Computer-Aided Fall Recognition Using a Three-Stream Spatial-Temporal GCN Model with Adaptive Feature Aggregation

TL;DR

The paper tackles automated fall detection for the elderly using privacy-preserving skeleton data. It introduces a three-stream spatial-temporal GSTCN framework with adaptive feature aggregation and Sep-TCN to reduce computational load while maintaining high accuracy. Across four benchmark datasets, the method achieves near-perfect to perfect accuracies and outperforms state-of-the-art baselines, underscoring robustness and real-time applicability. The approach holds promise for safer, privacy-conscious deployment in smart homes, hospitals, and eldercare facilities, potentially reducing fall-related morbidity and mortality.

Abstract

The prevention of falls is paramount in modern healthcare, particularly for the elderly, as falls can lead to severe injuries or even fatalities. Additionally, the growing incidence of falls among the elderly, coupled with the urgent need to prevent suicide attempts resulting from medication overdose, underscores the critical importance of accurate and efficient fall detection methods. In this scenario, a computer-aided fall detection system is inevitable to save elderly people's lives worldwide. Many researchers have been working to develop fall detection systems. However, the existing fall detection systems often struggle with issues such as unsatisfactory performance accuracy, limited robustness, high computational complexity, and sensitivity to environmental factors due to a lack of effective features. In response to these challenges, this paper proposes a novel three-stream spatial-temporal feature-based fall detection system. Our system incorporates joint skeleton-based spatial and temporal Graph Convolutional Network (GCN) features, joint motion-based spatial and temporal GCN features, and residual connections-based features. Each stream employs adaptive graph-based feature aggregation and consecutive separable convolutional neural networks (Sep-TCN), significantly reducing computational complexity and model parameters compared to prior systems. Experimental results across multiple datasets demonstrate the superior effectiveness and efficiency of our proposed system, with accuracies of 99.51\%, 99.15\%, 99.79\% and 99.85 \% achieved on the ImViA, UR-Fall, Fall-UP and FU-Kinect datasets, respectively. The remarkable performance of our system highlights its superiority, efficiency, and generalizability in real-world fall detection scenarios, offering significant advancements in healthcare and societal well-being.

Figures (4)

• Figure 1: Proposed working flow diagram.
• Figure 2: Details of each module (a) Sep TCN (b) Depthwise separable convolution (c) Classification Module
• Figure 3: Visual representation of body skeleton joints produced using AlphaPose.
• Figure 4: Example illustrating the motion calculation process.