Automatic Handgun Detection Alarm in Videos Using Deep Learning
This addresses the need for automated surveillance systems to reduce human intervention, though it is incremental as it builds on existing deep learning methods for a specific domain.
The paper tackles the problem of automatic handgun detection in videos by developing a system that minimizes false positives using a deep learning approach, achieving alarm activation in 27 out of 30 scenes within 0.2 seconds after five successive true positives.
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.