Aerial Fire and Smoke Essential Dataset

Citation Author(s):
Giovanny
Vazquez
University of Nevada, Las Vegas
Shengjie
Zhai
University of Nevada, Las Vegas
Mei
Yang
University of Nevada, Las Vegas
Submitted by:
Giovanny Vazquez
Last updated:
Sun, 02/02/2025 - 19:29
DOI:
10.21227/h2zw-pq68
Data Format:
.jpg; .txt
Research Article Link:
Transfer Learning Enhanced Deep Learning Model for Wildfire Flame and Smoke Detection
Links:
Wildfire Detection with Bounding Boxes - Essential Computer Vision Project
License:
Creative Commons Attribution
120 Views
Categories:
Artificial Intelligence
Machine Learning
Image Processing
Computer Vision
Climate Change/Environmental
Geoscience and Remote Sensing
Remote Sensing
Keywords:
Fire; Fire detection; Fire prevention; Wildfire; Unmanned Aerial Vehicles; UAVs; UAV; Drones; Aerial Imagery; Computer Vision; Image Processing; Machine Learning
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

A new small aerial flame dataset, called the Aerial Fire and Smoke Essential (AFSE) dataset, is created which is comprised of screenshots from different YouTube wildfire videos as well as images from FLAME2. Two object categories are included in this dataset: smoke and fire. The collection of images is made to mostly contain pictures utilizing aerial viewpoints. It contains a total of 282 images with no augmentations and has a combination of images with only smoke, fire and smoke, and no fire nor smoke. A total of 66 images are taken from the FLAME2 dataset while the remaining images are taken from recent wildfires in Alberta, British Columbia, California, Hawaii, Oregon, Greece, and Turkey. There are 656 instances of fire and 333 instances of smoke in the dataset. 

Instructions: 

Images and annotations are organized into the "images" and "labels" directories, respectively. 

Images and annotations are split into training, validation, and testing folders.

Annotations are saved into YOLOv5 PyTorch format. 

 

Introductory IEEE Access Paper Link: https://ieeexplore.ieee.org/document/10577715

DOI: 10.1109/SmartNets61466.2024.10577715

Funding Agency: 
National Science Foundation
Grant Number: 
1949585

Comments

Good One

Submitted by Jayadeep Gondhipalli on Sun, 02/02/2025 - 23:29

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?