Cut and Continuous Paste towards Real-time Deep Fall Detection

TL;DR

This paper introduces a lightweight deep learning framework for real-time fall detection using a novel image synthesis method that condenses human motion into a single frame, enabling efficient classification.

Contribution

It presents a new synthetic data generation technique and a simplified image-based approach for fall detection with a small neural network, improving efficiency and performance.

Findings

Effective fall detection on URFD and AIHub datasets

Synthetic data enhances training with limited model size

Single-frame motion representation simplifies the task

Abstract

Deep learning based fall detection is one of the crucial tasks for intelligent video surveillance systems, which aims to detect unintentional falls of humans and alarm dangerous situations. In this work, we propose a simple and efficient framework to detect falls through a single and small-sized convolutional neural network. To this end, we first introduce a new image synthesis method that represents human motion in a single frame. This simplifies the fall detection task as an image classification task. Besides, the proposed synthetic data generation method enables to generate a sufficient amount of training dataset, resulting in satisfactory performance even with the small model. At the inference step, we also represent real human motion in a single image by estimating mean of input frames. In the experiment, we conduct both qualitative and quantitative evaluations on URFD and AIHub airport datasets to show the effectiveness of our method.