IMPROVEMENT OF THE PIXEL-WISE CLASSIFICATION METHOD FOR REMOTE SENSING DATA UNDER DISTORTIONS BASED ON COMBINED LBP FEATURES

Maksym Rybnytskyi, Sergii Kryvenko, Volodymyr Lukin

Abstract


The subject of this article is the process of pixel-wise classification of satellite images under distortions caused by lossy data compression and additive white Gaussian noise (AWGN). The relevance of the work is driven by the fact that while previous studies using the Local Binary Patterns (LBP) method have demonstrated promising results, they have also revealed the high sensitivity of baseline configurations with a small feature extraction radius to additive pixel noise and compression artifacts (such as boundary blurring and the formation of block effects). In certain cases, this leads to the misclassification of homogeneous areas distorted by compression (e.g., misidentifying water surfaces as vegetation). The goal is to improve the accuracy of pixel-wise classification of satellite images under distortions by developing a robust approach based on a combined feature space that integrates spectral intensity and texture information of different scales. The tasks addressed are: conducting an experimental analysis on 4 diverse satellite scenes modeled under 4 distortion states (reference image, noisy, and two levels of compression); forming an expanded feature space using the combined LBP (by integrating radii of 1, 2, and 3 pixels); and tuning and optimizing the hyperparameters of the XGBoost ensemble classifier. The methods used are based on texture analysis tools, decision-tree-based machine learning algorithms, and statistical accuracy assessment techniques. The study's results experimentally confirm that combining LBP descriptors across different radii partially mitigates microtexture loss caused by compression. Conclusions. The findings confirm that the proposed algorithm effectively compensates for the shortcomings of individual LBP texture descriptors under image distortion conditions. The practical significance of the obtained results lies in establishing a reliable baseline for developing robust automated monitoring and analysis systems for Earth remote sensing (RS) data.


Keywords


pixel-wise classification; remote sensing data; LBP; combined LBP; XGBoost; image distortions; additive white Gaussian noise; data compression

References


Dritsas, E., Trigka, M. Remote Sensing and Geospatial Analysis in the Big Data Era: A Survey. Remote Sensing, 2025, vol. 17, no. 3. 30 p. DOI: 10.3390/rs17030550..

Chen, X., Zhou, H., Li, Y., Wang, Z., Shan, F., Lin, W., Da, H., Li, J. Review of compression approaches for optical remote-sensing images from post-processing perspective. Geocarto International, 2026, vol. 41, iss. 1. 23 p. DOI: 10.1080/10106049.2026.2647547.

Wei, J., Mi, L., Hu, Y., Ling, J., Li, Y., Chen, Z. Effects of Lossy Compression on Remote Sensing Image Classification Based on Convolutional Sparse Coding. IEEE Geoscience and Remote Sensing Letters, 2021, vol. 19, pp. 1–5. DOI: 10.1109/LGRS.2020.3047789.

Proskura, G., Rubel, O., Kryvenko, S., Lukin, V. On classifier performance for remote sensing images compressed by different coders. Aerospace Technic and Technology, 2023, no. 1 (185), pp. 67–77. DOI: 10.32620/aktt.2023.1.07.

Rasti, B., Scheunders, P., Ghamisi, P., Licciardi, G., Chanussot, J. Noise Reduction in Hyperspectral Imagery: Overview and Application. Remote Sensing, 2018, vol. 10, iss. 3. 28 p. DOI: 10.3390/rs10030482.

Maxwell, A. E., Warner, T. A., Fang, F. Implementation of machine-learning classification in remote sensing: an applied review. International Journal of Remote Sensing, 2018, vol. 39, iss. 9, pp. 2784–2817. DOI: 10.1080/01431161.2018.1433343.

González-de-Regàs, J., Mijares, S., Bartrina-Rapesta, J., Serra-Sagristà, J. Robustness of Lossy Multispectral Compression to Simulated Instrumental Noise: A Comparative Study. IEEE Geoscience and Remote Sensing Letters, 2025, vol. 22, pp. 1–5. DOI: 10.1109/LGRS.2025.3623314.

Pietikäinen, M., Hadid, A., Zhao, G., Ahonen, T. Computer Vision Using Local Binary Patterns. Springer, 2011, vol. 40. 228 p. DOI: 10.1007/978-0-85729-748-8.

Zhao, Z., Zheng, N. Adjacent paired LBP and enhanced HOG for improved facial expression recognition. SPIE International Conference on Computer Vision, Robotics and Automation Engineering, 2025, vol. 13790. 6 p. DOI: 10.1117/12.3082520.

Ojala, T., Pietikainen, M., Maenpaa, T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, vol. 24, no. 7, pp. 971–987. DOI: 10.1109/TPAMI.2002.1017623.

Liao, S., Law, M., Chung, A. Dominant Local Binary Patterns for Texture Classification. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2009, vol. 18, iss. 5, pp. 1107–1118. DOI: 10.1109/TIP.2009.2015682.

Gomes, H. M., Bifet, A., Read, J., Barddal, J. P., Enembreck, F., Pfharinger, B., Holmes, G., Abdessalem, T. Adaptive random forests for evolving data stream classification. Machine Learning, 2017, vol. 106, iss. 9–10, pp. 1469–1495. DOI: 10.1007/s10994-017-5642-8.

Yang, R., Chen, Z., Wang, B., Guo, Y., Hu, L. A Lightweight Detection Method for Remote Sensing Images and Its Energy-Efficient Accelerator on Edge Devices. Sensors, 2023, vol. 23, iss. 14. 27 p. DOI: https://doi.org/10.3390/s23146497.

Zhai, G., Min, X. Perceptual image quality assessment: a survey. Science China Information Sciences, 2020, vol. 63. 52 p. DOI: 10.1007/s11432-019-2757-1.

Garcia-Vilchez, F., Muñoz, J., Zortea, M., Blanes, I., Gonzalez-Ruíz, V., Camps-Valls, G., Plaza, A., Serra-Sagristà, J. On the Impact of Lossy Compression on Hyperspectral Image Classification and Unmixing. Geoscience and Remote Sensing Letters, IEEE, 2011, vol. 8, iss. 2, pp. 253–257. DOI: 10.1109/LGRS.2010.2062484.

Bernacki, J., Scherer, R. Algorithms and Methods for Individual Source Camera Identification: A Survey. Sensors, 2025, vol. 25, iss. 10. 43 p. DOI: 10.3390/s25103027.

Sun, H., Dai, X., Shou, W., Wang, J., Ruan, X. An Efficient Decision Support System for Flood Inundation Management Using Intermittent Remote-Sensing Data. Remote Sensing, 2021, vol. 13, iss. 14. 26 p. DOI: 10.3390/rs13142818.

BPG Image format. Available et: https://bellard.org/bpg/ (accessed: July 13, 2025).

Chen, T., Guestrin, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, in KDD ’16. New York, NY, USA: Association for Computing Machinery, 2016, pp. 785–794. DOI: 10.1145/2939672.2939785

Golilarz, N. A., Gao, H., Pirasteh, S., Yazdi, M., Zhou, J., Fu, Y. Satellite Multispectral and Hyperspectral Image De-Noising with Enhanced Adaptive Generalized Gaussian Distribution Threshold in the Wavelet Domain. Remote Sensing, 2021, vol. 13, iss. 1. 16 p. DOI: 10.3390/rs13010101.

Kovalenko, B., Lukin, V., Kryvenko, S., Naumenko, V., Vozel, B. Prediction of parameters in optimal operation point for BPG-based lossy compression of noisy images. Ukrainian journal of remote sensing, 2022, vol. 9, iss. 2, pp. 4–12.

Feng, H., Wang, Y., Li, Z., Zhang, N., Zhang, Y., Gao, Y. Information Leakage in Deep Learning-Based Hyperspectral Image Classification: A Survey. Remote Sensing, 2023, vol. 15, iss. 15. – 34 p. DOI: 10.3390/rs15153793.

Meyer, H., Reudenbach, C., Wöllauer, S., Nauss, T. Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction. Ecological Modelling, 2019, vol. 411. 12 p. DOI: 10.1016/j.ecolmodel.2019.108815.

Abdi, A. M., Wang, F. Forest tree species classification and entropy-derived uncertainty mapping using extreme gradient boosting and Sentinel-1/2 satellite data, 2025. Available et: https://api.semanticscholar.org/CorpusID:281496896

Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera‐Arroita, G., Hauenstein, S., Lahoz‐Monfor,t J. J., Schröder, B., Thuiller, W., Warton, D. I., Wintle, B. A., Hartig, F., Dormann, C. F. Cross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 2017, vol. 40, iss. 8, pp. 913–929. DOI: 10.1111/ecog.02881.

Rybnytskyi, M., Kryvenko, S., Lukin, V., Rebrov, V. A combined approach to pixel-wise classification of satellite images based on LBP, pseudocolor features, and XGBoost. Radioelectronic and Computer Systems, 2025, no. 4 (116), pp. 206–219. DOI: 10.32620/reks.2025.4.14.

Yang, S., Berdine, G. The receiver operating characteristic (ROC) curve. The Southwest Respiratory and Critical Care Chronicles, 2017, vol. 5, iss. 19. p. 34-36. DOI: 10.12746/swrccc.v5i19.391.

Kovalenko B., Lukin V., Kryvenko S., Naumenko V., Vozel B. BPG-Based Automatic Lossy Compression of Noisy Images with the Prediction of an Optimal Operation Existence and Its Parameters. Applied Sciences, 2022, vol. 12, iss. 15. 23 p. DOI: 10.3390/app12157555.




DOI: https://doi.org/10.32620/aktt.2026.4.09