Comprehensive Analysis of Forest Fire Detection using Deep Learning Models and Conventional Machine Learning Algorithms
Zeynep Hilal Kilimci and Süha Berk Kukuk
Paper : International Journal of Computational and Experimental Science and Engineering
Abstract : Forest fire detection is a very challenging problem in the field of object detection. Fire detection-based image analysis have advantages such as usage on wide open areas, the possibility for operator to visually confirm presence, intensity and the size of the hazards, lower cost for installation and further exploitation. To overcome the problem of fire detection in outdoors, deep learning and conventional machine learning based computer vision techniques are employed to determine the fire detection when indoor fire detection systems are not capable. In this work, we propose a comprehensive analysis of forest fire detection using conventional machine learning algorithms, object detection techniques, deep and hybrid deep learning models. The contribution of this work to the literature is to analyze different classification and object detection techniques in more details that is not addressed before in order to detect forest fire. Experiment results demonstrate that convolutional neural networks outperform other methods with 99.32% of accuracy result.
ObjectDetection-TensorFlowAPI.zip folder contains :
-
Fire folder contains the dataset
-
Models folder contains Single Shot Detector and Faster R-CNN that are Object detection Applications
-
Preparing-Dataset contains codes that need to convert folders types
This is a dataset that I collected to train my own Fire detector with TensorFlow's Object Detection API. Images are from Google and Pixabay. In total, there are 10.000 images.
preparing dataset is used the LabelImg Applications. LabelImg is a graphical image annotation tool. tzutalin/labelImg
.png)
PC requirements that have Intel (R) Core (TM) i5-7200U CPU @ 2.50GHz 2.71 GHz process unit and NVIDIA GeForce 940MX graphic card in Windows 10 operation system.
.png)
Model is Tested On Raspberry Pi 4 8 GB ram
