“…Fortunately, the development of UAVs has attained a more mature stage, while video, image, and image processing technologies continue to advance [19,20]. UAV-based image analysis for forest fire smoke detection systems can effectively conduct inspections of mountains and forests [21][22][23]. The UAV's camera captures images or videos of the mountains and forests, eliminating the cumbersome process of camera deployment and reducing the allocation of manpower, material resources, and financial resources.…”
Forest fires pose severe challenges to forest management because of their unpredictability, extensive harm, broad impact, and rescue complexities. Early smoke detection is pivotal for prompt intervention and damage mitigation. Combining deep learning techniques with UAV imagery holds potential in advancing forest fire smoke recognition. However, issues arise when using UAV-derived images, especially in detecting miniature smoke patches, complicating effective feature discernment. Common deep learning approaches for forest fire detection also grapple with limitations due to sparse datasets. To counter these challenges, we introduce a refined UAV-centric forest fire smoke detection approach utilizing YOLOv5. We first enhance anchor box clustering through K-means++ to boost the classification precision and then augment the YOLOv5 architecture by integrating a novel partial convolution (PConv) to trim down model parameters and elevate processing speed. A unique detection head is also incorporated to the model to better detect diminutive smoke traces. A coordinate attention module is embedded within YOLOv5, enabling precise smoke target location and fine-grained feature extraction amidst complex settings. Given the scarcity of forest fire smoke datasets, we employ transfer learning for model training. The experimental results demonstrate that our proposed method achieves 96% AP50 and 57.3% AP50:95 on a customized dataset, outperforming other state-of-the-art one-stage object detectors while maintaining real-time performance.
“…Fortunately, the development of UAVs has attained a more mature stage, while video, image, and image processing technologies continue to advance [19,20]. UAV-based image analysis for forest fire smoke detection systems can effectively conduct inspections of mountains and forests [21][22][23]. The UAV's camera captures images or videos of the mountains and forests, eliminating the cumbersome process of camera deployment and reducing the allocation of manpower, material resources, and financial resources.…”
Forest fires pose severe challenges to forest management because of their unpredictability, extensive harm, broad impact, and rescue complexities. Early smoke detection is pivotal for prompt intervention and damage mitigation. Combining deep learning techniques with UAV imagery holds potential in advancing forest fire smoke recognition. However, issues arise when using UAV-derived images, especially in detecting miniature smoke patches, complicating effective feature discernment. Common deep learning approaches for forest fire detection also grapple with limitations due to sparse datasets. To counter these challenges, we introduce a refined UAV-centric forest fire smoke detection approach utilizing YOLOv5. We first enhance anchor box clustering through K-means++ to boost the classification precision and then augment the YOLOv5 architecture by integrating a novel partial convolution (PConv) to trim down model parameters and elevate processing speed. A unique detection head is also incorporated to the model to better detect diminutive smoke traces. A coordinate attention module is embedded within YOLOv5, enabling precise smoke target location and fine-grained feature extraction amidst complex settings. Given the scarcity of forest fire smoke datasets, we employ transfer learning for model training. The experimental results demonstrate that our proposed method achieves 96% AP50 and 57.3% AP50:95 on a customized dataset, outperforming other state-of-the-art one-stage object detectors while maintaining real-time performance.
“…Property damage caused by fire occurrences is approximately 805.9 billion won. The NFA states the leading causes of these fire occurrences were a series of mountain fires [12].…”
Mountains are popular tourist destinations due to their climate, fresh atmosphere, breathtaking sceneries, and varied topography. However, they are at times exposed to accidents, such as fire caused due to natural hazards and human activities. Such unforeseen fire accidents have a social, economic, and environmental impact on mountain towns worldwide. Protecting mountains from such fire accidents is also very challenging in terms of the high cost of fire containment resources, tracking fire spread, and evacuating the people at risk. This paper aims to fill this gap and proposes a three-fold methodology for fire safety in the mountains. The first part of the methodology is an optimization model for effective fire containment resource utilization. The second part of the methodology is a novel ensemble model based on machine learning, the heuristic approach, and principal component regression for predictive analytics of fire spread data. The final part of the methodology consists of an Internet of Things-based task orchestration approach to notify fire safety information to safety authorities. The proposed three-fold fire safety approach provides in-time information to safety authorities for making on-time decisions to minimize the damage caused by mountain fire with minimum containment cost. The performance of optimization models is evaluated in terms of execution time and cost. The particle swarm optimization-based model performs better in terms of cost, whereas the bat algorithm performs better in terms of execution time. The prediction models’ performance is evaluated in terms of root mean square error, mean absolute error, and mean absolute percentage error. The proposed ensemble-based prediction model accuracy for fire spread and burned area prediction is higher than that of the state-of-the-art algorithms. It is evident from the results that the proposed fire safety mechanism is a step towards efficient mountain fire safety management.
“…Therefore, the coefficients should also be adjusted by performing a new vicarious calibration for consistent radiance values. Although most studies related to these satellites have focused on the verification and calibration of the imaging sensors [23][24][25][26][27][28][29][30], efforts to improve and conserve the quality of satellite images must be maintained. Therefore, this study performs an absolute radiometric calibration of KOMPSAT-3 and -3A multispectral images from electro-optical imaging sensors to obtain the latest DN to radiance coefficients.…”
Radiometric calibration of satellite imaging sensors should be performed periodically to account for the effect of sensor degradation in the space environment on image accuracy. In this study, we performed vicarious radiometric calibrations (relying on in situ data) of multispectral imaging sensors on the Korea multi-purpose satellite-3 and -3A (KOMPSAT-3 and -3A) to adjust the existing radiometric conversion coefficients according to time delay integration (TDI) adjustments and sensor degradation over time. The Second Simulation of a Satellite Signal in the Solar Spectrum (6S) radiative transfer model was used to obtain theoretical top of atmosphere radiances for both satellites. As input parameters for the 6S model, surface reflectance values of well-characterized pseudo-invariant tarps were measured using dual ASD FieldSpec ® 3 hyperspectral radiometers, and atmospheric conditions were measured using Microtops II ® Sunphotometer and Ozonometer. We updated the digital number (DN) of the radiance coefficients of the satellites; these had been used to calibrate the sensors during in-orbit test periods in 2013 and 2015. The coefficients of determination, R 2 , values between observed DNs of the sensors, and simulated radiances for the tarps were more than 0.999. The calibration errors were approximately 5.7% based on manifested error sources. We expect that the updated coefficients will be an important reference for KOMPSAT-3 and -3A users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.