Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Light...Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Lightweight Fire Detector (YOLO-LFD), to address the limitations of traditional sensor-based fire detection methods in terms of real-time performance and accuracy. The proposed model is designed to enhance inference speed while maintaining high detection accuracy on resource-constrained devices such as drones and embedded systems. Firstly, we introduce Depthwise Separable Convolutions (DSConv) to reduce the complexity of the feature extraction network. Secondly, we design and implement the Lightweight Faster Implementation of Cross Stage Partial (CSP) Bottleneck with 2 Convolutions (C2f-Light) and the CSP Structure with 3 Compact Inverted Blocks (C3CIB) modules to replace the traditional C3 modules. This optimization enhances deep feature extraction and semantic information processing, thereby significantly increasing inference speed. To enhance the detection capability for small fires, the model employs a Normalized Wasserstein Distance (NWD) loss function, which effectively reduces the missed detection rate and improves the accuracy of detecting small fire sources. Experimental results demonstrate that compared to the baseline YOLOv5s model, the YOLO-LFD model not only increases inference speed by 19.3% but also significantly improves the detection accuracy for small fire targets, with only a 1.6% reduction in overall mean average precision (mAP)@0.5. Through these innovative improvements to YOLOv5s, the YOLO-LFD model achieves a balance between speed and accuracy, making it particularly suitable for real-time detection tasks on mobile and embedded devices.展开更多
Sudden wildfires cause significant global ecological damage.While satellite imagery has advanced early fire detection and mitigation,image-based systems face limitations including high false alarm rates,visual obstruc...Sudden wildfires cause significant global ecological damage.While satellite imagery has advanced early fire detection and mitigation,image-based systems face limitations including high false alarm rates,visual obstructions,and substantial computational demands,especially in complex forest terrains.To address these challenges,this study proposes a novel forest fire detection model utilizing audio classification and machine learning.We developed an audio-based pipeline using real-world environmental sound recordings.Sounds were converted into Mel-spectrograms and classified via a Convolutional Neural Network(CNN),enabling the capture of distinctive fire acoustic signatures(e.g.,crackling,roaring)that are minimally impacted by visual or weather conditions.Internet of Things(IoT)sound sensors were crucial for generating complex environmental parameters to optimize feature extraction.The CNN model achieved high performance in stratified 5-fold cross-validation(92.4%±1.6 accuracy,91.2%±1.8 F1-score)and on test data(94.93%accuracy,93.04%F1-score),with 98.44%precision and 88.32%recall,demonstrating reliability across environmental conditions.These results indicate that the audio-based approach not only improves detection reliability but also markedly reduces computational overhead compared to traditional image-based methods.The findings suggest that acoustic sensing integrated with machine learning offers a powerful,low-cost,and efficient solution for real-time forest fire monitoring in complex,dynamic environments.展开更多
Early detection of Forest and Land Fires(FLF)is essential to prevent the rapid spread of fire as well as minimize environmental damage.However,accurate detection under real-world conditions,such as low light,haze,and ...Early detection of Forest and Land Fires(FLF)is essential to prevent the rapid spread of fire as well as minimize environmental damage.However,accurate detection under real-world conditions,such as low light,haze,and complex backgrounds,remains a challenge for computer vision systems.This study evaluates the impact of three image enhancement techniques—Histogram Equalization(HE),Contrast Limited Adaptive Histogram Equalization(CLAHE),and a hybrid method called DBST-LCM CLAHE—on the performance of the YOLOv11 object detection model in identifying fires and smoke.The D-Fire dataset,consisting of 21,527 annotated images captured under diverse environmental scenarios and illumination levels,was used to train and evaluate the model.Each enhancement method was applied to the dataset before training.Model performance was assessed using multiple metrics,including Precision,Recall,mean Average Precision at 50%IoU(mAP50),F1-score,and visual inspection through bounding box results.Experimental results show that all three enhancement techniques improved detection performance.HE yielded the highest mAP50 score of 0.771,along with a balanced precision of 0.784 and recall of 0.703,demonstrating strong generalization across different conditions.DBST-LCM CLAHE achieved the highest Precision score of 79%,effectively reducing false positives,particularly in scenes with dispersed smoke or complex textures.CLAHE,with slightly lower overall metrics,contributed to improved local feature detection.Each technique showed distinct advantages:HE enhanced global contrast;CLAHE improved local structure visibility;and DBST-LCM CLAHE provided an optimal balance through dynamic block sizing and local contrast preservation.These results underline the importance of selecting preprocessing methods according to detection priorities,such as minimizing false alarms or maximizing completeness.This research does not propose a new model architecture but rather benchmarks a recent lightweight detector,YOLOv11,combined with image enhancement strategies for practical deployment in FLF monitoring.The findings support the integration of preprocessing techniques to improve detection accuracy,offering a foundation for real-time FLF detection systems on edge devices or drones,particularly in regions like Indonesia.展开更多
This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to...This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.展开更多
Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learn...Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learning method, named Attention-Based Prototypical Network, is proposed for forest fire smoke detection. Specifically, feature extraction network, which consists of convolutional block attention module, could extract high-level and discriminative features and further decrease the false alarm rate resulting from suspected smoke areas. Moreover, we design a metalearning module to alleviate the overfitting issue caused by limited smoke images, and the meta-learning network enables achieving effective detection via comparing the distance between the class prototype of support images and the features of query images. A series of experiments on forest fire smoke datasets and miniImageNet dataset testify that the proposed method is superior to state-of-the-art few-shot learning approaches.展开更多
Disasters may occur at any time and place without little to no presage in advance.With the development of surveillance and forecasting systems,it is now possible to forebode the most life-threatening and formidable di...Disasters may occur at any time and place without little to no presage in advance.With the development of surveillance and forecasting systems,it is now possible to forebode the most life-threatening and formidable disasters.However,forestfires are among the ones that are still hard to anticipate beforehand,and the technologies to detect and plot their possible courses are still in development.Unmanned Aerial Vehicle(UAV)image-basedfire detection systems can be a viable solution to this problem.However,these automatic systems use advanced deep learning and image processing algorithms at their core and can be tuned to provide accurate outcomes.Therefore,this article proposed a forestfire detection method based on a Convolutional Neural Network(CNN)architecture using a newfire detection dataset.Notably,our method also uses separable convolution layers(requiring less computational resources)for immediatefire detection and typical convolution layers.Thus,making it suitable for real-time applications.Consequently,after being trained on the dataset,experimental results show that the method can identify forestfires within images with a 97.63%accuracy,98.00%F1 Score,and 80%Kappa.Hence,if deployed in practical circumstances,this identification method can be used as an assistive tool to detectfire outbreaks,allowing the authorities to respond quickly and deploy preventive measures to minimize damage.展开更多
A forest fire is a severe threat to forest resources and human life, In this paper, we propose a forest-fire detection system that has an artificial neural network algorithm implemented in a wireless sensor network （...A forest fire is a severe threat to forest resources and human life, In this paper, we propose a forest-fire detection system that has an artificial neural network algorithm implemented in a wireless sensor network （WSN）. The proposed detection system mitigates the threat of forest fires by provide accurate fire alarm with low maintenance cost. The accuracy is increased by the novel multi- criteria detection, referred to as an alarm decision depends on multiple attributes of a forest fire. The multi-criteria detection is implemented by the artificial neural network algorithm. Meanwhile, we have developed a prototype of the proposed system consisting of the solar batter module, the fire detection module and the user interface module.展开更多
Earth resource and environmental monitoring are essential areas that can be used to investigate the environmental conditions and natural resources supporting sustainable policy development,regulatory measures,and thei...Earth resource and environmental monitoring are essential areas that can be used to investigate the environmental conditions and natural resources supporting sustainable policy development,regulatory measures,and their implementation elevating the environment.Large-scale forest fire is considered a major harmful hazard that affects climate change and life over the globe.Therefore,the early identification of forest fires using automated tools is essential to avoid the spread of fire to a large extent.Therefore,this paper focuses on the design of automated forest fire detection using a fusion-based deep learning(AFFD-FDL)model for environmental monitoring.The AFFDFDL technique involves the design of an entropy-based fusion model for feature extraction.The combination of the handcrafted features using histogram of gradients(HOG)with deep features using SqueezeNet and Inception v3 models.Besides,an optimal extreme learning machine(ELM)based classifier is used to identify the existence of fire or not.In order to properly tune the parameters of the ELM model,the oppositional glowworm swarm optimization(OGSO)algorithm is employed and thereby improves the forest fire detection performance.A wide range of simulation analyses takes place on a benchmark dataset and the results are inspected under several aspects.The experimental results highlighted the betterment of the AFFD-FDL technique over the recent state of art techniques.展开更多
Compared with the traditional techniques of forest fires detection,wireless sensor network(WSN)is a very promising green technology in detecting efficiently the wildfires.However,the power constraint of sensor nodes i...Compared with the traditional techniques of forest fires detection,wireless sensor network(WSN)is a very promising green technology in detecting efficiently the wildfires.However,the power constraint of sensor nodes is one of the main design limitations of WSNs,which leads to limited operation time of nodes and late fire detection.In the past years,wireless power transfer(WPT)technology has been known as a proper solution to prolong the operation time of sensor nodes.In WPT-based mechanisms,wireless mobile chargers(WMC)are utilized to recharge the batteries of sensor nodes wirelessly.Likewise,the energy of WMC is provided using energy-harvesting or energy-scavenging techniques with employing huge,and expensive devices.However,the high price of energy-harvesting devices hinders the use of this technology in large and dense networks,as such networks require multiple WMCs to improve the quality of service to the sensor nodes.To solve this problem,multiple power banks can be employed instead of utilizing WMCs.Furthermore,the long waiting time of critical sensor nodes located outside the charging range of the energy transmitters is another limitation of the previous works.However,the sensor nodes are equipped with radio frequency(RF)technology,which allows them to exchange energy wirelessly.Consequently,critical sensor nodes located outside the charging range of the WMC can easily receive energy from neighboring nodes.Therefore,in this paper,an energy-efficient and cost-effective wireless power transmission(ECWPT)scheme is presented to improve the network lifetime and performance in forest fire detection-based systems.Simulation results exhibit that ECWPT scheme achieves improved network performance in terms of computational time(12.6%);network throughput(60.7%);data delivery ratio(20.9%);and network overhead(35%)as compared to previous related schemes.In conclusion,the proposed scheme significantly improves network energy efficiency for WSN.展开更多
To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight netwo...To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight network and attention mechanism was proposed. Based on the YOLOv4 algorithm, the backbone network CSPDarknet53 was replaced with a lightweight network MobilenetV1 to reduce the model’s size. An attention mechanism was added to the three channels before the output to increase its ability to extract forest fire smoke effectively. The algorithm used the K-means clustering algorithm to cluster the smoke dataset, and obtained candidate frames that were close to the smoke images;the dataset was expanded to 2000 images by the random flip expansion method to avoid overfitting in training. The experimental results show that the improved YOLOv4 algorithm has excellent detection effect. Its mAP can reach 93.45%, precision can get 93.28%, and the model size is only 45.58 MB. Compared with YOLOv4 algorithm, MoAm-YOLOv4 improves the accuracy by 1.3% and reduces the model size by 80% while sacrificing only 0.27% mAP, showing reasonable practicability.展开更多
A forest fire is a natural disaster characterized by rapid spread,difficulty in extinguishing,and widespread destruction,which requires an efficient response.Existing detection methods fail to balance global and local...A forest fire is a natural disaster characterized by rapid spread,difficulty in extinguishing,and widespread destruction,which requires an efficient response.Existing detection methods fail to balance global and local fire features,resulting in the false detection of small or hidden fires.In this paper,we propose a novel detection technique based on an improved YOLO v5 model to enhance the visual representation of forest fires and retain more information about global interactions.We add a plug-and-play global attention mechanism to improve the efficiency of neck and backbone feature extraction of the YOLO v5 model.Then,a re-parameterized convolutional module is designed,and a decoupled detection head is used to accelerate the convergence speed.Finally,a weighted bi-directional feature pyramid network(BiFPN)is introduced to merge feature information for local information processing.In the evaluation,we use the complete intersection over union(CIoU)loss function to optimize the multi-task loss for different kinds of forest fires.Experiments show that the precision,recall,and mean average precision are increased by 4.2%,3.8%,and 4.6%,respectively,compared with the classic YOLO v5 model.In particular,the mAP@0.5:0.95 is 2.2% higher than the other detection methods,while meeting the requirements of real-time detection.展开更多
From May 6 to June 2,1987,a huge forest fire broke out and raged for 28 days in Da Hinggan Ling region in far Northeast China,causing heavy loss of life and property,which claims the biggest forest fire disaster in Ch...From May 6 to June 2,1987,a huge forest fire broke out and raged for 28 days in Da Hinggan Ling region in far Northeast China,causing heavy loss of life and property,which claims the biggest forest fire disaster in Chinese history.The fire drew attention of the whole of China and was also concerned by many other countries.How were the meteorological satellites used in the detection of the forest fire?This paper elaborates the principles and methods of the fire detection using meteorological satellites,so that to sum up the experience and to increase the ability of forest fire detection.展开更多
Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration assessments.In this study,we propose an autoencoder-based mo...Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration assessments.In this study,we propose an autoencoder-based model for forest disturbance detection,which considers disturbances as anomalous events in forest temporal trajectories.The autoencoder network is established and trained to reconstruct intact forest trajectories.Then,the disturbance detection threshold is derived by Tukey’s method based on the reconstruction error of the intact forest trajectory.The assessment result shows that the model using the NBR time series performs better than the NDVIbased model,with an overall accuracy of 90.3%.The omission and commission errors of disturbed forest are 7%and 12%,respectively.Additionally,the trained NBR-based model is implemented in two test areas,with overall accuracies of 87.2%and 86.1%,indicating the robustness and scalability of the model.Moreover,comparing three common methods,the proposed model performs better,especially for intact forest detection accuracy.This study provides a novel and robust approach with acceptable accuracy for forest disturbance detection,enabling forest disturbance to be identified in regions with limited disturbance reference data.展开更多
With the rising frequency and severity of wildfires across the globe,researchers have been actively searching for a reliable solution for early-stage forest fire detection.In recent years,Convolutional Neural Networks...With the rising frequency and severity of wildfires across the globe,researchers have been actively searching for a reliable solution for early-stage forest fire detection.In recent years,Convolutional Neural Networks(CNNs)have demonstrated outstanding performances in computer vision-based object detection tasks,including forest fire detection.Using CNNs to detect forest fires by segmenting both flame and smoke pixels not only can provide early and accurate detection but also additional information such as the size,spread,location,and movement of the fire.However,CNN-based segmentation networks are computationally demanding and can be difficult to incorporate onboard lightweight mobile platforms,such as an Uncrewed Aerial Vehicle(UAV).To address this issue,this paper has proposed a new efficient upsampling technique based on transposed convolution to make segmentation CNNs lighter.This proposed technique,named Reversed Depthwise Separable Transposed Convolution(RDSTC),achieved F1-scores of 0.78 for smoke and 0.74 for flame,outperforming U-Net networks with bilinear upsampling,transposed convolution,and CARAFE upsampling.Additionally,a Multi-signature Fire Detection Network(MsFireD-Net)has been proposed in this paper,having 93%fewer parameters and 94%fewer computations than the RDSTC U-Net.Despite being such a lightweight and efficient network,MsFireD-Net has demonstrated strong results against the other U-Net-based networks.展开更多
Characterisation and mapping of land cover/land use within forest areas over long-multitemporal intervals is a complex task.This complexity is mainly due to the location and extent of such areas and,as a consequence,t...Characterisation and mapping of land cover/land use within forest areas over long-multitemporal intervals is a complex task.This complexity is mainly due to the location and extent of such areas and,as a consequence,to the lack of full continuous cloud-free coverage of those large regions by one single remote sensing instrument.In order to provide improved long-multitemporal forest change detection using Landsat MSS and ETMin part of Mt.Kenya rainforest,and to develop a model for forest change monitoring,wavelet transforms analysis was tested against the ISOCLUS algorithm for the derivation of changes in natural forest cover,as determined using four simple ratio-based Vegetation Indices:Simple Ratio(SR),Normalised Difference Vegetation Index(NDVI),Renormalised Difference Vegetation Index(RDVI)and modified simple ratio(MSR).Based on statistical and empirical accuracy assessments,RDVI presented the optimal index for the case study.The overall accuracy statistic of the wavelet derived change/no-change was used to rank the performances of the indices as:RDVI(91.68%),MSR(82.55%),NDVI(79.73%)and SR(65.34%).The integrated discrete wavelet transformISOCLUS(DWTISOCLUS)result was 42.65%higher than the independent ISOCLUS approach in mapping the change/no-change information.The methodology suggested in this study presents a cost-effective and practical method to detect land-cover changes in support of decision-making for updating forest databases,and for long-term monitoring of vegetation changes from multisensor imagery.The current research contributes to Digital Earth with regards to geo-data acquisition,data mining and representation of one forest systems.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62101275 and 62101274).
文摘Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Lightweight Fire Detector (YOLO-LFD), to address the limitations of traditional sensor-based fire detection methods in terms of real-time performance and accuracy. The proposed model is designed to enhance inference speed while maintaining high detection accuracy on resource-constrained devices such as drones and embedded systems. Firstly, we introduce Depthwise Separable Convolutions (DSConv) to reduce the complexity of the feature extraction network. Secondly, we design and implement the Lightweight Faster Implementation of Cross Stage Partial (CSP) Bottleneck with 2 Convolutions (C2f-Light) and the CSP Structure with 3 Compact Inverted Blocks (C3CIB) modules to replace the traditional C3 modules. This optimization enhances deep feature extraction and semantic information processing, thereby significantly increasing inference speed. To enhance the detection capability for small fires, the model employs a Normalized Wasserstein Distance (NWD) loss function, which effectively reduces the missed detection rate and improves the accuracy of detecting small fire sources. Experimental results demonstrate that compared to the baseline YOLOv5s model, the YOLO-LFD model not only increases inference speed by 19.3% but also significantly improves the detection accuracy for small fire targets, with only a 1.6% reduction in overall mean average precision (mAP)@0.5. Through these innovative improvements to YOLOv5s, the YOLO-LFD model achieves a balance between speed and accuracy, making it particularly suitable for real-time detection tasks on mobile and embedded devices.
基金funded by the Directorate of Research and Community Service,Directorate General of Research and Development,Ministry of Higher Education,Science and Technologyin accordance with the Implementation Contract for the Operational Assistance Program for State Universities,Research Program Number:109/C3/DT.05.00/PL/2025.
文摘Sudden wildfires cause significant global ecological damage.While satellite imagery has advanced early fire detection and mitigation,image-based systems face limitations including high false alarm rates,visual obstructions,and substantial computational demands,especially in complex forest terrains.To address these challenges,this study proposes a novel forest fire detection model utilizing audio classification and machine learning.We developed an audio-based pipeline using real-world environmental sound recordings.Sounds were converted into Mel-spectrograms and classified via a Convolutional Neural Network(CNN),enabling the capture of distinctive fire acoustic signatures(e.g.,crackling,roaring)that are minimally impacted by visual or weather conditions.Internet of Things(IoT)sound sensors were crucial for generating complex environmental parameters to optimize feature extraction.The CNN model achieved high performance in stratified 5-fold cross-validation(92.4%±1.6 accuracy,91.2%±1.8 F1-score)and on test data(94.93%accuracy,93.04%F1-score),with 98.44%precision and 88.32%recall,demonstrating reliability across environmental conditions.These results indicate that the audio-based approach not only improves detection reliability but also markedly reduces computational overhead compared to traditional image-based methods.The findings suggest that acoustic sensing integrated with machine learning offers a powerful,low-cost,and efficient solution for real-time forest fire monitoring in complex,dynamic environments.
基金funded by the Directorate of Research,Technology,and Community Service,Ministry of Higher Education,Science,and Technology of the Republic of Indonesia the Regular Fundamental Research scheme,with grant numbers 001/LL6/PL/AL.04/2025,011/SPK-PFR/RIK/05/2025.
文摘Early detection of Forest and Land Fires(FLF)is essential to prevent the rapid spread of fire as well as minimize environmental damage.However,accurate detection under real-world conditions,such as low light,haze,and complex backgrounds,remains a challenge for computer vision systems.This study evaluates the impact of three image enhancement techniques—Histogram Equalization(HE),Contrast Limited Adaptive Histogram Equalization(CLAHE),and a hybrid method called DBST-LCM CLAHE—on the performance of the YOLOv11 object detection model in identifying fires and smoke.The D-Fire dataset,consisting of 21,527 annotated images captured under diverse environmental scenarios and illumination levels,was used to train and evaluate the model.Each enhancement method was applied to the dataset before training.Model performance was assessed using multiple metrics,including Precision,Recall,mean Average Precision at 50%IoU(mAP50),F1-score,and visual inspection through bounding box results.Experimental results show that all three enhancement techniques improved detection performance.HE yielded the highest mAP50 score of 0.771,along with a balanced precision of 0.784 and recall of 0.703,demonstrating strong generalization across different conditions.DBST-LCM CLAHE achieved the highest Precision score of 79%,effectively reducing false positives,particularly in scenes with dispersed smoke or complex textures.CLAHE,with slightly lower overall metrics,contributed to improved local feature detection.Each technique showed distinct advantages:HE enhanced global contrast;CLAHE improved local structure visibility;and DBST-LCM CLAHE provided an optimal balance through dynamic block sizing and local contrast preservation.These results underline the importance of selecting preprocessing methods according to detection priorities,such as minimizing false alarms or maximizing completeness.This research does not propose a new model architecture but rather benchmarks a recent lightweight detector,YOLOv11,combined with image enhancement strategies for practical deployment in FLF monitoring.The findings support the integration of preprocessing techniques to improve detection accuracy,offering a foundation for real-time FLF detection systems on edge devices or drones,particularly in regions like Indonesia.
文摘This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.
基金The work was supported by the National Key R&D Program of China(Grant No.2020YFC1511601)Fundamental Research Funds for the Central Universities(Grant No.2019SHFWLC01).
文摘Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learning method, named Attention-Based Prototypical Network, is proposed for forest fire smoke detection. Specifically, feature extraction network, which consists of convolutional block attention module, could extract high-level and discriminative features and further decrease the false alarm rate resulting from suspected smoke areas. Moreover, we design a metalearning module to alleviate the overfitting issue caused by limited smoke images, and the meta-learning network enables achieving effective detection via comparing the distance between the class prototype of support images and the features of query images. A series of experiments on forest fire smoke datasets and miniImageNet dataset testify that the proposed method is superior to state-of-the-art few-shot learning approaches.
文摘Disasters may occur at any time and place without little to no presage in advance.With the development of surveillance and forecasting systems,it is now possible to forebode the most life-threatening and formidable disasters.However,forestfires are among the ones that are still hard to anticipate beforehand,and the technologies to detect and plot their possible courses are still in development.Unmanned Aerial Vehicle(UAV)image-basedfire detection systems can be a viable solution to this problem.However,these automatic systems use advanced deep learning and image processing algorithms at their core and can be tuned to provide accurate outcomes.Therefore,this article proposed a forestfire detection method based on a Convolutional Neural Network(CNN)architecture using a newfire detection dataset.Notably,our method also uses separable convolution layers(requiring less computational resources)for immediatefire detection and typical convolution layers.Thus,making it suitable for real-time applications.Consequently,after being trained on the dataset,experimental results show that the method can identify forestfires within images with a 97.63%accuracy,98.00%F1 Score,and 80%Kappa.Hence,if deployed in practical circumstances,this identification method can be used as an assistive tool to detectfire outbreaks,allowing the authorities to respond quickly and deploy preventive measures to minimize damage.
文摘A forest fire is a severe threat to forest resources and human life, In this paper, we propose a forest-fire detection system that has an artificial neural network algorithm implemented in a wireless sensor network （WSN）. The proposed detection system mitigates the threat of forest fires by provide accurate fire alarm with low maintenance cost. The accuracy is increased by the novel multi- criteria detection, referred to as an alarm decision depends on multiple attributes of a forest fire. The multi-criteria detection is implemented by the artificial neural network algorithm. Meanwhile, we have developed a prototype of the proposed system consisting of the solar batter module, the fire detection module and the user interface module.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under Grant Number(RGP.1/172/42)Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2023R191)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.This study is supported via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2023/R/1444).
文摘Earth resource and environmental monitoring are essential areas that can be used to investigate the environmental conditions and natural resources supporting sustainable policy development,regulatory measures,and their implementation elevating the environment.Large-scale forest fire is considered a major harmful hazard that affects climate change and life over the globe.Therefore,the early identification of forest fires using automated tools is essential to avoid the spread of fire to a large extent.Therefore,this paper focuses on the design of automated forest fire detection using a fusion-based deep learning(AFFD-FDL)model for environmental monitoring.The AFFDFDL technique involves the design of an entropy-based fusion model for feature extraction.The combination of the handcrafted features using histogram of gradients(HOG)with deep features using SqueezeNet and Inception v3 models.Besides,an optimal extreme learning machine(ELM)based classifier is used to identify the existence of fire or not.In order to properly tune the parameters of the ELM model,the oppositional glowworm swarm optimization(OGSO)algorithm is employed and thereby improves the forest fire detection performance.A wide range of simulation analyses takes place on a benchmark dataset and the results are inspected under several aspects.The experimental results highlighted the betterment of the AFFD-FDL technique over the recent state of art techniques.
文摘Compared with the traditional techniques of forest fires detection,wireless sensor network(WSN)is a very promising green technology in detecting efficiently the wildfires.However,the power constraint of sensor nodes is one of the main design limitations of WSNs,which leads to limited operation time of nodes and late fire detection.In the past years,wireless power transfer(WPT)technology has been known as a proper solution to prolong the operation time of sensor nodes.In WPT-based mechanisms,wireless mobile chargers(WMC)are utilized to recharge the batteries of sensor nodes wirelessly.Likewise,the energy of WMC is provided using energy-harvesting or energy-scavenging techniques with employing huge,and expensive devices.However,the high price of energy-harvesting devices hinders the use of this technology in large and dense networks,as such networks require multiple WMCs to improve the quality of service to the sensor nodes.To solve this problem,multiple power banks can be employed instead of utilizing WMCs.Furthermore,the long waiting time of critical sensor nodes located outside the charging range of the energy transmitters is another limitation of the previous works.However,the sensor nodes are equipped with radio frequency(RF)technology,which allows them to exchange energy wirelessly.Consequently,critical sensor nodes located outside the charging range of the WMC can easily receive energy from neighboring nodes.Therefore,in this paper,an energy-efficient and cost-effective wireless power transmission(ECWPT)scheme is presented to improve the network lifetime and performance in forest fire detection-based systems.Simulation results exhibit that ECWPT scheme achieves improved network performance in terms of computational time(12.6%);network throughput(60.7%);data delivery ratio(20.9%);and network overhead(35%)as compared to previous related schemes.In conclusion,the proposed scheme significantly improves network energy efficiency for WSN.
文摘To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight network and attention mechanism was proposed. Based on the YOLOv4 algorithm, the backbone network CSPDarknet53 was replaced with a lightweight network MobilenetV1 to reduce the model’s size. An attention mechanism was added to the three channels before the output to increase its ability to extract forest fire smoke effectively. The algorithm used the K-means clustering algorithm to cluster the smoke dataset, and obtained candidate frames that were close to the smoke images;the dataset was expanded to 2000 images by the random flip expansion method to avoid overfitting in training. The experimental results show that the improved YOLOv4 algorithm has excellent detection effect. Its mAP can reach 93.45%, precision can get 93.28%, and the model size is only 45.58 MB. Compared with YOLOv4 algorithm, MoAm-YOLOv4 improves the accuracy by 1.3% and reduces the model size by 80% while sacrificing only 0.27% mAP, showing reasonable practicability.
基金supported by the Graduate Research and Innovation Projects of Jiangsu Province(No.SJCX23_0320).
文摘A forest fire is a natural disaster characterized by rapid spread,difficulty in extinguishing,and widespread destruction,which requires an efficient response.Existing detection methods fail to balance global and local fire features,resulting in the false detection of small or hidden fires.In this paper,we propose a novel detection technique based on an improved YOLO v5 model to enhance the visual representation of forest fires and retain more information about global interactions.We add a plug-and-play global attention mechanism to improve the efficiency of neck and backbone feature extraction of the YOLO v5 model.Then,a re-parameterized convolutional module is designed,and a decoupled detection head is used to accelerate the convergence speed.Finally,a weighted bi-directional feature pyramid network(BiFPN)is introduced to merge feature information for local information processing.In the evaluation,we use the complete intersection over union(CIoU)loss function to optimize the multi-task loss for different kinds of forest fires.Experiments show that the precision,recall,and mean average precision are increased by 4.2%,3.8%,and 4.6%,respectively,compared with the classic YOLO v5 model.In particular,the mAP@0.5:0.95 is 2.2% higher than the other detection methods,while meeting the requirements of real-time detection.
文摘From May 6 to June 2,1987,a huge forest fire broke out and raged for 28 days in Da Hinggan Ling region in far Northeast China,causing heavy loss of life and property,which claims the biggest forest fire disaster in Chinese history.The fire drew attention of the whole of China and was also concerned by many other countries.How were the meteorological satellites used in the detection of the forest fire?This paper elaborates the principles and methods of the fire detection using meteorological satellites,so that to sum up the experience and to increase the ability of forest fire detection.
基金funded by the National Natural Science Foundation of China under Grant 41871223the China Scholarship Council(CSC)(No.201806400048)for doctoral scholarship support.
文摘Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration assessments.In this study,we propose an autoencoder-based model for forest disturbance detection,which considers disturbances as anomalous events in forest temporal trajectories.The autoencoder network is established and trained to reconstruct intact forest trajectories.Then,the disturbance detection threshold is derived by Tukey’s method based on the reconstruction error of the intact forest trajectory.The assessment result shows that the model using the NBR time series performs better than the NDVIbased model,with an overall accuracy of 90.3%.The omission and commission errors of disturbed forest are 7%and 12%,respectively.Additionally,the trained NBR-based model is implemented in two test areas,with overall accuracies of 87.2%and 86.1%,indicating the robustness and scalability of the model.Moreover,comparing three common methods,the proposed model performs better,especially for intact forest detection accuracy.This study provides a novel and robust approach with acceptable accuracy for forest disturbance detection,enabling forest disturbance to be identified in regions with limited disturbance reference data.
文摘With the rising frequency and severity of wildfires across the globe,researchers have been actively searching for a reliable solution for early-stage forest fire detection.In recent years,Convolutional Neural Networks(CNNs)have demonstrated outstanding performances in computer vision-based object detection tasks,including forest fire detection.Using CNNs to detect forest fires by segmenting both flame and smoke pixels not only can provide early and accurate detection but also additional information such as the size,spread,location,and movement of the fire.However,CNN-based segmentation networks are computationally demanding and can be difficult to incorporate onboard lightweight mobile platforms,such as an Uncrewed Aerial Vehicle(UAV).To address this issue,this paper has proposed a new efficient upsampling technique based on transposed convolution to make segmentation CNNs lighter.This proposed technique,named Reversed Depthwise Separable Transposed Convolution(RDSTC),achieved F1-scores of 0.78 for smoke and 0.74 for flame,outperforming U-Net networks with bilinear upsampling,transposed convolution,and CARAFE upsampling.Additionally,a Multi-signature Fire Detection Network(MsFireD-Net)has been proposed in this paper,having 93%fewer parameters and 94%fewer computations than the RDSTC U-Net.Despite being such a lightweight and efficient network,MsFireD-Net has demonstrated strong results against the other U-Net-based networks.
文摘Characterisation and mapping of land cover/land use within forest areas over long-multitemporal intervals is a complex task.This complexity is mainly due to the location and extent of such areas and,as a consequence,to the lack of full continuous cloud-free coverage of those large regions by one single remote sensing instrument.In order to provide improved long-multitemporal forest change detection using Landsat MSS and ETMin part of Mt.Kenya rainforest,and to develop a model for forest change monitoring,wavelet transforms analysis was tested against the ISOCLUS algorithm for the derivation of changes in natural forest cover,as determined using four simple ratio-based Vegetation Indices:Simple Ratio(SR),Normalised Difference Vegetation Index(NDVI),Renormalised Difference Vegetation Index(RDVI)and modified simple ratio(MSR).Based on statistical and empirical accuracy assessments,RDVI presented the optimal index for the case study.The overall accuracy statistic of the wavelet derived change/no-change was used to rank the performances of the indices as:RDVI(91.68%),MSR(82.55%),NDVI(79.73%)and SR(65.34%).The integrated discrete wavelet transformISOCLUS(DWTISOCLUS)result was 42.65%higher than the independent ISOCLUS approach in mapping the change/no-change information.The methodology suggested in this study presents a cost-effective and practical method to detect land-cover changes in support of decision-making for updating forest databases,and for long-term monitoring of vegetation changes from multisensor imagery.The current research contributes to Digital Earth with regards to geo-data acquisition,data mining and representation of one forest systems.
