time-series-9

Fire Detection

3260 papers • 126 benchmarks • 313 datasets

Detection of fire using multi-variate time series sensor data.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in fire-detection-9

Trend

Dataset

Best Model

Actions

NIST Report of Test FR 4016

Libraries

i

Use these libraries to find fire-detection-9 models and implementations

Datasets

895 Fire Videos Data

Subtasks

No subtasks available.

Most implemented papers

Efficient and Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection

T. Breckon, Neelanjan Bhowmik, W. Thomson•Fri Oct 16 2020

This work investigates different Convolutional Neural Network architectures and their variants for the non-temporal real-time bounds detection of fire pixel regions in video (or still) imagery and achieves an accuracy of 95% for full-frame binary classification and 97% for superpixel localisation.

21

Content

0

Paper Graph

FireNet: A Specialized Lightweight Fire & Smoke Detection Model for Real-Time IoT Applications

Rishabh Sharma, Arpit Jadon, Mohd. Omama, Akshay Varshney, M. S. Ansari•Mon May 27 2019

A `designed-from-scratch' neural network, named FireNet, is proposed which is worthy on both the counts: it has better performance than existing counterparts, and it is lightweight enough to be deploy-able on embedded platforms like Raspberry Pi.

153 0

Paper Graph

BoWFire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis

D. Y. T. Chino, Letricia P. S. Avalhais, J. F. Rodrigues, A. Traina•Tue Jun 09 2015

This work proposes a novel fire detection method for still images that uses classification based on color features combined with texture classification on super pixel regions and shows the effectiveness of the method of reducing false-positives while its precision remains compatible with the state-of-the-art methods.

182 0

Paper Graph

Fully Convolutional Variational Autoencoder For Feature Extraction Of Fire Detection System

H. Nugroho, Meredita Susanty, A. Irawan, Muhamad Koyimatu, Ariana Yunita•Fri Mar 13 2020

A fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images, which will be used to train the deep learning algorithm to detect fire and smoke.

9 0

Paper Graph

Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset

Erik Blasch, Alireza Shamsoshoara, F. Afghah, Abolfazl Razi, Liming Zheng, Peter Z Ful'e•Sun Dec 27 2020

A fire image dataset collected by drones during a prescribed burning piled detritus in an Arizona pine forest is provided and a deep learning method is designed based on the U-Net up-Sampling and down-sampling approach to extract a fire mask from the video frames.

290 0

Paper Graph

Active Fire Detection in Landsat-8 Imagery: a Large-Scale Dataset and a Deep-Learning Study

R. Minetto, G. Pereira, A. M. Fusioka, B. Nassu•Fri Jan 08 2021

This paper introduces a new large-scale dataset for active fire detection, with over 150,000 image patches extracted from Landsat-8 images captured around the world in August and September 2020, containing wildfires in several locations.

142 0

Paper Graph

Recurrent Trend Predictive Neural Network for Multi-Sensor Fire Detection

Mert Nakıp, C. Güzelı̇ş, Osman Yildiz•Thu Dec 31 2020

The rTPNN model significantly outperforms all of the other models (with 96% accuracy) while it is the only model that achieves high True Positive and True Negative rates at the same time.

25 0

Paper Graph

Assessing the Impact of the Loss Function, Architecture and Image Type for Deep Learning-Based Wildfire Segmentation

J. F. Ciprián-Sánchez, G. Ochoa-Ruiz, L. Rossi, F. Morandini•Thu Jul 29 2021

This is the first work that evaluates the impact of the architecture, loss function, and image type in the performance of DL-based wildfire segmentation models and evaluates if the addition of attention modules on the best performing architecture can further improve the segmentation results.

16 0

Paper Graph

ABANICCO: A New Color Space for Multi-Label Pixel Classification and Color Segmentation

A. Muñoz-Barrutia, Agapito Ledezma, Laura Nicol'as-S'aenz, J. Pascau•Mon Nov 14 2022

A novel method combining geometric analysis of color theory, fuzzy color spaces, and multi-label systems for the automatic classifying pixels according to 12 standard color categories, and a robust, unsupervised, unbiased strategy for color naming based on statistics and color theory is presented.

0 0

Paper Graph

Rapid Deforestation and Burned Area Detection using Deep Multimodal Learning on Satellite Imagery

Marcos V. Conde, Gábor Fodor•Sun Jul 09 2023

This research paper introduces a new curated dataset and a deep learning-based approach to solve deforestation estimation and fire detection in the Amazon forest using convolutional neural networks (CNNs) and comprehensive data processing techniques.

7 0

Paper Graph

Adding a benchmark result helps the community track progress.