A Video-based Fall Detection Network by Spatio-temporal Joint-point Model on Edge Devices
Ziyi Guan1, Shuwei Li1, Yuan Cheng2, Changhai Man1, Wei Mao1, Ngai Wong3, Hao Yu1
1School of Microelectronics, Southern University of Science and Technology, Shenzhen, China
2Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai, China
3Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China
ABSTRACT
Tripping or falling is among the top threats in elderly healthcare, and the development of automatic fall detection systems are of considerable importance.With the fast development of the Internet of Things (IoT), camera vision-based solutions have drawn much attention in recent years. The traditional fall video analysis on the cloud has significant communication overhead. This work introduces a fast and lightweight video fall detection network based on a spatio-temporal joint-point model to overcome these hurdles. Instead of detecting falling motion by the traditional Convolutional Neural Networks (CNNs), we propose a Long Short-Term Memory (LSTM) model based on time-series jointpoint features, extracted from a pose extractor and then filtered from a geometric joint-point filter. Experiments are conducted to verify the proposed framework, which shows a high sensitivity of 98:46% on Multiple Cameras Fall Dataset and 100% on UR Fall Dataset. Furthermore, our model can achieve pose estimation tasks simultaneously, attaining 73:3 mAP in the COCO keypoint challenge dataset, which outperforms the OpenPose work by 8%.
Keywords: Fall Detection, Pose Estimation, Spatio-Temporal Model, Joint-Point Features.
