Advanced wildfire detection using generative adversarial network-based augmented datasets and weakly supervised object localization

Park, Minsoo; Tran, Dai Quoc; Bak, JinYeong; Park, Seunghee

doi:10.1016/j.jag.2022.103052

Cited by 17 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have also explored the generation of synthetic training data to overcome the limitation of scarce datasets. Zhang et al [35] and Park et al [36] utilized novel data augmentation techniques to enrich training sets for more effective model training. While these methods enhance model robustness, the synthetic data might not perfectly replicate the complex dynamics of real forest fires, potentially leading to inaccuracies in practical applications.…”

Section: Related Workmentioning

confidence: 99%

“…The existing literature on wildfire detection is often lacking in computational efficiency [29,39,40,42,46,[48][49][50], with limited focus on model interpretability [32,33,36,37] and comprehensive comparative analysis [39,40,46,48,51]. Our FireXplainNet addresses these shortcomings by offering a lightweight and efficient design, integrating interpretability through LIME [30], and conducting extensive comparative evaluations, enhancing both practicality and transparency in diverse fire scenarios.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FireXplainNet: Optimizing Convolution Block Architecture for Enhanced Wildfire Detection and Interpretability

Khan,

Park

2024

Electronics

View full text Add to dashboard Cite

The early detection of wildfires is a crucial challenge in environmental monitoring, pivotal for effective disaster management and ecological conservation. Traditional detection methods often fail to detect fires accurately and in a timely manner, resulting in significant adverse consequences. This paper presents FireXplainNet, a Convolutional Neural Network (CNN) base model, designed specifically to address these limitations through enhanced efficiency and precision in wildfire detection. We optimized data input via specialized preprocessing techniques, significantly improving detection accuracy on both the Wildfire Image and FLAME datasets. A distinctive feature of our approach is the integration of Local Interpretable Model-agnostic Explanations (LIME), which facilitates a deeper understanding of and trust in the model’s predictive capabilities. Additionally, we have delved into optimizing pretrained models through transfer learning, enriching our analysis and offering insights into the comparative effectiveness of FireXplainNet. The model achieved an accuracy of 87.32% on the FLAME dataset and 98.70% on the Wildfire Image dataset, with inference times of 0.221 and 0.168 milliseconds, respectively. These performance metrics are critical for the application of real-time fire detection systems, underscoring the potential of FireXplainNet in environmental monitoring and disaster management strategies.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

FireXplainNet: Optimizing Convolution Block Architecture for Enhanced Wildfire Detection and Interpretability

Khan,

Park

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Park et al [ 116 ] addressed the challenge of the lack of wildfire occurred image datasets by employing generative adversarial networks (GAN) and weakly supervised object localization (WSOL). Their study aimed to create synthetic wildfire images with various shapes by inserting damage into free-wildfire images.…”

Section: The Role Of Traditional Machine Learning and Deep Learning I...mentioning

confidence: 99%

Advancements in Forest Fire Prevention: A Comprehensive Survey

Carta,

Zidda,

Putzu

et al. 2023

Sensors

View full text Add to dashboard Cite

Nowadays, the challenges related to technological and environmental development are becoming increasingly complex. Among the environmentally significant issues, wildfires pose a serious threat to the global ecosystem. The damages inflicted upon forests are manifold, leading not only to the destruction of terrestrial ecosystems but also to climate changes. Consequently, reducing their impact on both people and nature requires the adoption of effective approaches for prevention, early warning, and well-coordinated interventions. This document presents an analysis of the evolution of various technologies used in the detection, monitoring, and prevention of forest fires from past years to the present. It highlights the strengths, limitations, and future developments in this field. Forest fires have emerged as a critical environmental concern due to their devastating effects on ecosystems and the potential repercussions on the climate. Understanding the evolution of technology in addressing this issue is essential to formulate more effective strategies for mitigating and preventing wildfires.

show abstract

“…The introduction of the attention mechanism has proven transformative in object detection tasks. By dynamically emphasizing salient image features while downplaying less informative ones, models exhibit enhanced capacity for accurate object detection and classification, all while preserving the efficiency of the detection process (Park, et al, 2022;Guo, et al, 2022). Traditional attention methods, including squeeze-and-excitation (SE) (Hu, et al, 2018) and convolutional block attention mechanism (CBAM) (Woo, et al, 2018), utilize convolutional neural networks to recalibrate feature maps, enhancing model accuracy and robustness by prioritizing meaningful information over less relevant components.…”

Section: Attention Mechanismmentioning

confidence: 99%

Deep Learning-Based Pose Estimation for Identifying Potential Fall Hazards of Construction Worker

Park,

Lee,

Choi

et al. 2023

CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality

Self Cite

View full text Add to dashboard Cite

Fall from height (FFH) is one of the major causes of injury and fatalities in construction industry. Deep learning-based computer vision for safety monitoring has gained attention due to its relatively lower initial cost compared to traditional sensing technologies. However, a single detection model that has been used in many related studies cannot consider various contexts at the construction site. In this paper, we propose a deep learning-based pose estimation approach for identifying potential fall hazards of construction workers. This approach can relatively increase the accuracy of estimating the distance between the worker and the fall hazard area compared to the existing methods from the experimental results. Our proposed approach can improve the robustness of worker location estimation compared to existing methods in complex construction site environments with obstacles that can obstruct the worker's position. Also, it is possible to provide information on whether a worker is aware of a potential fall risk area. Our approach can contribute to preventing FFH by providing access information to fall risk areas such as construction site openings and inducing workers to recognize the risk area even in Inattentional blindness (IB) situations

show abstract

Advanced wildfire detection using generative adversarial network-based augmented datasets and weakly supervised object localization

Cited by 17 publications

References 47 publications

FireXplainNet: Optimizing Convolution Block Architecture for Enhanced Wildfire Detection and Interpretability

FireXplainNet: Optimizing Convolution Block Architecture for Enhanced Wildfire Detection and Interpretability

Advancements in Forest Fire Prevention: A Comprehensive Survey

Deep Learning-Based Pose Estimation for Identifying Potential Fall Hazards of Construction Worker

Contact Info

Product

Resources

About