Two-Stage Violence Detection Using ViTPose and Classification Models at Smart Airports

TL;DR

This paper presents a real-time violence detection system for smart airports that combines ViTPose for pose estimation with CNN-BiLSTM models, demonstrating improved accuracy and robustness in surveillance scenarios.

Contribution

The study introduces a novel two-stage framework integrating ViTPose and classification models for real-time violence detection in airport security.

Findings

High accuracy in violence classification on AIRTLab dataset

Robust performance in real-world airport scenarios

Reduced false positives in violence detection

Abstract

This study introduces an innovative violence detection framework tailored to the unique requirements of smart airports, where prompt responses to violent situations are crucial. The proposed framework harnesses the power of ViTPose for human pose estimation. It employs a CNN - BiLSTM network to analyse spatial and temporal information within keypoints sequences, enabling the accurate classification of violent behaviour in real time. Seamlessly integrated within the SAFE (Situational Awareness for Enhanced Security framework of SAAB, the solution underwent integrated testing to ensure robust performance in real world scenarios. The AIRTLab dataset, characterized by its high video quality and relevance to surveillance scenarios, is utilized in this study to enhance the model's accuracy and mitigate false positives. As airports face increased foot traffic in the post pandemic era, implementing AI driven violence detection systems, such as the one proposed, is paramount for improving security, expediting response times, and promoting data informed decision making. The implementation of this framework not only diminishes the probability of violent events but also assists surveillance teams in effectively addressing potential threats, ultimately fostering a more secure and protected aviation sector. Codes are available at: https://github.com/Asami-1/GDP.