Detection of Intoxicated Individuals from Facial Video Sequences via a Recurrent Fusion Model

TL;DR

This paper presents a novel video-based facial analysis method combining facial landmarks and spatiotemporal features to accurately detect alcohol intoxication, outperforming existing approaches and supporting public safety applications.

Contribution

Introduces a new fusion model integrating facial landmark analysis with 3D visual features for alcohol intoxication detection, along with a curated dataset for training and evaluation.

Findings

Achieves 95.82% accuracy in intoxication detection

Outperforms baseline models in precision and recall

Demonstrates potential for real-world public safety deployment

Abstract

Alcohol consumption is a significant public health concern and a major cause of accidents and fatalities worldwide. This study introduces a novel video-based facial sequence analysis approach dedicated to the detection of alcohol intoxication. The method integrates facial landmark analysis via a Graph Attention Network (GAT) with spatiotemporal visual features extracted using a 3D ResNet. These features are dynamically fused with adaptive prioritization to enhance classification performance. Additionally, we introduce a curated dataset comprising 3,542 video segments derived from 202 individuals to support training and evaluation. Our model is compared against two baselines: a custom 3D-CNN and a VGGFace+LSTM architecture. Experimental results show that our approach achieves 95.82% accuracy, 0.977 precision, and 0.97 recall, outperforming prior methods. The findings demonstrate the model's potential for practical deployment in public safety systems for non-invasive, reliable alcohol intoxication detection.