基于深度语义分割的FY-2E遥感影像云检测方法     

高昂  肖萌  唐世浩  姜灵峰  咸迪  郑伟 《气象科技》2021,49(5):671-680

本文提出了一种基于深度语义分割技术的全自动云检测算法,可提高FY-2E遥感影像的云检测精度。首先,将FY-2EL1数据与精度较高的云检测结果进行匹配,获得用于训练和评估样本的数据集;其次,设计了深度语义分割网络,并针对训练集中正负样本严重失衡的问题,改进了损失函数,可以有效提取云的边界;最后,分别以FY-2E和MODIS数据作为训练和标签样本训练网络,得到了可用于FY-2EL1影像检测的四分类模型。试验结果表明,在四分类检测中,所提方法的准确率达到了75%,Kappa系数为0.53左右。与现有多通道阈值法相比,采用所提方法进行二分类检测可提高约90%样本的准确率,部分样本的准确率提升20%以上。此外,所提方法对云边缘、破碎云等细节识别能力较强,且具有一定的鲁棒性,受训练样本中的误判类别影响较小。未来通过扩充数据集并优化网络,可提高FY-2全圆盘影像的数据质量。  相似文献   

天宫一号高光谱遥感场景分类数据集及应用     

刘康  周壮  李盛阳  刘云飞  万雪  刘志文  谭洪  张万峰 《遥感学报》2020,24(9):1077-1087

天宫一号高光谱成像仪具有空间分辨率高、光谱分辨率高、图谱合一等特性，在中国航天高光谱领域具有里程碑的意义。针对一般遥感场景分类数据集尺度单一、光谱分辨率较低等问题，本文提出基于天宫一号的多谱段、高空间分辨率、多时相高光谱遥感场景分类数据集(TG1HRSSC)。利用天宫一号高光谱成像仪获取的高质量数据，经过辐射校正、几何校正、空间裁剪、波段筛选、数据质量分析与控制等，制作了一批通用的航天高光谱遥感场景分类数据集，通过载人航天空间应用数据推广服务平台（http://www.msadc.cn[2019-09-10]）进行分发和共享。该数据集包括天宫一号高光谱成像仪获取的城镇、农田、林地、养殖塘、荒漠、湖泊、河流、港口、机场等9个典型地物场景的204个高光谱影像数据，其中5 m分辨率全色谱段1个波段、10 m分辨率可见近红外谱段54个有效波段以及20 m分辨率短波红外谱段52个有效波段。研究利用AlexNet、VGG-VD-16、GoogLeNet等深度学习算法网络对构建的数据集进行场景分类的试验，结果表明该数据集的场景分类应用实现较好效果。由于该数据集具备高分辨、高光谱等特征优势，未来在语义理解、多目标检测等方面有着广泛的应用价值。  相似文献   

Deep learning for geometric and semantic tasks in photogrammetry and remote sensing     

Christian Heipke  Franz Rottensteiner 《地球空间信息科学学报》2020,23(1):10-19

ABSTRACT

During the last few years, artificial intelligence based on deep learning, and particularly based on convolutional neural networks, has acted as a game changer in just about all tasks related to photogrammetry and remote sensing. Results have shown partly significant improvements in many projects all across the photogrammetric processing chain from image orientation to surface reconstruction, scene classification as well as change detection, object extraction and object tracking and recognition in image sequences. This paper summarizes the foundations of deep learning for photogrammetry and remote sensing before illustrating, by way of example, different projects being carried out at the Institute of Photogrammetry and GeoInformation, Leibniz University Hannover, in this exciting and fast moving field of research and development.  相似文献   

Comparative performance of convolutional neural network,weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data     

C. Sothe  C. M. De Almeida  M. B. Schimalski  L. E. C. La Rosa  J. D. B. Castro  R. Q. Feitosa 《地理信息系统科学与遥感》2020,57(3):369-394

ABSTRACT

The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced classification methods. This study investigated the following topics concerning the classification of 16 tree species in two subtropical forest fragments of Southern Brazil: i) the potential integration of UAV-borne hyperspectral images with 3D information derived from their photogrammetric point cloud (PPC); ii) the performance of two machine learning methods (support vector machine – SVM and random forest – RF) when employing different datasets at a pixel and individual tree crown (ITC) levels; iii) the potential of two methods for dealing with the imbalanced sample set problem: a new weighted SVM (wSVM) approach, which attributes different weights to each sample and class, and a deep learning classifier (convolutional neural network – CNN), associated with a previous step to balance the sample set; and finally, iv) the potential of this last classifier for tree species classification as compared to the above mentioned machine learning methods. Results showed that the inclusion of the PPC features to the hyperspectral data provided a great accuracy increase in tree species classification results when conventional machine learning methods were applied, between 13 and 17% depending on the classifier and the study area characteristics. When using the PPC features and the canopy height model (CHM), associated with the majority vote (MV) rule, the SVM, wSVM and RF classifiers reached accuracies similar to the CNN, which outperformed these classifiers for both areas when considering the pixel-based classifications (overall accuracy of 84.4% in Area 1, and 74.95% in Area 2). The CNN was between 22% and 26% more accurate than the SVM and RF when only the hyperspectral bands were employed. The wSVM provided a slight increase in accuracy not only for some lesser represented classes, but also some major classes in Area 2. While conventional machine learning methods are faster, they demonstrated to be less stable to changes in datasets, depending on prior segmentation and hand-engineered features to reach similar accuracies to those attained by the CNN. To date, CNNs have been barely explored for the classification of tree species, and CNN-based classifications in the literature have not dealt with hyperspectral data specifically focusing on tropical environments. This paper thus presents innovative strategies for classifying tree species in subtropical forest areas at a refined legend level, integrating UAV-borne 2D hyperspectral and 3D photogrammetric data and relying on both deep and conventional machine learning approaches.  相似文献   

Modeling the spatial variation of urban land surface temperature in relation to environmental and anthropogenic factors: a case study of Tehran,Iran     

Hossein Shafizadeh-Moghadam  Hua Liu  Roozbeh Valavi 《地理信息系统科学与遥感》2020,57(4):483-496

ABSTRACT

Spatial variation of Urban Land Surface Temperature (ULST) is a complex function of environmental, climatic, and anthropogenic factors. It thus requires specific techniques to quantify this phenomenon and its influencing factors. In this study, four models, Random Forest (RF), Generalized Additive Model (GAM), Boosted Regression Tree (BRT), and Support Vector Machine (SVM), are calibrated to simulate the ULST based on independent factors, i.e., land use/land cover (LULC), solar radiation, altitude, aspect, distance to major roads, and Normalized Difference Vegetation Index (NDVI). Additionally, the spatial influence and the main interactions among the influential factors of the ULST are explored. Landsat-8 is the main source for data extraction and Tehran metropolitan area in Iran is selected as the study area. Results show that NDVI, LULC, and altitude explained 86% of the ULST °C variation. Unexpectedly, lower LST is observed near the major roads, which was due to the presence of vegetation along the streets and highways in Tehran. The results also revealed that variation in the ULST was influenced by the interaction between altitude – NDVI, altitude – road, and LULC – altitude. This indicates that the individual examination of the underlying factors of the ULST variation might be unilluminating. Performance evaluation of the four models reveals a close performance in which their R² and Root Mean Square Error (RMSE) fall between 60.6–62.1% and 2.56–2.60 °C, respectively. However, the difference between the models is not statistically significant. This study evaluated the predictive performance of several models for ULST simulation and enhanced our understanding of the spatial influence and interactions among the underlying driving forces of the ULST variations.  相似文献   

航拍图像跨数据域特征迁移道路提取方法     

王舒洋  慕晓冬  贺浩  杨东方  马晨晖 《测绘学报》2020,49(5):611-621

针对传统道路提取方法应用于新数据泛化能力不足的问题,研究了通过特征迁移和编解码网络实现跨数据域的道路提取方法。首先,构建了基于编解码网络的道路提取基本模型,用于实现单一数据来源的道路提取任务。然后,基于道路提取网络结构和循环一致性原则,提出了用于跨数据域图像特征迁移的循环生成对抗网络,使目标域图像映射入源域特征空间。使用预训练的道路提取模型处理特征迁移后的目标域图像,即可实现跨数据域道路提取任务。试验结果表明,本文所提方法能够拓展道路提取网络的泛化能力,准确有效地提取跨数据域图像中的道路目标。相较于未特征迁移的结果,本文所提方法大幅改善了道路提取指标,使得F1提升了50%以上。本文方法不需要目标域的标注信息,也不需要对道路提取网络进行微调训练,而只需训练由目标域向源域的特征迁移模型,所耗时间和人力成本较低,因而具有良好的应用价值。  相似文献   

Comparison of local and global approximators in multivariate chaotic forecasting of daily streamflow     

Hakan Tongal 《水文科学杂志》2020,65(7):1129-1144

ABSTRACT

Although it is conceptually assumed that global models are relatively ineffective in modelling the highly unstable structure of chaotic hydrologic dynamics, there is not a detailed study of comparing the performances of local and global models in a hydrological context, especially with new emerging machine learning models. In this study, the performance of a local model (k-nearest neighbour, k-nn) and, as global models, several recent machine learning models – artificial neural network (ANN), least square-support vector regression (LS-SVR), random forest (RF), M5 model tree (M5), multivariate adaptive regression splines (MARS) – was analysed in multivariate chaotic forecasting of streamflow. The models were developed for Australia’s largest river, the River Murray. The results indicate that the k-nn model was more successful than the global models in capturing the streamflow dynamics. Furthermore, coupled with the multivariate phase-space, it was shown that the global models can be successfully used for obtaining reliable uncertainty estimates for streamflow.  相似文献   

Deep echo state network: a novel machine learning approach to model dew point temperature using meteorological variables     

Meysam Alizamir  Sungwon Kim  Ozgur Kisi  Mohammad Zounemat-Kermani 《水文科学杂志》2020,65(7):1173-1190

ABSTRACT

The potential of different models – deep echo state network (DeepESN), extreme learning machine (ELM), extra tree (ET), and regression tree (RT) – in estimating dew point temperature by using meteorological variables is investigated. The variables consist of daily records of average air temperature, atmospheric pressure, relative humidity, wind speed, solar radiation, and dew point temperature (T_dew) from Seoul and Incheon stations, Republic of Korea. Evaluation of the model performance shows that the models with five and three-input variables yielded better accuracy than the other models in these two stations, respectively. In terms of root-mean-square error, there was significant increase in accuracy when using the DeepESN model compared to the ELM (18%), ET (58%), and RT (64%) models at Seoul station and the ELM (12%), ET (23%), and RT (49%) models at Incheon. The results show that the proposed DeepESN model performed better than the other models in forecasting T_dew values.  相似文献   

基于深度学习技术的地震实时流数据自动处理辅助工具开发     

赵明  廖诗荣  黄玲珠 《地震地磁观测与研究》2020,41(2):165-171

以JOPENS系统实时流接收为基础,应用Redis共享内存技术和近年来发展较快的深度学习震相自动识别技术,设计一套可7×24小时不间断稳定接收并实时识别连续地震流数据中P、S震相的系统,为地震台网实时数据处理提供一套辅助工具,并在福建省地震局测震台网128个台站的实时数据流上进行测试。该工具由Redis实时数据流共享模块与深度学习震相到时自动拾取、MSDP震相格式转换3个模块组成,可以实时接收并自动识别台网地震连续波形,生成P、S震相报告,并可导入MSDP人机交互工具进一步处理,在一定程度上可以减轻人工处理工作量。  相似文献   

机器学习在气象领域的应用现状与展望     

杜智涛  姜明波  杜晓勇  周育峰  王鹏宇  张志标 《气象科技》2021,49(6):930-941

机器学习是人工智能的核心，是使计算机具有智能的根本途径之一。随着以深度学习为代表的机器学习算法取得突破，人工智能呈现了加速发展的趋势，在各行业取得了广泛的应用。机器学习在计算效率、准确性、可移植性、协同性、灵活性、易用性等方面具有较大的优势，下一步将有可能改变传统的气象观测模式，加速和改善气象观测数据的处理，改善数值天气预报质量以及推进地球科学的交叉融合。为更好地推动人工智能相关技术在气象领域的应用，本文从气象观探测、数值预报、危险天气识别与预警和卫星资料处理等方面对机器学习算法的应用现状进行了整理。  相似文献