Automatic Handgun Detection Alarm in Videos Using Deep Learning

TL;DR

This paper introduces a deep learning-based system for automatic handgun detection in videos, aiming to improve surveillance by reducing false positives and enabling quick alarm activation.

Contribution

The work develops a novel training dataset and evaluates CNN-based models, with the Faster R-CNN approach showing high effectiveness in real-time handgun detection.

Findings

Faster R-CNN achieved the best detection performance.

The system activates alarms within 0.2 seconds in most scenes.

A new metric, AApI, was proposed to evaluate detection system performance.

Abstract

Current surveillance and control systems still require human supervision and intervention. This work presents a novel automatic handgun detection system in videos appropriate for both, surveillance and control purposes. We reformulate this detection problem into the problem of minimizing false positives and solve it by building the key training data-set guided by the results of a deep Convolutional Neural Networks (CNN) classifier, then assessing the best classification model under two approaches, the sliding window approach and region proposal approach. The most promising results are obtained by Faster R-CNN based model trained on our new database. The best detector show a high potential even in low quality youtube videos and provides satisfactory results as automatic alarm system. Among 30 scenes, it successfully activates the alarm after five successive true positives in less than 0.2 seconds, in 27 scenes. We also define a new metric, Alarm Activation per Interval (AApI), to assess the performance of a detection model as an automatic detection system in videos.