Computer Vision based Fire Detection and Extinguisher System

As it is well known that accidental fire can cause very much damage to important property, so it is required to produce an efficient autonomous system to avoid this damage. Previously, sensors were used for smoke detection, which would have given false alarm in case there exist a smoke coming from c

Project Title

Computer Vision based Fire Detection and Extinguisher System

Project Area of Specialization

Artificial Intelligence

Project Summary

As it is well known that accidental fire can cause very much damage to important property, so it is required to produce an efficient autonomous system to avoid this damage. Previously, sensors were used for smoke detection, which would have given false alarm in case there exist a smoke coming from cigarettes and burning woods. Here we propose a computer vision based fire detection and extinguisher system. Fire is detected using Image Processing techniques on the fire contained image.The image is taken using a digital camera. And after the detection of fire regions, an extinguisher system is automatically triggered using microcontroller.

Project Objectives

Aim of this project is to integrate computer vision and electronics to develop an  automated and accurate surveillance and safety system. Objectives are to secure the sensitive areas like important industrial areas and automate the extinguishing process to reduce the personal causality rate. And develop an effective and accurate system than existing.

Project Implementation Method

This project is based on both the hardware and software. First an image will be captured using an IP camera. So far we have implemented an IEEE paper, forest fire detection using YCbCr colour model. The proposed method adopts rule based colour model due to its less complexity and effectiveness. YCbCr colour space effectively separates luminance from chrominance compared to other colour spaces like RGB and rgb(normalized RGB). The proposed method not only separates fire flame pixels but also separates high temperature fire centre pixels by taking in to account of statistical parameters of fire image in YCbCr colour space like mean and standard deviation. In this method four rules are formed to separate the true fire region. Two rules are used for segmenting the fire region and other two rules are used for segmenting the high temperature fire centre region. The results obtained are compared with the other methods in the literature and shows higher true fire detection rate and less false detection rate. Now, we are trying to implement a latest technique which will hopefully give much better performance than the present one.

Benefits of the Project

After implementing this project we'll have an advance & robust safety system. Personal casualty rate will also be reduced due to the autonomous extinguisher system. Also sensitive areas like important industrial areas will have effective protection.

Technical Details of Final Deliverable

After completion of this project, we'll be able to present a real time implementation of the project along with the innovated image processing algorithm.

Final Deliverable of the Project

HW/SW integrated system

Type of Industry

Security

Technologies

Artificial Intelligence(AI), Others

Sustainable Development Goals

Climate Action

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com