Novel Deep Learning Pipeline for Automatic Weapon Detection

TL;DR

This paper introduces a novel ensemble deep learning pipeline for real-time weapon detection in surveillance videos, significantly improving accuracy over existing models.

Contribution

It presents a new ensemble CNN architecture trained with diverse mini-batches, enhancing weapon detection performance in real-time video analysis.

Findings

5% average increase in accuracy, specificity, and recall

Effective ensemble approach with diverse CNN architectures

Improved detection performance over state-of-the-art models

Abstract

Weapon and gun violence have recently become a pressing issue today. The degree of these crimes and activities has risen to the point of being termed as an epidemic. This prevalent misuse of weapons calls for an automatic system that detects weapons in real-time. Real-time surveillance video is captured and recorded in almost all public forums and places. These videos contain abundant raw data which can be extracted and processed into meaningful information. This paper proposes a novel pipeline consisting of an ensemble of convolutional neural networks with distinct architectures. Each neural network is trained with a unique mini-batch with little to no overlap in the training samples. This paper will present several promising results using multiple datasets associated with comparing the proposed architecture and state-of-the-art (SoA) models. The proposed pipeline produced an average increase of 5% in accuracy, specificity, and recall compared to the SoA systems.