hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20190411015902

An Improved Feature-Based Method for Fall Detection

Leiyue Yao ; School of Information Engineering, Nanchang University, Nanchang, China, 330031
Wei Yang ; Jiangxi University of Technology, The Center of Collaboration and Innovation, Nanchang, China, 330098
Wei Huang   ORCID icon orcid.org/0000-0002-0541-8612 ; School of Information Engineering, Nanchang University, Nanchang, China, 330031

Puni tekst: engleski, pdf (1 MB) str. 1363-1368 preuzimanja: 50* citiraj
APA 6th Edition
Yao, L., Yang, W. i Huang, W. (2019). An Improved Feature-Based Method for Fall Detection. Tehnički vjesnik, 26 (5), 1363-1368. https://doi.org/10.17559/TV-20190411015902
MLA 8th Edition
Yao, Leiyue, et al. "An Improved Feature-Based Method for Fall Detection." Tehnički vjesnik, vol. 26, br. 5, 2019, str. 1363-1368. https://doi.org/10.17559/TV-20190411015902. Citirano 15.11.2019.
Chicago 17th Edition
Yao, Leiyue, Wei Yang i Wei Huang. "An Improved Feature-Based Method for Fall Detection." Tehnički vjesnik 26, br. 5 (2019): 1363-1368. https://doi.org/10.17559/TV-20190411015902
Harvard
Yao, L., Yang, W., i Huang, W. (2019). 'An Improved Feature-Based Method for Fall Detection', Tehnički vjesnik, 26(5), str. 1363-1368. https://doi.org/10.17559/TV-20190411015902
Vancouver
Yao L, Yang W, Huang W. An Improved Feature-Based Method for Fall Detection. Tehnički vjesnik [Internet]. 2019 [pristupljeno 15.11.2019.];26(5):1363-1368. https://doi.org/10.17559/TV-20190411015902
IEEE
L. Yao, W. Yang i W. Huang, "An Improved Feature-Based Method for Fall Detection", Tehnički vjesnik, vol.26, br. 5, str. 1363-1368, 2019. [Online]. https://doi.org/10.17559/TV-20190411015902

Sažetak
Aiming at improving the efficiency and accuracy of fall detection, this paper fuses traditional feature-based methods and Support Vector Machine (SVM). The proposed method provides two major improvements. Firstly, the classic features were adopted and together with machine learning technology form an improved and efficient fall detection method. Secondly, the definition of a threshold which needs massive experiments was now learned by the program itself. Compared with the current popular end-to-end deep learning methods, the improved feature-based method fusing machine learning technology shows great advantages in time efficiency because of the significant reduction of the input parameters. Additionally, with the help of SVM, the thresholds need no manual definition, which saves a lot of time and makes it more precise. Our approach is evaluated on a public dataset, TST fall detection dataset v2. The results show that our approach achieves an accuracy of 93.56%, which is better than other typical methods. Furthermore, the approach can be used in real-time video surveillance because of its time efficiency and robustness.

Ključne riječi
computer vision; fall detection; feature-based method; handcrafted feature; Support Vector Machine (SVM)

Hrčak ID: 226032

URI
https://hrcak.srce.hr/226032

Posjeta: 83 *