Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations

2026-05-21

AI Summary

This work addresses the critical challenge of early identification of suicide risk among passengers in subway stations by proposing the first explainable AI framework that formalizes suicide risk assessment as a standalone task. The framework integrates multimodal cues to jointly model passenger behavior, spatial context, and temporal dynamics, leveraging pedestrian tracking, behavior recognition, platform semantic segmentation, and trajectory-driven risk heatmaps to enable comprehensive risk evaluation—without directly inferring suicidal intent. Experimental results on real-world surveillance data demonstrate the method’s effectiveness, achieving a ROC-AUC of 83.2% and highlighting its potential for practical deployment in real-time safety monitoring systems.

Abstract

Understanding and monitoring human behavior in metro stations play an important role in supporting suicide prevention efforts, where early identification of high-risk situations can enable timely intervention. This requires assessing suicide risk from a surveillance video by jointly reasoning about the behavior of each passenger, his/her spatial context, and temporal dynamics. However, this assessment using videos captured by surveillance cameras is challenging, as it demands accurate perception of human motion, understanding of platform geometry, and aggregation of heterogeneous behavioral cues over time. In this work, we formalize the task of Suicide Risk Assessment (SRA) in metro stations and introduce the first interpretable framework that addresses this challenge. Unlike approaches that focus on isolated subtasks or attempt to infer intent directly, our formulation assesses suicide risk from accumulated evidence by incorporating person tracking, activity recognition, semantic segmentation of the platform, and trajectory-driven risk heatmap modeling. By formalizing SRA as a distinct task and benchmarking a complete operational pipeline achieving 83.2% ROC-AUC on real surveillance data, this work highlights the complexity of suicide risk assessment and opens new directions for research on interpretable AI systems for social good.

Problem

• Suicide Risk Assessment
• Video Surveillance
• Human Behavior Analysis
• Metro Stations
• Interpretable AI

Innovation

• Suicide Risk Assessment
• Interpretable AI
• Video Surveillance
• Trajectory-driven Risk Heatmap
• Multimodal Behavior Analysis