在林业管理中,及时发现火灾并识别其规模对于安全防护和治理火灾至关重要。针对现有火灾检测算法存在的精度低、漏检误检和实时性不足等问题,提出一种无人机航拍图像下火灾实时检测算法——MDSYOLOv8。以YOLOv8为基线算法,将骨干网络第...在林业管理中,及时发现火灾并识别其规模对于安全防护和治理火灾至关重要。针对现有火灾检测算法存在的精度低、漏检误检和实时性不足等问题,提出一种无人机航拍图像下火灾实时检测算法——MDSYOLOv8。以YOLOv8为基线算法,将骨干网络第7层卷积模块和颈部网络卷积模块替换成动态蛇形卷积(DSConv),提高算法的特征提取性能,并强化算法对微小特征的学习能力;然后在颈部与检测头之间添加多维协作注意力机制(MCA),加强颈部特征融合,增强算法对小目标的检测能力,并抑制无关背景信息;最后使用SIoU损失函数替换原YOLOv8中的CIoU损失函数,加快算法的收敛速度和回归精度。实验结果表明,MDSYOLOv8在公开数据集KMU上对烟雾目标的检测精度mAP达到95.89%,相较于基线YOLOv8提高了3.33个百分点,具有卓越的检测性能。此外,本研究采集互联网上的无人机航拍火灾图像制作UFF(UAV field fire)数据集,主要对象为火焰和烟雾,包含森林和城市等火灾隐患可能发生场景。在自制数据集UFF上进行深度实验分析,MDSYOLOv8的检测精度达到93.98%,检测速度为54帧/s,并且能同时识别烟雾和火焰两种火灾场景中的主要目标,与主流目标检测方法相比,在检测精度和效率方面均展现出明显优势,更加契合航拍场景下的火灾检测应用。展开更多
Fire incidents in commercial vehicles pose significant risks to passengers, drivers, and cargo. Traditional fire extinguishing systems, while effective, may have limitations in terms of response time, coverage, and hu...Fire incidents in commercial vehicles pose significant risks to passengers, drivers, and cargo. Traditional fire extinguishing systems, while effective, may have limitations in terms of response time, coverage, and human intervention [1]. This study investigates the efficacy of a novel fire suppression technology—the Exploding Fire Extinguishing Ball (EFEB) —as an alternative and complementary fire safety solution for commercial vehicles. The research employs a multidisciplinary approach, encompassing engineering, materials science, fire safety, and human factors analysis. A systematic literature review establishes a comprehensive understanding of existing fire suppression technologies, including EFEBs. Subsequently, this study analyzes the unique features of EFEBs, such as automatic activation, as well as manual activation upon exposure to fire, and their potential to provide rapid, localized, and autonomous fire suppression. The study presents original experimental investigations to assess the performance and effectiveness of EFEBs in various fire scenarios representative of commercial vehicles. Experiments include controlled fires in confined spaces and dynamic simulations to emulate real-world fire incidents. Data on activation times, extinguishing capability, and coverage area are collected and analyzed to compare the efficacy of EFEBs with traditional fire extinguishing methods. Furthermore, this research shows the practical aspects of implementing EFEBs in commercial vehicles. A feasibility study examines the integration challenges, cost-benefit analysis, and potential regulatory implications. The study also addresses the impact of EFEBs on vehicle weight, stability, and overall safety. Human factors and user acceptance are crucial elements in adopting new safety technologies. Therefore, this research utilizes an experimental design to assess the performance and effectiveness of EFEBs in various fire scenarios representative of commercial vehicles. This dissertation presents original controlled experiments to emulate real-world fire incidents, including controlled fires in confined spaces and dynamic simulations. The experimental approach ensures rigorous evaluation and objective insights into EFEBs’ potential as an autonomous fire suppression system for commercial vehicles. This includes the perspectives of drivers, passengers, fleet operators, insurance agencies, and regulatory bodies. Factors influencing trust, perceived safety, and willingness to adopt EFEBs are analyzed to provide insights into the successful integration of this technology. The findings of this research will contribute to the knowledge of fire safety technology and expand the understanding of the applicability of EFEBs in commercial vehicles.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
文摘在林业管理中,及时发现火灾并识别其规模对于安全防护和治理火灾至关重要。针对现有火灾检测算法存在的精度低、漏检误检和实时性不足等问题,提出一种无人机航拍图像下火灾实时检测算法——MDSYOLOv8。以YOLOv8为基线算法,将骨干网络第7层卷积模块和颈部网络卷积模块替换成动态蛇形卷积(DSConv),提高算法的特征提取性能,并强化算法对微小特征的学习能力;然后在颈部与检测头之间添加多维协作注意力机制(MCA),加强颈部特征融合,增强算法对小目标的检测能力,并抑制无关背景信息;最后使用SIoU损失函数替换原YOLOv8中的CIoU损失函数,加快算法的收敛速度和回归精度。实验结果表明,MDSYOLOv8在公开数据集KMU上对烟雾目标的检测精度mAP达到95.89%,相较于基线YOLOv8提高了3.33个百分点,具有卓越的检测性能。此外,本研究采集互联网上的无人机航拍火灾图像制作UFF(UAV field fire)数据集,主要对象为火焰和烟雾,包含森林和城市等火灾隐患可能发生场景。在自制数据集UFF上进行深度实验分析,MDSYOLOv8的检测精度达到93.98%,检测速度为54帧/s,并且能同时识别烟雾和火焰两种火灾场景中的主要目标,与主流目标检测方法相比,在检测精度和效率方面均展现出明显优势,更加契合航拍场景下的火灾检测应用。
文摘Fire incidents in commercial vehicles pose significant risks to passengers, drivers, and cargo. Traditional fire extinguishing systems, while effective, may have limitations in terms of response time, coverage, and human intervention [1]. This study investigates the efficacy of a novel fire suppression technology—the Exploding Fire Extinguishing Ball (EFEB) —as an alternative and complementary fire safety solution for commercial vehicles. The research employs a multidisciplinary approach, encompassing engineering, materials science, fire safety, and human factors analysis. A systematic literature review establishes a comprehensive understanding of existing fire suppression technologies, including EFEBs. Subsequently, this study analyzes the unique features of EFEBs, such as automatic activation, as well as manual activation upon exposure to fire, and their potential to provide rapid, localized, and autonomous fire suppression. The study presents original experimental investigations to assess the performance and effectiveness of EFEBs in various fire scenarios representative of commercial vehicles. Experiments include controlled fires in confined spaces and dynamic simulations to emulate real-world fire incidents. Data on activation times, extinguishing capability, and coverage area are collected and analyzed to compare the efficacy of EFEBs with traditional fire extinguishing methods. Furthermore, this research shows the practical aspects of implementing EFEBs in commercial vehicles. A feasibility study examines the integration challenges, cost-benefit analysis, and potential regulatory implications. The study also addresses the impact of EFEBs on vehicle weight, stability, and overall safety. Human factors and user acceptance are crucial elements in adopting new safety technologies. Therefore, this research utilizes an experimental design to assess the performance and effectiveness of EFEBs in various fire scenarios representative of commercial vehicles. This dissertation presents original controlled experiments to emulate real-world fire incidents, including controlled fires in confined spaces and dynamic simulations. The experimental approach ensures rigorous evaluation and objective insights into EFEBs’ potential as an autonomous fire suppression system for commercial vehicles. This includes the perspectives of drivers, passengers, fleet operators, insurance agencies, and regulatory bodies. Factors influencing trust, perceived safety, and willingness to adopt EFEBs are analyzed to provide insights into the successful integration of this technology. The findings of this research will contribute to the knowledge of fire safety technology and expand the understanding of the applicability of EFEBs in commercial vehicles.
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.
