Hyperspectral Image Compression Using Lightweight Deep Learning for Onboard UAV Applications
| International Journal of Electronics and Communication Engineering |
| © 2025 by SSRG - IJECE Journal |
| Volume 12 Issue 7 |
| Year of Publication : 2025 |
| Authors : D. Balaji, S. Shiyamala |
10.14445/23488549/IJECE-V12I7P103
How to Cite?
D. Balaji, S. Shiyamala, "Hyperspectral Image Compression Using Lightweight Deep Learning for Onboard UAV Applications," SSRG International Journal of Electronics and Communication Engineering, vol. 12, no. 7, pp. 24-34, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I7P103
Abstract:
Hyperspectral Imaging (HSI) is crucial to remote sensing and in applications involving Unmanned Aerial Vehicles (UAVs) because it has the ability to provide detailed scene analyses that take advantage of broad spectral information. However, the large amounts of data involved with HSI pose big challenges for real-time processing and transmission on board. Utilising a light deep learning model optimised for Unmanned Aerial Vehicle (UAV) platforms with limited computing capabilities, this study introduces a new mechanism of efficiently compressing hyperspectral images. The spectral-spatial convolutional autoencoder attains high compression rates while maintaining meaningful information by taking advantage of the spectral redundancy and spatial correlations in hyperspectral data. Attributed to its efficient memory and CPU resource needs, as well as the provision of a compromise between efficiency and speed, the new approach suits real-time deployment in UAVs more than other compression techniques. A broad sweep of experimentation based on benchmark hyperspectral data testifies to significant model size minimisation and runtime reduction, further proving the method to surpass all current methods through improved compression rates. The system is backed by autonomous low-latency hyperspectral data processing within UAV systems through this lightweight paradigm.
Keywords:
Hyperspectral Imaging (HSI) is crucial to remote sensing and in applications involving Unmanned Aerial Vehicles (UAVs) because it has the ability to provide detailed scene analyses that take advantage of broad spectral information. However, the large amounts of data involved with HSI pose big challenges for real-time processing and transmission on board. Utilising a light deep learning model optimised for Unmanned Aerial Vehicle (UAV) platforms with limited computing capabilities, this study introduces a new mechanism of efficiently compressing hyperspectral images. The spectral-spatial convolutional autoencoder attains high compression rates while maintaining meaningful information by taking advantage of the spectral redundancy and spatial correlations in hyperspectral data. Attributed to its efficient memory and CPU resource needs, as well as the provision of a compromise between efficiency and speed, the new approach suits real-time deployment in UAVs more than other compression techniques. A broad sweep of experimentation based on benchmark hyperspectral data testifies to significant model size minimisation and runtime reduction, further proving the method to surpass all current methods through improved compression rates. The system is backed by autonomous low-latency hyperspectral data processing within UAV systems through this lightweight paradigm.
References:
[1] Linmi Tao, and Atif Mughees, Deep Learning for Hyperspectral Image Analysis and Classification, 1st ed., Springer Singapore, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Yaman Dua, Ravi Shankar Singh, and Vinod Kumar, “Compression of Multi-Temporal Hyperspectral Images Based on RLS Filter,” The Visual Computer, vol. 38, pp. 65-75, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Yaman Dua et al., “Convolution Neural Network Based Lossy Compression of Hyperspectral Images,” Signal Processing: Image Communication, vol. 95, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Md. Rakibul Haque et al., “A Lightweight 3D-2D Convolutional Neural Network for Spectral-Spatial Classification of Hyperspectral Images,” Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, vol. 43, no. 1, pp. 1241-1258, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Yaman Dua, Vinod Kumar, and Ravi Shankar Singh, “Comprehensive Review of Hyperspectral Image Compression Algorithms,” Optical Engineering, vol. 59, no. 9, pp. 1-39, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jannick Kuester et al., “Adaptive Two-Stage Multisensor Convolutional Autoencoder Model for Lossy Compression of Hyperspectral Data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-22, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Riccardo La Grassa et al., “Hyperspectral Data Compression Using Fully Convolutional Autoencoder,” Remote Sensing, vol. 14, no. 10, pp. 1-14, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Bart Beusen, Xenia Ivashkovyc, and T.V. Achteren, “Image Compression Using Vector-Quantized Auto-Encoders with Semantically Meaningful Feature Extraction,” 4S Symposium, pp. 1-13, 2022.
[Google Scholar]
[9] S. Navaneethan, and N. Nandhagopal, “RE-PUPIL: Resource Efficient Pupil Detection System Using the Technique of Average Black Pixel Density,” Sādhanā, vol. 46, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Jiahui Yu et al., “Vector-Quantized Image Modeling with Improved VQGAN,” Arxiv, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Yuanyuan Guo, Yanwen Chong, and Shaoming Pan, “Hyperspectral Image Compression via Cross-Channel Contrastive Learning,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Bart Beusen et al., “On-Board Hyperspectral Image Compression Using Vector-Quantized Auto Encoders,” IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, pp. 1703-1707, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Nafiseh Ghasemi et al., “Onboard Processing of Hyperspectral Imagery: Deep Learning Advancements, Methodologies, Challenges, and Emerging Trends,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 4780-4790, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Afsana Afrin, and Md. Al Mamun, “A Comprehensive Review of Deep Learning Methods for Hyperspectral Image Compression,” 2024 3rd International Conference on Advancement in Electrical and Electronic Engineering, Gazipur, Bangladesh, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Saurabh Kumar et al., “Onboard Hyperspectral Image Compression Using Compressed Sensing and Deep Learning,” Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pp. 1-13, 2019.
[Google Scholar] [Publisher Link]
[16] Michael Iliadis, Leonidas Spinoulas, and Aggelos K. Katsaggelos, “Deep Fully-Connected Networks for Video Compressive Sensing,” Digital Signal Processing, vol. 72, pp. 9-18, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Raúl Guerra et al., “A New Algorithm for the On-Board Compression of Hyperspectral Images,” Remote Sensing, vol. 10, no. 3, pp. 1-41, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Nan Zhao et al., “The Paradigm Shift in Hyperspectral Image Compression: A Neural Video Representation Methodology,” Remote Sensing, vol. 17, no. 4, pp. 1-20, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Yuting Wan et al., “Tailings Reservoir Disaster and Environmental Monitoring Using the UAV-Ground Hyperspectral Joint Observation and Processing: A Case of Study in Xinjiang, the Belt and Road,” IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, pp. 9713-9716, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Lili Luo et al., “Combining Different Transformations of Ground Hyperspectral Data with Unmanned Aerial Vehicle (UAV) Images for Anthocyanin Estimation in Tree Peony Leaves,” Remote Sensing, vol. 14, no. 9, pp. 1-20, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Bogdan Kovalenko, Vladimir Lukin, and Benoit Vozel, “BPG-Based Lossy Compression of Three-Channel Noisy Images with Prediction of Optimal Operation Existence and its Parameters,” Remote Sensing, vol. 15, no. 6, pp. 1-24, 2023. [CrossRef] [Google Scholar] [Publisher Link]
[22] Zizhang Li et al., “E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context,” Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, pp. 267-284, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Shao Xiang, and Qiaokang Liang, “Remote Sensing Image Compression Based on High-Frequency and Low-Frequency Components,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Yuanyuan Guo et al., “Edge-Guided Hyperspectral Image Compression with Interactive Dual Attention,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Lili Zhang et al., “Compressing Hyperspectral Images Into Multilayer Perceptrons Using Fast-Time Hyperspectral Neural Radiance Fields,” IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]