Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation

Abstract

Wildfires are a worldwide natural disaster causing important economic damages and loss of lives. Experts predict that wildfires will increase in the coming years mainly due to climate change. Early detection and prediction of fire spread can help reduce affected areas and improve firefighting. Numerous systems were developed to detect fire. Recently, Unmanned Aerial Vehicles were employed to tackle this problem due to their high flexibility, their low-cost, and their ability to cover wide areas during the day or night. However, they are still limited by challenging problems such as small fire size, background complexity, and image degradation. To deal with the aforementioned limitations, we adapted and optimized Deep Learning methods to detect wildfire at an early stage. A novel deep ensemble learning method, which combines EfficientNet-B5 and DenseNet-201 models, is proposed to identify and classify wildfire using aerial images. In addition, two vision transformers (TransUNet and TransFire) and a deep convolutional model (EfficientSeg) were employed to segment wildfire regions and determine the precise fire regions. The obtained results are promising and show the efficiency of using Deep Learning and vision transformers for wildfire classification and segmentation. The proposed model for wildfire classification obtained an accuracy of 85.12% and outperformed many state-of-the-art works. It proved its ability in classifying wildfire even small fire areas. The best semantic segmentation models achieved an F1-score of 99.9% for TransUNet architecture and 99.82% for TransFire architecture superior to recent published models. More specifically, we demonstrated the ability of these models to extract the finer details of wildfire using aerial images. They can further overcome current model limitations, such as background complexity and small wildfire areas.

Comparative Research on Forest Fire Image Segmentation Algorithms Based on Fully Convolutional Neural Networks

“…In general, these methods not only require a large amount of resource input, but also are severely limited by the weather and environmental conditions, making it difficult to ensure the quality of forest fire monitoring. With the advancement in image-processing technology, in recent years, authorities have increased the use of unmanned aerial vehicles (UAVs) and surveillance for aerial monitoring of forest areas [9,10], collecting and real-timeprocessing fire images for earlier warning and intervention. In order to identify forest fire areas in the images, flame detection techniques are introduced in some studies.…”

A Comprehensive Review on Artificial Intelligence/Machine Learning Algorithms for Empowering the Future IoT Toward 6G Era

“…Research topic Research analysis/findings Deep Learning [148] Network access and routing algorithm Survey on DL, supervised, reinforcement and imitation learning [149], [150] Indoor localization Localization error analysis [151] CSI estimation technique CSI overhead, channel measurement and sum rate analysis [152] DoA estimation Estimation accuracy analysis with the proposed, RVNN, SVR and MUSIC approaches [154] Power allocation strategy Analysis of secrecy rate, computation time and interference leakage [155] QoE forecasting mechanism Performance analysis of the proposed scheme against SVR, MLP, LSTM-based schemes [156] Anti-jamming scheme Throughput analysis Transformer algorithm [157] Medical image classification Classification accuracy analysis [158] Traffic sign recognition Classification accuracy analysis [159] Wildfire recognition and region detection Classification and detection accuracy analysis [160] Modulation recognition Classification and detection accuracy analysis [161] Intrusion detection Detection accuracy analysis Graph neural network [162] Topology control Network lifetime enhancement [163] IoT device tracking Tracking optimization in terms of execution time and distance covered by the tracking devices [164] Sentiment classification Interpretation accuracy of the aspect of text(s) [165] Vehicular traffic data prediction Prediction accuracy of the missing data from the available dataset recognition mechanism is designed in [158] with the help of DNN consisting of CNN and transformer-based algorithm.…”

“…The designed system claims to have high accuracy in terms of recognition. In [159], a novel deep ensemble learning-based methodology is combined with two-transformer based algorithm and a DNN model for classification of wildfire regions and precise region detection. In case of cellular network system, modulation recognition and network intrusion detection is also being conducted with transformer-based algorithms to analyze their classification and detection accuracy [160], [161] .…”

A Wildfire Smoke Detection System Using Unmanned Aerial Vehicle Images Based on the Optimized YOLOv5

“…Fire smoke shares similar and overlapping spectral signatures with a wide variety of other objects, such as fog, haze, snow, clouds, dust, and plants. Smoke always appears far from the camera, and the area of smoke typically accounts for only a small portion of the video frame [ 13 , 14 , 15 , 16 , 17 ].…”