An Edge-device Based Fast Fall Detection Using Spatio-temporal Optical Flow Model

The elderly fall detection is one critical function in health of the elderly. A real-time fall detection for the elderly has been a significant healthcare issue. The traditional video analysis on cloud has large communication overhead. In this paper, a fast fall detection system based on the spatiotemporal optical flow model is proposed, which is further deeply compressed by a structured tensorization towards an implementation on edge devices. Firstly, an object extractor is built to extract motion objects from video clips. The spatiotemporal optical flow model is formed to estimate optical flow fields of motion objects. It can extract features from objects and their corresponding optical flow fields. Then these two features are fused to form new spatio-temporal features. Finally, the tensor-compressed model processes the fused features to determine fall detection, where the strongest optical field would indicate the fall. We conduct experiments with Multicam and URFD datasets. Clinical relevance- It demonstrates that the proposed model achieves the accuracy of 9623% and 9937%, respectively. Besides, it attains the inference speed of 833 FPS and storage reduction of 2109x. Our work is further implemented on an AI acceleration core based edge device, and the runtime is reduced by 921x.This high performance system can be applied to the field of clinical monitoring in the future.