# Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks

arXiv: https://arxiv.org/abs/1910.06540 · HTML: https://mlsanity.com/paper/1910.06540/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2019.

## Built on by (most cited first, 5 of 5)

- [Fast Facial Landmark Detection and Applications: A Survey](https://mlsanity.com/paper/2101.10808/) (2021)
- [Applying Spatiotemporal Attention to Identify Distracted and Drowsy Driving with Vision Transformers](https://mlsanity.com/paper/2207.12148/) (2022)
- [AdaEnlight: Energy-aware Low-light Video Stream Enhancement on Mobile Devices](https://mlsanity.com/paper/2211.16135/) (2022)
- [Real-Time Drivers' Drowsiness Detection and Analysis through Deep Learning](https://mlsanity.com/paper/2511.12438/) (2025)
- [HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment](https://mlsanity.com/paper/2604.08435/) (2026)

## Abstract (arXiv)

Driver drowsiness increases crash risk, leading to substantial road trauma each year. Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a mobile phone. Phone applications reduce the need for specialised hardware and hence, enable a cost-effective roll-out of the technology across the driving population. While it has been shown that three-dimensional (3D) operations are more suitable for spatiotemporal feature learning, current methods for drowsiness detection commonly use frame-based, multi-step approaches. However, computationally expensive techniques that achieve superior results on action recognition benchmarks (e.g. 3D convolutions, optical flow extraction) create bottlenecks for real-time, safety-critical applications on mobile devices. Here, we show how depthwise separable 3D convolutions, combined with an early fusion of spatial and temporal information, can achieve a balance between high prediction accuracy and real-time inference requirements. In particular, increased accuracy is achieved when assessment requires motion information, for example, when sunglasses conceal the eyes. Further, a custom TensorFlow-based smartphone application shows the true impact of various approaches on inference times and demonstrates the effectiveness of real-time monitoring based on out-of-sample data to alert a drowsy driver. Our model is pre-trained on ImageNet and Kinetics and fine-tuned on a publicly available Driver Drowsiness Detection dataset. Fine-tuning on large naturalistic driving datasets could further improve accuracy to obtain robust in-vehicle performance. Overall, our research is a step towards practical deep learning applications, potentially preventing micro-sleeps and reducing road trauma.