Document For AI Training Models

Gun & Fire Detection

Created By
Rocketflyer Technology Private Limited

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Agenda
This document has been prepared to describe the core practices which have been followed during the training process of AI (Artificial Intelligence) Models -
Gun Detection & Fire Detection. The document also contains information of architecture used and the overall process flow. The document is capable to
provide following informations-

- Overview
- Process Overview
- Architecture
- Model Performance
- Input vs Output

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Overview
Real-time object detection to improve surveillance methods is one of the sought-after applications of Convolutional Neural Networks
(CNNs). This model works in the detection of fire and handguns in areas monitored by cameras. Home fires, industrial explosions, and
wildfires are a huge problem that cause adverse effects on the environment. Gun violence and mass shootings are also on the rise in
certain parts of the world. Such incidents are time-sensitive and can cause a huge loss to life and property. Hence, the proposed work has
built a deep learning model based on the YOLOv3 algorithm that processes a video frame-by-frame to detect such anomalies in real-time
and generate an alert for the concerned authorities. The final model has a validation loss of 0.2864, with a detection rate of 45 frames per
second and has been benchmarked on datasets like IMFDB, UGR, and FireNet with accuracies of 89.3%, 82.6% and 86.5% respectively.
Experimental result satisfies the goal of the proposed model and also shows a fast detection rate that can be deployed indoor as well as
outdoor.

The main idea of our project is to create a system that monitors surveillance data of an area and sends alerts in case a fire or gun is
detected. Closed Circuit Television (CCTV) cameras record video footage 24 hours of the day, however there isn’t enough manpower
to monitor each and every camera for various anomalous events. There are systems to detect fire using smoke sensors in many places
like schools, educational institutes, etc. However, a cost-effective system that combines fire as well as gun detection for security
purposes is the need of the time. Surveillance systems such as closed-circuit television (CCTV) and drones are becoming
increasingly common. Research also shows that the installation of CCTV systems helps to combat mass shooting incidents and are
also extremely important for evidence collection.

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Process Flow - High Level Technical Flow of Branch

Video Ingestion to AI
•Load YOLO Model
Raw Input Video Video Transformation •Detect Object
Trained AI Model •Get Box Dimensions
Source Services
Converted frames •Draw Label

AI Processed Output Frame

UI Stream Frames AI Prediction

Business Inference
Engine

AWS S3
Save Video During Upload To Cloud
Centralized Monitoring Trigger Inferences
inference Occurrence Storage
System

Return URL

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Architecture
● batch=1
● subdivisions=1
● width=416
● height=416
● channels=3

YOLOv3
● momentum=0.9
● decay=0.0005
● angle=0
● saturation = 1.5
● exposure = 1.5
● hue=.1
● learning_rate=0.001
● burn_in=1000
● max_batches = 19000
● policy=steps
● steps=15000,17000
● Scales=.1,.1

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Model Performance

A custom dataset has been created as there was no dataset for images of guns from a CCTV perspective. Therefore, 300 gun
images were collected from CCTV images of humans with a gun.

Our dataset also includes 2 videos containing gun to test the performance of our model on video. The model also gives good
performance when used on video by frame by frame processing.

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Input vs Output

Gun

Input Output

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
Input vs Output

Input Output

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.
 Thank You!
We love solving Engineering and Business problems.If you have a use case in mind which our platform doesn’t cater at present. We would try whatever it takes to
accommodate the suggested feature in our product plan.

Do write us back to us with your feedback, suggestions, queries and custom requirements
Reach out to our Product Engineering Team at [email protected]

Strictly Private & Confidential | All rights are reserved by Rocket Flyer Technology Pvt. Ltd.