An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
This work addresses the problem of unclear model behaviors in fall detection for elderly healthcare, but it is incremental as it focuses on analysis rather than novel solutions.
The paper conducted an empirical study to understand how deep convolutional neural networks recognize falls, revealing patterns learned by the nets and factors influencing performance, without proposing a new method.
Detecting unintended falls is essential for ambient intelligence and healthcare of elderly people living alone. In recent years, deep convolutional nets are widely used in human action analysis, based on which a number of fall detection methods have been proposed. Despite their highly effective performances, the behaviors of how the convolutional nets recognize falls are still not clear. In this paper, instead of proposing a novel approach, we perform a systematical empirical study, attempting to investigate the underlying fall recognition process. We propose four tasks to investigate, which involve five types of input modalities, seven net instances and different training samples. The obtained quantitative and qualitative results reveal the patterns that the nets tend to learn, and several factors that can heavily influence the performances on fall recognition. We expect that our conclusions are favorable to proposing better deep learning solutions to fall detection systems.