A deep learning approach for early wildfire detection from hyperspectral satellite images

Toan, Nguyen Thanh; Cong, Phan Thanh; Hùng, Nguyễn Quốc; Jo, Jun

doi:10.1109/ritapp.2019.8932740

Cited by 38 publications

(23 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the above-mentioned systems have been using traditional detection methods since their first implementation, but the use of Machine Learning techniques has started to capture more interest in recent years, with Deep Learning techniques gaining traction in the last two years, as one of the main tools used in the automatic recognition of forest fires [2,11]. The most common models that are implemented for smoke and fire detection and classification in images are based on either CNN (Convolutional Neural Networks) [15,21], Faster R-CNN [21], Fully Convolutional Neural networks [22] or Spatiospectral Deep Neural Networks [23]. Some of the most recent studies in fire detection systems have also been changing their traditional Deep learning approaches to object-based detection systems [24,25], which has also been rising in popularity in the Industry.…”

Section: State Of the Artmentioning

confidence: 99%

A Deep Learning Based Object Identification System for Forest Fire Detection

Guede-Fernández

Martins

Almeida

et al. 2021

Fire

View full text Add to dashboard Cite

Forest fires are still a large concern in several countries due to the social, environmental and economic damages caused. This paper aims to show the design and validation of a proposed system for the classification of smoke columns with object detection and a deep learning-based approach. This approach is able to detect smoke columns visible below or above the horizon. During the dataset labelling, the smoke object was divided into three different classes, depending on its distance to the horizon, a cloud object was also added, along with images without annotations. A comparison between the use of RetinaNet and Faster R-CNN was also performed. Using an independent test set, an F1-score around 80%, a G-mean around 80% and a detection rate around 90% were achieved by the two best models: both were trained with the dataset labelled with three different smoke classes and with augmentation; Faster R-CNNN was the model architecture, re-trained during the same iterations but following different learning rate schedules. Finally, these models were tested in 24 smoke sequences of the public HPWREN dataset, with 6.3 min as the average time elapsed from the start of the fire compared to the first detection of a smoke column.

show abstract

Section: State Of the Artmentioning

confidence: 99%

A Deep Learning Based Object Identification System for Forest Fire Detection

Guede-Fernández

Martins

Almeida

et al. 2021

Fire

View full text Add to dashboard Cite

show abstract

“…Finally, the work proposed by Toan et al [39] is, to the best of our knowledge, the only DL model that leverages multispectral images to perform wildfire segmentation. The authors propose a DCNN that incorporates both spectral and spatial information that they obtain through the GOES-16 satellite.…”

Section: Deep Learning-based Wildfire Segmentationmentioning

confidence: 99%

“…The authors propose a DCNN that incorporates both spectral and spatial information that they obtain through the GOES-16 satellite. As spectral images have an additional dimension of spectral bands with partial dependencies between them [39], Toan et al propose a 3D version of a convolutional layer, in which each neuron in the following layer is connected only to a cube of neurons in the previous layer [39]. The model proposed by Toan et al employs three of the mentioned 3D convolutional layers.…”

Section: Deep Learning-based Wildfire Segmentationmentioning

confidence: 99%

“…In the context of wildfire detection, several approaches have been proposed for both fire image classification (as mentioned previously, to classify a full image as either fire or non-fire) [8][9][10]35] and fire semantic segmentation. [5,[36][37][38][39]. DL-based wildfire semantic segmentation methods seek to classify each pixel in an image as fire or non-fire.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2021

View full text Add to dashboard Cite

Wildfires stand as one of the most relevant natural disasters worldwide, particularly more so due to the effect of climate change and its impact on various societal and environmental levels. In this regard, a significant amount of research has been done in order to address this issue, deploying a wide variety of technologies and following a multi-disciplinary approach. Notably, computer vision has played a fundamental role in this regard. It can be used to extract and combine information from several imaging modalities in regard to fire detection, characterization and wildfire spread forecasting. In recent years, there has been work pertaining to Deep Learning (DL)-based fire segmentation, showing very promising results. However, it is currently unclear whether the architecture of a model, its loss function, or the image type employed (visible, infrared, or fused) has the most impact on the fire segmentation results. In the present work, we evaluate different combinations of state-of-the-art (SOTA) DL architectures, loss functions, and types of images to identify the parameters most relevant to improve the segmentation results. We benchmark them to identify the top-performing ones and compare them to traditional fire segmentation techniques. Finally, we evaluate if the addition of attention modules on the best performing architecture can further improve the segmentation results. To the best of our knowledge, 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.

show abstract

“…By leveraging low-level representations of the input data, deep learning models are capable of making robust classification in active fire detection. In [22], a deep learning algorithm based on convolutional neural network is adopted using GOES-16 images as the input to detect wildfires. The proposed method utilize spatial and spectral information to classify the center pixel of image patches.…”

Section: Introductionmentioning

confidence: 99%

Early Detection of Wildfires with GOES-R Time Series and Deep GRU-Network

Zhao¹,

Ban²

2022

Preprint

View full text Add to dashboard Cite

Early detection of wildfires has been limited using the sun-synchronous orbit satellites due to their low temporal resolution and wildfires’ fast spread in the early stage. NOAA’s geostationary weather satellites GOES-R can acquire images every 15 minutes at 2km spatial resolution, and have been used for early fire detection. However, advanced processing algorithms are needed to provide timely and reliable detection of wildfires. In this research, a deep learning framework, based on Gated Recurrent Units (GRU), is proposed to detect wildfires at early stage using GOES-R dense time series data. GRU model maintains good performance on temporal modelling while keep a simple architecture, makes it suitable to efficiently process time-series data. 36 different wildfires in North and South America under the coverage of GOES-R satellites are selected to assess the effectiveness of the GRU method. The detection times based on GOES-R are compared with VIIRS active fire products at 375m resolution in NASA’s Fire Information for Resource Management System (FIRMS). The results show that GRU-based GOES-R detections of the wildfires are earlier than that of the VIIRS active fire products in most of the study areas. Also, results from proposed method offer more precise location on the active fire at early stage than GOES-R Active Fire Product in mid-latitude and low-latitude regions.

show abstract

A deep learning approach for early wildfire detection from hyperspectral satellite images

Cited by 38 publications

References 16 publications

A Deep Learning Based Object Identification System for Forest Fire Detection

A Deep Learning Based Object Identification System for Forest Fire Detection

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

Early Detection of Wildfires with GOES-R Time Series and Deep GRU-Network

Contact Info

Product

Resources

About