Manuscript Number : IJSRSET24118038

Boosted Deep Learning for Hyperspectral Image Segmentation: An Adaptive Boosting Approach for Pixel-Level Classification

Authors(3) :-Parul Bhanarkar, Dr. Salim Y. Amdani, Dr. S. S. Asole

Hyperspectral image segmentation is a crucial task in remote sensing and computer vision, where the goal is to classify each pixel in an image based on its spectral characteristics. Despite significant advancements, achieving high classification accuracy in hyperspectral image segmentation remains challenging due to factors like noise, spectral variance, and the high dimensionality of hyperspectral data. In this work, we propose an innovative approach for hyperspectral image segmentation by integrating deep learning with adaptive boosting techniques. Our framework uses a boosting-based strategy to enhance classification accuracy at the pixel level, focusing on misclassified pixels to progressively refine predictions. The core of our approach lies in the use of weak learners, such as shallow convolutional neural networks (CNNs), decision trees, and support vector machines (SVMs), combined with popular boosting algorithms like AdaBoost, Gradient Boosting, and XGBoost. These weak learners are trained iteratively, with each iteration focusing on the misclassified pixels from the previous round, thereby improving the accuracy of the overall model. The adaptive boosting mechanism dynamically adjusts the weights of weak learners to ensure that challenging, hard-to-classify pixels are given more attention. This iterative refinement process results in a more robust and accurate classification model for hyperspectral image segmentation. We evaluate the performance of our proposed framework using standard performance metrics including accuracy, precision, recall, and F1-score.

Authors and Affiliations

Parul Bhanarkar
Babasaheb Naik College of Engineering, Pusad, Maharashtra, India.
Dr. Salim Y. Amdani
Babasaheb Naik College of Engineering, Pusad, Maharashtra, India.
Dr. S. S. Asole
Babasaheb Naik College of Engineering, Pusad, Maharashtra, India.

Hyperspectral Image Segmentation, Deep Learning, Adaptive Boosting, Pixel-Level Classification, XGBoost

  1. Ghaderizadeh, S.; Abbasi-Moghadam, D.; Sharifi, A.; Zhao, N.; Tariq, A. Hyperspectral Image Classification Using a Hybrid 3D-2D Convolutional Neural Networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 7570–7588.
  2. Feng, J.; Gao, Z.; Shang, R.; Zhang, X.; Jiao, L. Multi-Complementary Generative Adversarial Networks with Contrastive Learning for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 2023, 61, 5520018.
  3. Zhong, Z.; Li, Y.; Ma, L.; Li, J.; Zheng, W.-S. Spectral–Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5514715.
  4. He, Z.; Xia, K.; Ghamisi, P.; Hu, Y.; Fan, S.; Zu, B. HyperViTGAN: Semisupervised Generative Adversarial Network with Transformer for Hyperspectral Image Classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 6053–6068.
  5. Yang, X.; Cao, W.; Lu, Y.; Zhou, Y. Hyperspectral Image Transformer Classification Networks. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5528715.
  6. Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterhiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.; Gelly, S.; et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv 2020, arXiv:2010.11929.
  7. Zhong, Z.; Li, J.; Luo, Z.; Chapman, M. Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework. IEEE Trans. Geosci. Remote Sens. 2018, 56, 847–858.
  8. Roy, S.K.; Manna, S.; Song, T.; Bruzzone, L. Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 2021, 59, 7831–7843.
  9. Chen, Y.N.; Thaipisutikul, T.; Han, C.C.; Liu, T.-J.; Fan, K.-C. Feature line embedding based on support vector machine for hyperspectral image classification. Remote Sens. 2021, 13, 130.
  10. Kalaiarasi, G.; Maheswari, S. Deep proximal support vector machine classifiers for hyperspectral images classification. Neural Comput. Appl. 2021, 33, 13391–13415.
  11. Wieland, M.; Martinis, S.; Kiefl, R.; Gstaiger, V. Semantic segmentation of water bodies in very high-resolution satellite and aerial images. Remote Sens. Environ. 2023, 287, 113452.
  12. Xiang, D.; Zhang, X.; Wu, W.; Liu, H. Denseppmunet-a: A robust deep learning network for segmenting water bodies from aerial images. IEEE Trans. Geosci. Remote Sens. 2023, 61, 4202611.
  13. Luo, Z.; Yang, W.; Yuan, Y.; Gou, R.; Li, X. Semantic segmentation of agricultural images: A survey. Inf. Process. Agric. 2023; in press.
  14. Xu, H.; Song, J.; Zhu, Y. Evaluation and Comparison of Semantic Segmentation Networks for Rice Identification Based on Sentinel-2 Imagery. Remote Sens. 2023, 15, 1499.
  15. Wang, D.; Liu, S.; Zhang, C.; Xu, M.; Yang, J.; Yasir, M.; Wan, J. An improved semantic segmentation model based on SVM for marine oil spill detection using SAR image. Mar. Pollut. Bull. 2023, 192, 114981.
  16. Bai, T.; Wang, L.; Yin, D.; Sun, K.; Chen, Y.; Li, W.; Li, D. Deep learning for change detection in remote sensing: A review. Geo-Spat. Inf. Sci. 2023, 26, 262–288.
  17. Gao, L.; Liu, B.; Fu, P.; Xu, M. Adaptive spatial tokenization transformer for salient object detection in optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 2023, 61, 5602915.

Publication Details

Published in : Volume 11 | Issue 8 | May-June 2024
Date of Publication : 2024-12-25
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 260-272
Manuscript Number : IJSRSET24118038
Publisher : Technoscience Academy

Print ISSN : 2395-1990, Online ISSN : 2394-4099

Cite This Article :

Parul Bhanarkar, Dr. Salim Y. Amdani, Dr. S. S. Asole, " Boosted Deep Learning for Hyperspectral Image Segmentation: An Adaptive Boosting Approach for Pixel-Level Classification , International Journal of Scientific Research in Science, Engineering and Technology(IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 11, Issue 8, pp.260-272, May-June-2024. Journal URL : https://res.ijsrset.com/IJSRSET24118038

Article Preview