Autors: Bozhilov, I. B., Petkova, R. R., Tonchev K.T., Manolova, A. H.
Title: Exploring Semantic-Aware Compression of RGBD Images Using Conventional Codecs
Keywords: Compression, RGBD, Semantic

Abstract: RGBD data from 3D capture devices includes synchronized color and depth images, forming a four-channel format that traditional codecs (e.g., JPEG2000, H.264) are not designed to compress. Challenges include a lack of support for four-channel data, incompatibility with high bit-depth depth images, and synchronization overhead when transmitting separate streams. This paper investigates depth image colorization to make RGBD data compatible with standard codecs. We compare multiple colorization methods and propose two fusion strategies - simple spatial concatenation and PCA-based fusion - to combine RGB and depth data into a single image. Furthermore, we introduce a semantic-aware compression approach that leverages person segmentation from the Kinect to guide the encoding process. Our results show that incorporating semantic information significantly improves compression efficiency and rate-distortion performance.

References

  1. Marcellin, M. W., Gormish, M. J., Bilgin, A., & Boliek, M. P. (2000, March). An overview of JPEG-2000. In Proceedings DCC 2000. Data compression conference (pp. 523-541). IEEE.
  2. Grois, D., Marpe, D., Nguyen, T., & Hadar, O. (2014, September). Comparative assessment of H. 265/MPEG-HEVC, VP9, and H. 264/MPEG-AVC encoders for low-delay video applications. In Applications of Digital Image Processing XXXVII (Vol. 9217, pp. 207-216). SPIE.
  3. Petkova, R., Poulkov, V., Manolova, A., & Tonchev, K. (2022). Challenges in implementing low-latency holographic-type communication systems. Sensors, 22(24), 9617.
  4. Bozhilov, I., Petkova, R., Tonchev, K., & Manolova, A. (2024). A systematic survey into compression algorithms for threedimensional content. IEEE Access.
  5. Bozhilov, I., Petkova, R., Tonchev, K., Manolova, A., & Poulkov, V. (2023). HOLOTWIN: A modular and interoperable approach to holographic telepresence system development. Sensors, 23(21), 8692.
  6. Sonoda, T., & Grunnet-Jepsen, A. (2021). Depth image compression by colorization for Intel RealSense depth cameras. Intel Rev, 1.
  7. Pece, F., Kautz, J., & Weyrich, T. (2011, September). Adapting standard video codecs for depth streaming. In EGVE/EuroVR (pp. 59-66).
  8. Nenci, F., Spinello, L., & Stachniss, C. (2014, September). Effective compression of range data streams for remote robot operations using H. 264. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 3794-3799). IEEE.
  9. Liu, Y., Beck, S., Wang, R., Li, J., Xu, H., Yao, S., & Froehlich, B. (2015). Hybrid lossless-lossy compression for realtime depth-sensor streams in 3D telepresence applications. In Advances in Multimedia Information Processing-PCM 2015: 16th Pacific-Rim Conference on Multimedia, Gwangju, South Korea, September 16-18, 2015, Proceedings, Part I 16 (pp. 442-452). Springer International Publishing.
  10. Morvan, Y., & Farin, D. (2005, June). Novel coding technique for depth images using quadtree decomposition and plane approximation. In Visual Communications and Image Processing 2005 (Vol. 5960, pp. 1187-1194). SPIE.
  11. Varadarajan, K. M., Zhou, K., & Vincze, M. (2012, November). Rgb and depth intra-frame cross-compression for low bandwidth 3d video. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) (pp. 955-958). IEEE.
  12. GitHub repository, https: //github. com/cheind/hue-depthencoding, accessed Mar. 28, 2025.

Issue

60th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2025 - Proceedings, 2025, Macedonia, https://doi.org/10.1109/ICEST66328.2025.11098421

Copyright IEEE

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus