Overview / Usage

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.

Methodology / Approach

Although technology is a significant part of the project, what makes our project unique is its approach to provide real-time tools to the final users. The proposed end devices of our solution monitors a place and identifies the presence of guns and white weapons. If the presence of any of these elements is confirmed, the end devices send a series of frames to the cloud to confirm a potential assault. Currently, we have four alert channels: by sending messages with a chatbot on Whatsapp, by activating an audible alert, by showing the risk in a display integrated into the embedded device, and finally, by displaying the notifications in real-time on a web platform. The project's code is available at: https://github.com/Coding-Rod/crime\_detection

Technologies Used

Hardware

• Jetson Nano
• 3D printing

Software

• VueJS
• Python
• Yolo
• TensorFlow
• Whatsapp API

Documents and Presentations