Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2022, 5(4); doi: 10.25236/AJCIS.2022.050405.

YOLOv5-based fall detection method


Sichao Cheng1, Hekai Zhang2

Corresponding Author:
Sichao Cheng

1Tianjin University of Science and Technology, Tianjin, China

2Heilongjiang University, Harbin, Heilongjiang, China


With the rising elderly population in China, detecting whether an elderly person has fallen is one of the problems that people need to pay attention to today, however, most of the current detection methods are affected by problems such as expensive, vulnerable to environment and not easy to implement. In order to solve the above problems, this paper proposes a fall detection method with YOLOv5s as the basic network model, which first enhances the original image, and then improves the loss function and NMS non-maximal suppression. The final results show that applying this improved algorithm model can effectively perform fall detection.


Fall detection; YOLOv5s; NMS non-maximal suppression

Cite This Paper

Sichao Cheng, Hekai Zhang. YOLOv5-based fall detection method. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 4: 29-34. https://doi.org/10.25236/AJCIS.2022.050405.


[1] Lisa Ku, Suzhen Wang, Yiqian Chen, Chenlong Gao, Chunyu Hu, Xinlong Jiang, Zenyu Chen, Xingyu Xiao. A review of fall detection algorithms based on wearable devices [J]. Journal of Zhejiang University (Engineering Edition), 2018, 52(09): 1717-1728.

[2] Tu, Biqi. Research on fall detection algorithm for the elderly based on multi-sensor fusion [D]. Zhejiang University of Technology, 2017.

[3] Zhu Yan,Zhang Yaping,Li Shusheng,Li Weimin,Liu Yalu. Fall detection algorithm based on deep vision sensor and convolutional neural network [J]. Optical Technology, 2021, 47(01): 56-61. DOI: 10.13741/j.cnki.11-1879/o4.2021.01.011.

[4] Chen, Yijia. Faster RCNN-based target detection system [D]. Harbin Institute of Technology, 2019.

[5] Ruan Qi Yang. Design and implementation of YOLO-based target detection algorithm [D]. Beijing University of Posts and Telecommunications, 2019.

[6] Yang Can. Research on traffic target detection method based on deep learning [D]. East China Jiaotong University, 2021. DOI: 10.27147/d.cnki.ghdju.2021.000076.

[7] Liu, Jingyi. Research on adaptive planar area geometry partitioning algorithm [D]. China University of Petroleum (East China), 2017.

[8] Chen Zhaofan,Zhao Chunyang,Li Bo. A border regression loss function to improve IoU loss [J]. Computer Application Research, 2020, 37(S2): 293-296.

[9] Li Yongshang, Ma Ronggui, Zhang Meiyue. Improving YOLOv5s+DeepSORT for monitoring video traffic statistics [J/OL]. Computer Engineering and Applications: 1-11 [2022-02-25]. 

[10] Wu Hongwei. Research on license plate detection and recognition system based on deep learning [D]. Dalian University of Technology, 2021. DOI: 10.26991/d.cnki.gdllu. 2021.003057.

[11] Wen Jie-Wen, Zhan Yin-Wei, Li Chu-Hong, Lu Jian-Biao. An Atrous filter design to enhance the detection capability of small targets in SSD [J]. Computer Application Research, 2019, 36(03): 861-865+872. DOI: 10.19734/j.issn.1001-3695.2017.09.0967.