-Supervised Nets,” Arxiv, pp. 1-10, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ying Li, Haokui Zhang, and Qiang Shen, “Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network,” Remote Sensing, vol. 9, no. 1, pp. 1-21, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Jonathan Long, Evan Shelhamer, and Trevor Darrell, “Fully Convolutional Networks for Semantic Segmentation,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 3431-3440, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Alex Krizhevsky, Ilya Sutskever, and G. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” NIPS'12: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 1, pp. 1097-1105, 2012.
[Google Scholar] [Publisher Link]
[17] Xiang Li et al., “Selective Kernel Networks,” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 510-519, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Qilong Wang et al., “ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 11531-11539, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Kaiming He et al., “Identity Mappings in Deep Residual Networks,” Proceeding European Conference on Computer Vision (ECCV), pp. 630-645, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Sergey Zagoruyko, and Nikos Komodakis, “Wide Residual Networks,” Arxiv, pp. 1-15, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Fei Wang et al., “Residual Attention Network for Image Classification,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 6450-6458, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Dongyoon Han, Jiwhan Kim, and Junmo Kim, “Deep Pyramidal Residual Networks,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 6307-6315, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Ionut Cosmin Duta et al., “Improved Residual Networks for Image and Video Recognition,” Arxiv, pp. 1-22, 2020
[CrossRef] [Google Scholar] [Publisher Link]