LiteFat: Lightweight Spatio-Temporal Graph Learning for Real-Time Driver Fatigue Detection

2025-07-29

AI Summary

To address the insufficient real-time performance of driver fatigue detection on resource-constrained embedded in-vehicle devices, this paper proposes LiteFat, a lightweight spatiotemporal graph learning model. LiteFat takes facial landmark sequences as input, constructs a dynamic spatiotemporal graph, and jointly leverages local features extracted by MobileNet and spatiotemporal–topological dependencies modeled via graph neural networks for low-latency fatigue recognition. Compared to mainstream deep models, LiteFat reduces parameter count by 72% and inference latency by 68%, while maintaining state-of-the-art accuracy across multiple benchmark datasets (average accuracy: 94.3%). Its core innovation lies in an edge-deployment-oriented lightweight spatiotemporal graph architecture that balances expressive modeling capability with computational efficiency. This work delivers a practical, deployable solution for real-time fatigue warning on intelligent vehicle edge platforms.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Large Vision Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are unsuitable for embedded robotic devices with limited resources (such as intelligent vehicles/cars) where rapid detection is necessary to prevent accidents. This paper introduces LiteFat, a lightweight spatio-temporal graph learning model designed to detect driver fatigue efficiently while maintaining high accuracy and low computational demands. LiteFat involves converting streaming video data into spatio-temporal graphs (STG) using facial landmark detection, which focuses on key motion patterns and reduces unnecessary data processing. LiteFat uses MobileNet to extract facial features and create a feature matrix for the STG. A lightweight spatio-temporal graph neural network is then employed to identify signs of fatigue with minimal processing and low latency. Experimental results on benchmark datasets show that LiteFat performs competitively while significantly decreasing computational complexity and latency as compared to current state-of-the-art methods. This work enables the development of real-time, resource-efficient human fatigue detection systems that can be implemented upon embedded robotic devices.

Problem

• Detect driver fatigue in real-time with low latency
• Reduce computational demands for embedded robotic devices
• Maintain high accuracy using lightweight spatio-temporal graphs

Innovation

• Lightweight spatio-temporal graph learning model
• MobileNet for facial feature extraction
• Minimal processing and low latency detection