The main constituent parts of unmanned aerial vehicle aerial photogrammetry systems are discussed.The key issues including the division of regional networks,the layout of regional networks,the correction of lens disto...The main constituent parts of unmanned aerial vehicle aerial photogrammetry systems are discussed.The key issues including the division of regional networks,the layout of regional networks,the correction of lens distortion,the optimization of external orientation elements,the aerial triangulation,the image matching and fusion,and the production of digital elevation models and digital orthoimages,tilt real 3 D models,and digital line drawings,were analyzed.The advantages of UAV aerial photogrammetry were compared.This study provides reference for measuring large-scale topographic maps by UAV photogrammetry systems.展开更多
In collaboration with 12 other institutions, the Meteorological Observation Center of the China Meteorological Administration undertook a comprehensive marine observation experiment in the South China Sea using the Yi...In collaboration with 12 other institutions, the Meteorological Observation Center of the China Meteorological Administration undertook a comprehensive marine observation experiment in the South China Sea using the Yilong-10 high-altitude large unmanned aerial vehicle(UAV). The Yilong-10 UAV carried a self-developed dropsonde system and a millimeter-wave cloud radar system. In addition, a solar-powered unmanned surface vessel and two drifting buoys were used. The experiment was further supported by an intelligent, reciprocating horizontal drifting radiosonde system that was deployed from the Sansha Meteorological Observing Station, with the intent of producing a stereoscopic observation over the South China Sea. Comprehensive three-dimensional observations were collected using the system from 31 July to2 August, 2020. This information was used to investigate the formation and development processes of Typhoon Sinlaku(2020). The data contain measurements of 21 oceanic and meteorological parameters acquired by the five devices, along with video footage from the UAV. The data proved very helpful in determining the actual location and intensity of Typhoon Sinlaku(2020). The experiment demonstrates the feasibility of using a high-altitude, large UAV to fill in the gaps between operational meteorological observations of marine areas and typhoons near China, and marks a milestone for the use of such data for analyzing the structure and impact of a typhoon in the South China Sea. It also demonstrates the potential for establishing operational UAV meteorological observing systems in the future, and the assimilation of such data into numerical weather prediction models.展开更多
从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(conce...从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(concentration-based attention module)注意力机制改进卷积模块,解决注意力权重参数在感受野特征中共享问题的同时,在通道和空间维度加上注意力权重,增强特征提取能力;通过引入大型可分离卷积注意力思想,改造空间金字塔池化层,增加不同层级特征间的信息交融;优化颈部结构,增加具有丰富小目标语义信息的特征层;使用inner-IoU损失函数的思想改进MPDIoU(minimum point distance based IoU)函数,以innerMPDIoU代替原损失函数,提升对困难样本的学习能力。实验结果表明,改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%,性能超过YOLOv8m,可以有效应用于无人机平台上的目标检测任务。展开更多
文摘The main constituent parts of unmanned aerial vehicle aerial photogrammetry systems are discussed.The key issues including the division of regional networks,the layout of regional networks,the correction of lens distortion,the optimization of external orientation elements,the aerial triangulation,the image matching and fusion,and the production of digital elevation models and digital orthoimages,tilt real 3 D models,and digital line drawings,were analyzed.The advantages of UAV aerial photogrammetry were compared.This study provides reference for measuring large-scale topographic maps by UAV photogrammetry systems.
基金supported by the Petrel Meteorological Observation Experiment Project of the China Meteorological Administration and the “Adaptive Improvement of New Observation Platform for Typhoon Observation (2018YFC1506401)” of the Ministry of Science and Technology。
文摘In collaboration with 12 other institutions, the Meteorological Observation Center of the China Meteorological Administration undertook a comprehensive marine observation experiment in the South China Sea using the Yilong-10 high-altitude large unmanned aerial vehicle(UAV). The Yilong-10 UAV carried a self-developed dropsonde system and a millimeter-wave cloud radar system. In addition, a solar-powered unmanned surface vessel and two drifting buoys were used. The experiment was further supported by an intelligent, reciprocating horizontal drifting radiosonde system that was deployed from the Sansha Meteorological Observing Station, with the intent of producing a stereoscopic observation over the South China Sea. Comprehensive three-dimensional observations were collected using the system from 31 July to2 August, 2020. This information was used to investigate the formation and development processes of Typhoon Sinlaku(2020). The data contain measurements of 21 oceanic and meteorological parameters acquired by the five devices, along with video footage from the UAV. The data proved very helpful in determining the actual location and intensity of Typhoon Sinlaku(2020). The experiment demonstrates the feasibility of using a high-altitude, large UAV to fill in the gaps between operational meteorological observations of marine areas and typhoons near China, and marks a milestone for the use of such data for analyzing the structure and impact of a typhoon in the South China Sea. It also demonstrates the potential for establishing operational UAV meteorological observing systems in the future, and the assimilation of such data into numerical weather prediction models.
文摘从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(concentration-based attention module)注意力机制改进卷积模块,解决注意力权重参数在感受野特征中共享问题的同时,在通道和空间维度加上注意力权重,增强特征提取能力;通过引入大型可分离卷积注意力思想,改造空间金字塔池化层,增加不同层级特征间的信息交融;优化颈部结构,增加具有丰富小目标语义信息的特征层;使用inner-IoU损失函数的思想改进MPDIoU(minimum point distance based IoU)函数,以innerMPDIoU代替原损失函数,提升对困难样本的学习能力。实验结果表明,改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%,性能超过YOLOv8m,可以有效应用于无人机平台上的目标检测任务。