EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An end-to-end deep learning image compression method for satellite images based on entropy model

Yanlong Gao, Haiming Xu, Wei Huang, Hao Bai, Boer Peng, Heyang Xu iD

PLOS One · 03.08.2026 · 21 (8) · e0355234

DOI: 10.1371/journal.pone.0355234 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 03.08.2026. Verfasst von Yanlong Gao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Sichuan Expressway Construction and Development Group Co., Ltd, Chengdu, Sichuan, China. Hauptthemen laut MEDLINE: Deep Learning, Satellite Imagery, Data Compression, Compression Algorithms. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ChuanGao Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the extensive applications of satellite image data in environmental monitoring and geographic surveying and mapping, the amount of data has increased rapidly, which brings great challenges for transmitting and storing these images. However, when processing high-resolution and multi-spectral satellite data, existing image compression methods often lead to low compression efficiency or poor reconstruction image quality due to its insufficient generalization ability. In this paper, we propose an end-to-end deep learning image compression framework for visible infrared imaging radiometer suite (VIIRS) satellite imagery. The framework consists of an analysis transform encoder, a synthesis transform decoder, a hybrid training-testing quantizer and a probability model for entropy coding. A cumulative distribution function (CDF) is constructed to compute the discrete likelihood of quantized latent symbols under a Gaussian-mixture entropy model. It is integrated with a checkerboard context structure and a VIIRS-oriented block-processing pipeline. Finally, we conduct systematic experiments based on NASA VIIRS multi-spectral datasets. Experimental results show that the proposed method achieves 0.51 ± 0.04 bpp, 38.39 ± 0.72 dB PSNR and 0.973 ± 0.007 SSIM. Relative to ELIC and the Transformer-CNN baseline, it reduced bpp by 13.6% and 10.5% and improved PSNR by 0.78 dB and 0.61 dB, respectively. The framework can compress the data volume to approximately 1.5%−4% of the original size, corresponding to an average compression ratio of about 30:1. In order to meet the processing requirements of high-resolution satellite images, we further propose a block compression strategy, which divides large-size images into sub-blocks of 256 × 256 pixels for independent compression, and realizes complete image reconstruction through decompression and splicing technology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSatellite ImageryData CompressionCompression AlgorithmsImage Processing, Computer-AssistedEntropyAlgorithms

Autor:innen und Institutionen

  • Sichuan Expressway Construction and Development Group Co., Ltd, Chengdu, Sichuan, China.
  • Sichuan Panyan Expressway Construction and Development Co., Ltd, Chengdu, Sichuan, China.
  • School of Information Engineering, Yancheng Institute of Technology, Yancheng, Jiangsu, China.

ORCID-Profile: Heyang Xu

Förderung

  • ChuanGao Science and Technology Program

Zitieren

APA

Gao, Y., Xu, H., Huang, W., Bai, H., Peng, B., & Xu, H. (2026). An end-to-end deep learning image compression method for satellite images based on entropy model. PLOS One, 21(8), e0355234. https://doi.org/10.1371/journal.pone.0355234

Vancouver

Gao Y, Xu H, Huang W, Bai H, Peng B, Xu H. An end-to-end deep learning image compression method for satellite images based on entropy model. PLOS One. 2026;21(8):e0355234. doi:10.1371/journal.pone.0355234

BibTeX
@article{Gao2026,
  author = {Gao, Yanlong and Xu, Haiming and Huang, Wei and Bai, Hao and Peng, Boer and Xu, Heyang},
  title = {An end-to-end deep learning image compression method for satellite images based on entropy model},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {8},
  pages = {e0355234},
  doi = {10.1371/journal.pone.0355234}
}
Kostenlos starten →