Logo PTI Logo FedCSIS

Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 43

A Lightweight Optimization Approach to the Single-Person Pose Estimation Pipeline in RGB-D Cameras

,

DOI: http://dx.doi.org/10.15439/2025F6822

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 287–290 ()

Full text

Abstract. The paper presents a systematic benchmark for depth-assisted single-person pose estimation pipelines in three consumer RGB-D cameras. We introduce a lightweight optimization that adjusts only the relative depth coordinates of predicted joints so that their inter-joint depth gaps match those observed in the depth sensor image. The proposed approach is fully differentiable, sensor-agnostic, and light enough for real-time edge deployment, making it immediately applicable to sports coaching, workplace ergonomics, and mixed reality mobile systems. Experiments on a controlled motion capture dataset demonstrate performance trade-offs in accuracy, speed, and robustness under challenging viewing geometries. The findings provide practical guidance on which depth technology best complements state-of-the-art vision models and establish relative depth matching as an effective computationally trivial alternative for laboratory calibration.

References

  1. R. Maskeliūnas, R. Damaševičius, T. Blažauskas, C. Canbulut, A. Adomavičienė, and J. Griškevičius, “Biomacvr: A virtual reality-based system for precise human posture and motion analysis in rehabilitation exercises using depth sensors,” Electronics, vol. 12, no. 2, p. 339, 2023.
  2. R. Maskeliūnas, R. Damaševičius, V. Raudonis, A. Adomavičienė, J. Raistenskis, and J. Griškevičius, “Biomacemg: A pareto-optimized system for assessing and recognizing hand movement to track rehabilitation progress,” Applied Sciences, vol. 13, no. 9, p. 5744, 2023.
  3. V. Abromavičius, E. Gisleris, K. Daunoravičienė, J. Žižienė, A. Serackis, and R. Maskeliūnas, “Enhanced human skeleton tracking for improved joint position and depth accuracy in rehabilitation exercises,” Applied sciences., vol. 15, no. 2, pp. 1–23, 2025.
  4. R. O. Ogundokun, R. Damasevicius, and R. Maskeliunas, “Optimobilex: Optimizing deep transfer learning model for accurate human posture recognition using a deep feature fusion technique,” IEEE Sensors Journal, 2024.
  5. S. Li, N. Hendrich, H. Liang, P. Ruppel, C. Zhang, and J. Zhang, “A dexterous hand-arm teleoperation system based on hand pose estimation and active vision,” IEEE Transactions on Cybernetics, vol. 54, no. 3, pp. 1417–1428, 2022.
  6. P. Sharma, B. B. Shah, and C. Prakash, “A pilot study on human pose estimation for sports analysis,” in Pattern Recognition and Data Analysis with Applications. Springer, 2022, pp. 533–544.
  7. J. Wang, S. Tan, X. Zhen, S. Xu, F. Zheng, Z. He, and L. Shao, “Deep 3d human pose estimation: A review,” Computer Vision and Image Understanding, vol. 210, p. 103225, 2021.
  8. R. O. Ogundokun, R. Maskeliunas, and R. Damaševičius, “Human posture detection on lightweight dcnn and svm in a digitalized healthcare system,” in 2023 3rd International Conference on Applied Artificial Intelligence (ICAPAI). IEEE, 2023, pp. 1–6.
  9. C. Zheng, W. Wu, C. Chen, T. Yang, S. Zhu, J. Shen, N. Kehtarnavaz, and M. Shah, “Deep learning-based human pose estimation: A survey,” ACM Computing Surveys, vol. 56, no. 1, pp. 1–37, 2023.
  10. N. R. Fisal, A. Fathalla, D. Elmanakhly, and A. Salah, “Reported challenges in deep learning-based human pose estimation: A systematic review,” IEEE Access, 2025.
  11. Y. Lee, B. Lama, S. Joo, and J. Kwon, “Enhancing human key point identification: A comparative study of the high-resolution vicon dataset and coco dataset using bpnet,” Applied Sciences, vol. 14, no. 11, p. 4351, 2024.
  12. Y. Xu, J. Zhang, Q. Zhang, and D. Tao, “Vitpose: Simple vision transformer baselines for human pose estimation,” Advances in neural information processing systems, vol. 35, pp. 38 571–38 584, 2022.
  13. R. Bajpai and D. Joshi, “Movenet: A deep neural network for joint profile prediction across variable walking speeds and slopes,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–11, 2021.
  14. M. Cormier, A. Clepe, A. Specker, and J. Beyerer, “Where are we with human pose estimation in real-world surveillance?” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 591–601.
  15. V. Bazarevsky, I. Grishchenko, K. Raveendran, T. Zhu, F. Zhang, and M. Grundmann, “Blazepose: On-device real-time body pose tracking,” arXiv preprint https://arxiv.org/abs/2006.10204, 2020.
  16. A. Sengupta, F. Jin, R. Zhang, and S. Cao, “mm-pose: Real-time human skeletal posture estimation using mmwave radars and cnns,” IEEE Sensors Journal, vol. 20, no. 17, pp. 10 032–10 044, 2020.
  17. S. Hu, S. Cao, N. Toosizadeh, J. Barton, M. G. Hector, and M. J. Fain, “mmpose-fk: A forward kinematics approach to dynamic skeletal pose estimation using mmwave radars,” IEEE Sensors Journal, vol. 24, no. 5, pp. 6469–6481, 2024.
  18. Y. Zhang, Y. Zhou, P. Wang, L. He, Z. Zhang, and J. Ren, “Intelligent pose recognition and evaluation system for rowing sports,” in 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI). IEEE, 2024, pp. 620–625.
  19. M. Ota, H. Tateuchi, T. Hashiguchi, and N. Ichihashi, “Verification of validity of gait analysis systems during treadmill walking and running using human pose tracking algorithm,” Gait & posture, vol. 85, pp. 290–297, 2021.
  20. T. Li and H. Yu, “Visual–inertial fusion-based human pose estimation: A review,” IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–16, 2023.
  21. M. Boldo, M. De Marchi, E. Martini, S. Aldegheri, D. Quaglia, F. Fummi, and N. Bombieri, “Real-time multi-camera 3d human pose estimation at the edge for industrial applications,” Expert Systems with Applications, vol. 252, p. 124089, 2024.
  22. N. D. Ninh, K. N. Dang, T. T. Van, and B. T. Tung, “Navigation for drones in gps-denied environments based on vision processing,” Annals of Computer Science and Information Systems, vol. 33, 2022.
  23. G. Vdoviak, T. Sledevič, A. Serackis, D. Plonis, D. Matuzevičius, and V. Abromavičius, “Evaluation of deep learning models for insects detection at the hive entrance for a bee behavior recognition system,” Agriculture, vol. 15, no. 10, p. 1019, 2025.
  24. Y. Wang, Z. Jiang, Y. Li, J.-N. Hwang, G. Xing, and H. Liu, “Rodnet: A real-time radar object detection network cross-supervised by camera-radar fused object 3d localization,” IEEE Journal of Selected Topics in Signal Processing, vol. 15, no. 4, pp. 954–967, 2021.
  25. T. José, A. d. R. L. Ribeiro, and E. D. Moreno, “Performance analysis and application of mobile blockchain in mobile edge computing architecture,” in the 17th Conference on Computer Science and Intelligence Systems-Annals of Computer Science and Information Systems, vol. 32, 2022, pp. 191–197.