Autors: Spasova, V. G., Iliev, I. T., Petrova, G. I.
Title: Privacy preserving fall detection based on simple human silhouette extraction and a linear support vector machine
Keywords: fall detection, linear support vector machine, assistive systems

Abstract: The paper presents a novel fast, real-time and privacy protecting algorithm for fall detection based on geometric properties of the human silhouette and a linear support vector machine. The algorithm uses infrared and visible light imagery in order to detect the human. A simple real-time human silhouette extraction algorithm has been developed and used to extract features for training of the support vector machine. The achieved sensitivity and specificity of the proposed approach are over 97% which match state of the art research in the area of fall detection. The developed solution uses low-cost hardware components and open source software library and is suitable for usage in assistive systems for the home or nursing homes.

References

    Issue

    International Journal Bioautomation, vol. 20, issue 2, pp. 237-252, 2016, Bulgaria, Institute of Biophysics and Biomedical Engineering, ISSN 13141902

    Цитирания (Citation/s):
    1. Wang, X., Ellul, J., Azzopardi, G., Elderly Fall Detection Systems: A Literature Survey, Frontiers in Robotics and AI 7,71 - 2020 - в издания, индексирани в Scopus или Web of Science
    2. Zhang, S., Li, Z., Wei, Z., Wang, S., An automatic human fall detection approach using RGBD cameras, Proceedings of 2016 5th International Conference on Computer Science and Network Technology, ICCSNT 2016 8070265, pp. 781-784 - 2017 - в издания, индексирани в Scopus или Web of Science
    3. Wang, X., The application of genetic algorithms in the biological medical diagnostic research, International Journal Bioautomation 20(4), pp. 493-504 - 2016 - в издания, индексирани в Scopus или Web of Science
    4. Performance, Challenges, and Limitations in Multimodal Fall Detection Systems: A Review - 2021 - в издания, индексирани в Scopus или Web of Science
    5. Performance, Challenges, and Limitations in Multimodal Fall Detection Systems: A Review - 2021 - в издания, индексирани в Scopus или Web of Science

    Вид: статия в списание, публикация в издание с импакт фактор, публикация в реферирано издание