Distributed Intelligent Video Surveillance for Early Armed Robbery Detection based on Deep Learning

TL;DR

This paper presents a distributed IoT-based video surveillance system utilizing deep learning for early detection of armed robberies, combining weapon detection and scene classification to reduce false positives in real-time monitoring.

Contribution

The study introduces a novel distributed surveillance system integrating weapon detection with scene classification using deep learning, enhancing accuracy and reducing false alarms in crime detection.

Findings

YOLOv5s achieved 0.87 mAP at 4.43 FPS for weapon detection.

The 3DCNN classifier reached 0.88 accuracy in identifying robbery scenes.

System effectively reduces false positives in real-time multi-location surveillance.

Abstract

Low employment rates in Latin America have contributed to a substantial rise in crime, prompting the emergence of new criminal tactics. For instance, "express robbery" has become a common crime committed by armed thieves, in which they drive motorcycles and assault people in public in a matter of seconds. Recent research has approached the problem by embedding weapon detectors in surveillance cameras; however, these systems are prone to false positives if no counterpart confirms the event. In light of this, we present a distributed IoT system that integrates a computer vision pipeline and object detection capabilities into multiple end-devices, constantly monitoring for the presence of firearms and sharp weapons. Once a weapon is detected, the end-device sends a series of frames to a cloud server that implements a 3DCNN to classify the scene as either a robbery or a normal situation, thus minimizing false positives. The deep learning process to train and deploy weapon detection models uses a custom dataset with 16,799 images of firearms and sharp weapons. The best-performing model, YOLOv5s, optimized using TensorRT, achieved a final mAP of 0.87 running at 4.43 FPS. Additionally, the 3DCNN demonstrated 0.88 accuracy in detecting abnormal situations. Extensive experiments validate that the proposed system significantly reduces false positives while autonomously monitoring multiple locations in real-time.