A deep learning model for detecting fire in video and camera streams
FireNet is an artificial intelligence project for real-time fire detection.
This is the first release of the FireNet. It contains an annotated dataset of 502 images splitted into 412 images for training and 90 images for validation.
>>> DOWNLOAD, TRAINING AND DETECTION:
The FireNet dataset is provided for download in the release section of this repository. You can download the dataset via the link below.
We have also provided a ImageAI codebase to train a YOLOv3 detection model on the images
and perform detection in mages and videos using a pre-trained model (also using YOLOv3) provided in the release section of this repository.
The python codebase is contained in the firenet.py file and the detection configuration JSON file for detection is also provided the
<a href="detectionconfig.json" >detectionconfig.json. The pretrained YOLOv3 model is available for download via the link below.
<a href="https://github.com/OlafenwaMoses/FireNET/releases/download/v1.0/detectionmodel-ex-33--loss-4.97.h5" >https://github.com/OlafenwaMoses/FireNET/releases/download/v1.0/detection_model-ex-33--loss-4.97.h5
Running the experiment or detection requires that you have Tensorflow, and Keras, OpenCV and ImageAI installed. You can install this dependencies via the commands below.
- Tensorflow 1.4.0 (and later versions) Install or install via pip
pip3 install --upgrade tensorflow
- OpenCV Install or install via pip
pip3 install opencv-python
- Keras 2.x Install or install via pip
pip3 install keras
- ImageAI 2.0.3
pip3 install imageai --upgrade