[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content

Learning Human Postures Using Lab-Depth HOG Descriptors

  • Conference paper
  • First Online:
Computational Collective Intelligence (ICCCI 2023)

Abstract

Human Posture Recognition is gaining increasing attention in the field of computer vision due to its promising applications in the areas of health care, human-computer interaction, and surveillance systems. This paper presents a novel method for human posture recognition by combining both color and depth images and feeding the resulting information into the vision transformer (ViT) model. We want to take advantage of integrating the Lab-D HOG descriptor [18] into the ViT architecture [8]. First, we compute the multispectral Lab-D edge detector by opting for the maximum eigenvalue of the multiplication of the jacobian matrix by its transpose. Second, we select the multispectral corner points by picking the minimum of the eigenvalues of the multispectral Harris matrix. Third, for each selected corner point, we compute a Lab-D HOG descriptor. Last, we feed the extracted Lab-D HOG descriptors into the transformer encoder/decoder by implementing two different strategies. Results show that we outperform state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
GBP 19.95
Price includes VAT (United Kingdom)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
GBP 71.50
Price includes VAT (United Kingdom)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
GBP 89.99
Price includes VAT (United Kingdom)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Abobakr, A., Nahavandi, D., Iskander, J., Hossny, M., Nahavandi, S., Smets, M.: RGB-D human posture analysis for ergonomie studies using deep convolutional neural network. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2885–2890 (2017)

    Google Scholar 

  2. Amine Elforaici, M.E., Chaaraoui, I., Bouachir, W., Ouakrim, Y., Mezghani, N.: Posture recognition using an RGB-D camera: exploring 3D body modeling and deep learning approaches. In: 2018 IEEE Life Sciences Conference (LSC), pp. 69–72 (2018). https://doi.org/10.1109/LSC.2018.8572079

  3. Ayre-Storie, A., Zhang, L.: Deep learning-based human posture recognition. In: 2021 International Conference on Machine Learning and Cybernetics (ICMLC), pp. 1–6 (2021). https://doi.org/10.1109/ICMLC54886.2021.9737241

  4. Baronti, P., Girolami, M., Mavilia, F., Palumbo, F., Luisetto, G.: On the analysis of human posture for detecting social interactions with wearable devices. In: 2020 IEEE International Conference on Human-Machine Systems (ICHMS), pp. 1–6 (2020). https://doi.org/10.1109/ICHMS49158.2020.9209510

  5. Cai, Y., Wang, X., Kong, X.: 3D human pose estimation from RGB+D images with convolutional neural networks. In: Proceedings of the 2nd International Conference on Biomedical Engineering and Bioinformatics, ICBEB 2018, pp. 64–69. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3278198.3278225

  6. Cao, B., Bi, S., Zheng, J., Yang, D.: Human posture recognition using skeleton and depth information. In: 2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA), pp. 275–280 (2018). https://doi.org/10.1109/WRC-SARA.2018.8584233

  7. Ding, W., Hu, B., Liu, H., Wang, X., Huang, X.: Human posture recognition based on multiple features and rule learning. Int. J. Mach. Learn. Cybern. 11, 2529–2540 (2020). https://doi.org/10.1007/s13042-020-01138-y

    Article  Google Scholar 

  8. Dosovitskiy, A., et al.: An image is worth \(16\times 16\) words: transformers for image recognition at scale (2020). https://doi.org/10.48550/ARXIV.2010.11929. https://arxiv.org/abs/2010.11929

  9. Giannakos, I., Mathe, E., Spyrou, E., Mylonas, P.: A study on the effect of occlusion in human activity recognition, pp. 473–482 (2021). https://doi.org/10.1145/3453892.3461337

  10. Gjoreski, H., Gams, M.: Activity/posture recognition using wearable sensors placed on different body locations. In: Proceedings of Signal and Image Processing and Applications (2011). https://doi.org/10.2316/P.2011.716-067

  11. Iazzi, A., Rziza, M., Thami, R.O.H.: Human posture recognition based on projection histogram and Support Vector Machine. In: 2018 9th International Symposium on Signal, Image, Video and Communications (ISIVC), pp. 329–333 (2018). https://doi.org/10.1109/ISIVC.2018.8709235

  12. Li, X., Sun, M., Fang, X.: An approach for detecting human posture by using depth image. In: 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016), pp. 257–261. Atlantis Press (2016)

    Google Scholar 

  13. Li, X., Zhou, Z., Wu, J., Xiong, Y.: Human posture detection method based on wearable devices. J. Healthc. Eng. 2021, 1–8 (2021). https://doi.org/10.1155/2021/8879061

    Article  Google Scholar 

  14. Liu, S., Ostadabbas, S.: A vision-based system for in-bed posture tracking. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1373–1382 (2017). https://doi.org/10.1109/ICCVW.2017.163

  15. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021). https://doi.org/10.48550/ARXIV.2103.14030. https://arxiv.org/abs/2103.14030

  16. Malmsten, J., Cengiz, H., Lood, D.: Histogram of oriented gradients in a vision transformer (2022)

    Google Scholar 

  17. Mefteh, S., Kaâniche, M.B., Ksantini, R., Bouhoula, A.: A novel multispectral lab-depth based edge detector for color images with occluded objects. In: VISIGRAPP (4: VISAPP), pp. 272–279 (2019)

    Google Scholar 

  18. Mefteh, S., Kaâniche, M.B., Ksantini, R., Bouhoula, A.: A novel multispectral corner detector and a new local descriptor: an application to human posture recognition. Multimed. Tools Appl. 82, 28937–28956 (2023). https://doi.org/10.1007/s11042-023-14788-1

    Article  Google Scholar 

  19. Ni, B., Wang, G., Moulin, P.: RGBD-HuDaAct: a color-depth video database for human daily activity recognition. In: Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. (eds.) Consumer Depth Cameras for Computer Vision. ACVPR, pp. 193–208. Springer, London (2013). https://doi.org/10.1007/978-1-4471-4640-7_10

    Chapter  Google Scholar 

  20. Popescu, A.C., Mocanu, I., Cramariuc, B.: PRECIS HAR (2019). https://doi.org/10.21227/mene-ck48

  21. Qi, L., Han, Y.: Human motion posture detection algorithm using deep reinforcement learning. Mob. Inf. Syst. 2021, 1–10 (2021). https://doi.org/10.1155/2021/4023861

    Article  Google Scholar 

  22. Ramanan, D., Sminchisescu, C.: Training deformable models for localization, vol. 1, pp. 206–213 (2006). https://doi.org/10.1109/CVPR.2006.315

  23. Reddy, B.H., Karthikeyan, P.: Classification of fire and smoke images using decision tree algorithm in comparison with logistic regression to measure accuracy, precision, recall, f-score. In: 2022 14th International Conference on Mathematics, Actuarial Science, Computer Science and Statistics (MACS), pp. 1–5. IEEE (2022)

    Google Scholar 

  24. Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. CoRR abs/1506.02640 (2015). https://arxiv.org/abs/1506.02640

  25. Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 10347–10357. PMLR (2021). https://proceedings.mlr.press/v139/touvron21a.html

  26. Wang, W.J., Chang, J.W., Haung, S.F., Wang, R.J.: Human posture recognition based on images captured by the kinect sensor. Int. J. Adv. Robot. Syst. 13(2), 54 (2016). https://doi.org/10.5772/62163

    Article  Google Scholar 

  27. Wu, Q., Xu, G., Zhang, S., Li, Y., Wei, F.: Human 3D pose estimation in a lying position by RGB-D images for medical diagnosis and rehabilitation (2020). https://doi.org/10.1109/EMBC44109.2020.9176407

  28. Wu, Y., et al.: Rethinking classification and localization for object detection, pp. 10183–10192 (2020). https://doi.org/10.1109/CVPR42600.2020.01020

  29. Zhang, J., Wu, C., Wang, Y.: Human fall detection based on body posture spatio-temporal evolution. Sensors 20(3), 946 (2020). https://doi.org/10.3390/s20030946. https://www.mdpi.com/1424-8220/20/3/946

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Safa Mefteh .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mefteh, S., Kaâniche, MB., Ksantini, R., Bouhoula, A. (2023). Learning Human Postures Using Lab-Depth HOG Descriptors. In: Nguyen, N.T., et al. Computational Collective Intelligence. ICCCI 2023. Lecture Notes in Computer Science(), vol 14162. Springer, Cham. https://doi.org/10.1007/978-3-031-41456-5_42

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-41456-5_42

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-41455-8

  • Online ISBN: 978-3-031-41456-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics