Method of Bit Plates Semantic-Oriented Processing of Infrared Images
DOI:
https://doi.org/10.20535/RADAP.2025.102.%25pKeywords:
remote sensing systems, infrared image processing, bit plane bifurcation, information content metric, Haar wavelet transform, adaptive image segmentation, thermal signature preservation, low computational complexity image compression, semantic-oriented coding, selective image compressionAbstract
The paper considers the features of developing a semantic-oriented bit-plane processing method for infrared (IR) images, aimed at enhancing the efficiency of remote surveillance systems under resource-constrained conditions. The article presents an approach to reducing the bit volume of IR data without losing critical semantic information, which is essential for object detection and identification tasks. The advantages of employing an additional IR information channel are revealed, as it ensures reliable system operation under limited visibility, object camouflage, or adverse backgrounds. At the same time, the challenge of increasing the data volume for real-time processing is noted. It is found that traditional methods (PNG, JPEG-LS, JPEG 2000, HEVC) either have excessive computational complexity or fail to preserve thermal semantics. Thus, the paper defines an applied scientific task — to improve the efficiency of remote surveillance systems using IR information channels. To address this, the article proposes a method based on bit-plane bifurcation (extraction of most and least significant bits) followed by semantic-oriented processing. The most significant bits retain the global structure and primary scene information, while the least significant bits carry residual noise or imperceptible details. This allows for adaptive compression strategies depending on the informativeness of individual segments. The method includes hierarchical decomposition of the image into segments and subsegments for localized analysis. For each segment, informativeness is evaluated in the spectral domain using the Haar wavelet transform, followed by normalization of informativeness metrics and selective encoding: informative segments are encoded with minimal loss, non-informative ones with more aggressive compression. The informativeness metric is based on high-frequency components that represent thermal contours of objects. Specifically, it is computed as the normalized sum of the absolute values of high-frequency coefficients after transforming the subsegments into the difference domain. Threshold values are used to classify segments as informative or non-informative. Depending on the informativeness class, further selective encoding is performed to preserve the reconstruction accuracy of key scene areas. Special attention is given to preserving the key thermal structure of the scene even when reducing bit depth to 8 bits. A comparative experimental analysis was carried out on a dataset of 16-bit images. Under conditions of equal PSNR, the proposed method demonstrates an average compression ratio improvement of 2.63. Visual analysis showed that, unlike the traditional approach, the proposed method preserves the thermal integrity of objects of interest after decoding. Hence, the goal of the study is to develop a semantic-oriented bit-plane processing method for infrared images. The proposed method has practical value for integration into onboard systems of unmanned aerial vehicles (UAVs), monitoring systems, and other mobile platforms, where transmission speed and computational constraints are critical.
References
References
1. Naga Lakshmi, T., Jyothi, S. (2020). Performing Image Compression and Decompression Using Matrix Substitution Technique. In: Jyothi, S., Mamatha, D., Satapathy, S., Raju, K., Favorskaya, M. (eds) Advances in Computational and Bio-Engineering. CBE 2019. Learning and Analytics in Intelligent Systems, Vol. 15, pp. 25–36, Springer, Cham., doi: 10.1007/978-3-030-46939-9_3.
2. Bausys R. and Kazakeviciute-Januskeviciene G. (2021). Qualitative Rating of Lossy Compression for Aerial Imagery by Neutrosophic WASPAS Method. Symmetry, Vol. 13, Iss. 2, 273, DOI: 10.3390/sym13020273.
3. Putra A. B. W., Supriadi S., Wibawa A., Pranolo A. and Gaffar A. F. O. (2020). Modification of a gray-level dynamic range based on a number of binary bit representation for image compression. Science in Information Technology Letters, Vol. 1, No. 1, pp. 9–16, doi: 10.31763/sitech.v1i1.17.
4. Zhang X., Chu F. (2022). Multimedia Real-Time Transmission Protocol and Its Application in Video Transmission System. Computational Intelligence and Neuroscience, Vol. 2022, Article ID 8654756, 7 p., DOI: 10.1155/2022/8654756.
5. Omar H. M., Morsli M. and Yaichi S. (2020). Image Compression using Principal Component Analysis. Proceedings of the 2020 2nd International Conference on Mathematics and Information Technology (ICMIT), pp. 226–231, doi: 10.1109/ICMIT47780.2020.9047014.
6. Zhang L., Yang W., Li C. (2024). Enhanced High-Definition Video Transmission for Unmanned Driving in Mining Environments. Applied Sciences, Vol. 14, Iss. 10, DOI: 10.3390/app14104296.
7. Garg G. and Kumar R. (2022). Analysis of image types, compression techniques and performance assessment metrics: A review. Journal of Information and Optimization Sciences, Vol. 43, No. 3, pp. 429–436, doi: 10.1080/02522667.2022.2037282.
8. Qin C., Pournaras E. (2023). Coordination of drones at scale: Decentralized energy-aware swarm intelligence for spatio-temporal sensing. Transportation Research Part C: Emerging Technologies, Vol. 157, 104387, DOI: 10.1016/j.trc.2023.104387.
9. Uthayakumar J., Elhoseny M. and Shankar K. (2020). Highly Reliable and Low-Complexity Image Compression Scheme Using Neighborhood Correlation Sequence Algorithm in WSN. IEEE Transactions on Reliability, Vol. 69, No. 4, pp. 1398–1423, doi: 10.1109/TR.2020.2972567.
10. Descampe A. et al. (2021). JPEG XS—A New Standard for Visually Lossless Low-Latency Lightweight Image Coding. Proceedings of the IEEE, Vol. 109, Iss. 9, pp. 1559–1577, DOI: 10.1109/jproc.2021.3080916.
11. Resdiansyah, Darmawan J., Wijaya A. H. , Hakim L. and Tannady H. (2021). Comparing Freeman Chain Code 4 Adjacency Algorithm and LZMA Algorithm in Binary Image Compression. Journal of Physics: Conference Series, Vol. 1783, 012045, doi: 10.1088/1742-6596/1783/1/012045.
12. Li C., et. al. (2024). MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model. JOURNAL OF LATEX CLASS FILES, Vol. 1, Iss. 1, pp. 1-13, DOI: arxiv-2402.16749.
13. Qasim A., Din R. and Alyousuf F. Q. A. (2020). Review on techniques and file formats of image compression. Bulletin of Electrical Engineering and Informatics, Vol. 9, No. 2, pp. 602–610, doi: 10.11591/eei.v9i2.2085.
14. Brahimi T., Khelifi F., Kacha A. (2021). An efficient JPEG-2000 based multimodal compression scheme. Multimedia Tools and Applications, Vol. 80, Iss. 14, pp. 21241-21260, DOI: 10.1007/s11042-021-10776-5.
15. Lang H., Beischl A., Leis V., Boncz P., Neumann T. and Kemper A. (2020). Tree-Encoded Bitmaps. Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp. 937–967, doi: 10.1145/3318464.3380588.
16. Dua Y., Kumar V., Singh R. S. (2020). Comprehensive review of hyperspectral image compression algorithms. SPIE, Optical Engineering, Vol. 59, Iss. 9, 090902, DOI: 10.1117/1.OE.59.9.090902.
17. Barannik V., Hahanova A., Slobodyanyuk A. (2009). Architectural presentation of isotopic levels of relief of images. 2009 ІЕЕЕ 10th International Conference — The Experience of Designing and Application of CAD Systems in Microelectronics (CADSM), pp. 385–387.
18. Chi, X., Zhang, Y., Di Maio, D., Lieven, N. A. J. (2021). Viability of Image Compression in Vibrothermography. Experimental Techniques, Vol. 45, pp. 345–362, doi: 10.1007/s40799-020-00395-4.
19. Barannik D. and Barannik V. (2022). Steganographic Coding Technology for Hiding Information in Infocommunication Systems of Critical Infrastructure. 2022 IEEE 4th International Conference on Advanced Trends in Information Theory (ATIT), pp. 88-91, doi: 10.1109/ATIT58178.2022.10024185.
20. Son, D.-M., Kwon H.-J., and Lee S.-H. (2022). Visible and Near Infrared Image Fusion Using Base Tone Compression and Detail Transform Fusion. Chemosensors, Vol. 10, No. 4: 124, doi :10.3390/chemosensors10040124.
21. Barannik V., Barannik N., Ignatiev O., Khimenko V. (2021). Method of indirect information hiding in the process of video compression. Radioelectronic and Computer Systems, №. 4, pp. 119–131, doi: 10.32620/reks.2021.4.
22. Zhang X., Saniie J., Bakhtiari S. and Heifetz A. (2022). Compression of Pulsed Infrared Thermography Data With Unsupervised Learning for Nondestructive Evaluation of Additively Manufactured Metals. IEEE Access, Vol. 10, pp. 9094-9107, doi: 10.1109/ACCESS.2022.3141654.
23. Barannik V., Babenko Y., Barannik V., Khimenko A., Kulitsa O., Matviichuk-Yudina O. (2020). Significant Microsegment Transformants Encoding Method to Increase the Availability of Video Information Resource. 2020 IEEE 2nd International Conference on Advanced Trends in Information Theory (ATIT), pp. 52-56, DOI: 10.1109/ATIT50783.2020.9349256.
24. Li S., Li Y., Li Y., Li M. and Xu X. (2021). YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection. IEEE Access, Vol. 9, pp. 141861-141875, doi: 10.1109/ACCESS.2021.3120870.
25. Mentzer F., Toderici G., Tschannen M., Agustsson E. (2020). High-Fidelity Generative Image Compression. 34th Conference on Neural Information Processing Systems, DOI: 10.48550/arXiv.2006.09965.
26. Fan, K., Hong, K., and Li F. (2021). Infrared Image Super-Resolution via Progressive Compact Distillation Network. Electronics, Vol. 10, No. 24: 3107, doi :10.3390/electronics10243107.
27. Krasnorutsky A.; Onyshchenko R.; Barannik D.; Barannik V. (2022). The Methods of Intellectual Processing of Video Frames in Coding Systems in Progress Aeromonitor to Increase Efficiency and Semantic Integrity. 2022 IEEE 4th International Conference on Advanced Trends in Information Theory (ATIT), pp. 53-56, doi: 10.1109/ATIT58178.2022.10024208.
28. Huang Y., Jiang Z., Lan R., Zhang S. and Pi K. (2021). Infrared Image Super-Resolution via Transfer Learning and PSRGAN. IEEE Signal Processing Letters, Vol. 28, pp. 982-986, doi: 10.1109/LSP.2021.3077801.
29. Umam, A. K., Ngastiti, P. T. B., Alfan A., Shahadah Z., & Muamalah A. F. (2024). The Application of Dicrete Wavelet Transform for Digital Image Compression. Jurnal Matematika Sains dan Teknologi, Vol. 25, Iss. 1, pp. 01–08, doi: 10.33830/jmst.v25i1.3955.2024.
30. Manda, M. P., and Kim, H. S. (2020). A Fast Image Thresholding Algorithm for Infrared Images Based on Histogram Approximation and Circuit Theory. Algorithms, Vol. 13, No. 9: 207, doi: 10.3390/a13090207.
31. Starosolski R. (2020). Hybrid Adaptive Lossless Image Compression Based on Discrete Wavelet Transform. Entropy, Vol. 22, Iss. 7, 751, DOI: 10.3390/e22070751.
32. Uthayakumar J., Elhoseny M. and Shankar K. (2020). Highly Reliable and Low-Complexity Image Compression Scheme Using Neighborhood Correlation Sequence Algorithm in WSN. IEEE Transactions on Reliability, Vol. 69, No. 4, pp. 1398-1423, doi: 10.1109/TR.2020.2972567.
33. Ma H., Liu D., Yan N., Li H. and Wu F. (2022). End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, No. 3, pp. 1247-1263, doi: 10.1109/TPAMI.2020.3026003.
34. Hou, F., Zhang, Y., Zhou, Y., Zhang, M., Lv B., and Wu J. (2022). Review on Infrared Imaging Technology. Sustainability, Vol. 14, No. 18: 11161, doi: 10.3390/su141811161.
35. Abdulazeez A. M., Zeebaree D. Q., Zebari D. A., Zebari G. M., Adeen I. M. N. (2020). The Applications of Discrete Wavelet Transform in Image Processing: A Review. Journal of Soft Computing and Data Mining, Vol. 1, No. 2, doi: 10.30880/jscdm.2020.01.02.004.
36. Hou R. et al. (2020). VIF-Net: An Unsupervised Framework for Infrared and Visible Image Fusion. IEEE Transactions on Computational Imaging, Vol. 6, pp. 640-651, doi: 10.1109/TCI.2020.2965304.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 В. В. Бараннік , А. А. Берчанов , В. В. Бараннік , О. Ю. Суханов , П. Д. Перцев , О. С. Лиходєєв , О. К. Юдін , Р. О. Прокопенко , Ю. М. Чаун
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
