基于深度残差网络的机载LiDAR点云分类     

赵传  郭海涛  卢俊  余东行  张保明 《测绘学报》2020,49(2):202-213

机载LiDAR点云的分类是利用其进行城市场景三维重建的关键步骤之一。为充分利用现有的图像领域性能较好的深度学习网络模型,提高点云分类精度,并降低训练时间和对训练样本数量的要求,本文提出一种基于深度残差网络的机载LiDAR点云分类方法。首先提取归一化高程、表面变化率、强度和归一化植被指数4种具有较高区分度的点云低层次特征;然后通过设置不同的邻域大小和视角,利用所提出的点云特征图生成策略,得到多尺度和多视角点云特征图;再将点云特征图输入到预训练的深度残差网络,提取多尺度和多视角深层次特征;最后构建并训练神经网络分类器,利用训练的模型对待分类点云进行预测,经后处理得到分类结果。利用ISPRS三维语义标记竞赛的公开标准数据集进行试验,结果表明,本文方法可有效区分建筑物、地面、车辆等8类地物,分类结果的总体精度为87.1%,可为城市场景三维重建提供可靠的信息。  相似文献   

地表覆盖分类成果质量特征分析   总被引：1，自引：1，他引：0  

商建伟 《测绘通报》2020,(9):159-161

自我国全面建成地理国情普查成果库之后，工作重心由全面普查变为重点监测。不论普查还是监测，准确地对地表覆盖进行分类一直是工作的重点和难点。在常态化监测阶段，把握地表覆盖分类成果的主要质量指标，归纳其诸如变化率、变化区域分布、变化类型，分析影响其成果质量的主要因素，对监测生产组织及质量控制具有非常重要的作用。  相似文献   

Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data: A case study in the St. Lucia wetlands,South Africa     

《International Journal of Applied Earth Observation and Geoinformation》2020

Wetlands have been determined as one of the most valuable ecosystems on Earth and are currently being lost at alarming rates. Large-scale monitoring of wetlands is of high importance, but also challenging. The Sentinel-1 and -2 satellite missions for the first time provide radar and optical data at high spatial and temporal detail, and with this a unique opportunity for more accurate wetland mapping from space arises. Recent studies already used Sentinel-1 and -2 data to map specific wetland types or characteristics, but for comprehensive wetland characterisations the potential of the data has not been researched yet. The aim of our research was to study the use of the high-resolution and temporally dense Sentinel-1 and -2 data for wetland mapping in multiple levels of characterisation. The use of the data was assessed by applying Random Forests for multiple classification levels including general wetland delineation, wetland vegetation types and surface water dynamics. The results for the St. Lucia wetlands in South Africa showed that combining Sentinel-1 and -2 led to significantly higher classification accuracies than for using the systems separately. Accuracies were relatively poor for classifications in high-vegetated wetlands, as subcanopy flooding could not be detected with Sentinel-1’s C-band sensors operating in VV/VH mode. When excluding high-vegetated areas, overall accuracies were reached of 88.5% for general wetland delineation, 90.7% for mapping wetland vegetation types and 87.1% for mapping surface water dynamics. Sentinel-2 was particularly of value for general wetland delineation, while Sentinel-1 showed more value for mapping wetland vegetation types. Overlaid maps of all classification levels obtained overall accuracies of 69.1% and 76.4% for classifying ten and seven wetland classes respectively.  相似文献   

Satellite image analysis using crowdsourcing data for collaborative mapping: current and opportunities     

Wei Su  Xiaodong Zhang 《International Journal of Digital Earth》2020,13(6):645-660

ABSTRACT

Researchers are continually finding new applications of satellite images because of the growing number of high-resolution images with wide spatial coverage. However, the cost of these images is sometimes high, and their temporal resolution is relatively coarse. Crowdsourcing is an increasingly common source of data that takes advantage of local stakeholder knowledge and that provides a higher frequency of data. The complementarity of these two data sources suggests there is great potential for mutually beneficial integration. Unfortunately, there are still important gaps in crowdsourced satellite image analysis by means of crowdsourcing in areas such as land cover classification and emergency management. In this paper, we summarize recent efforts, and discuss the challenges and prospects of satellite image analysis for geospatial applications using crowdsourcing. Crowdsourcing can be used to improve satellite image analysis and satellite images can be used to organize crowdsourced efforts for collaborative mapping.  相似文献   

基于深度学习的目标检测定位系统设计与实现     

王俊强  李建胜  程相博  杨戬峰 《测绘与空间地理信息》2020,(1):133-136,144

针对传统遥感影像目标检测方法效率不高,并且无有效手段对检测信息进行管理利用的问题,提出了在B/S构架下基于深度学习的目标检测及定位方法。通过集成深度学习框架、WebGIS以及数据库,实现了集遥感影像目标检测、展示及管理于一体的目标检测定位系统,满足多用户基于前端浏览器的并发目标检测需求。利用网格划分策略,实现了基于前端的大区域范围的目标快速检测。基于某机场飞机目标及某城市区域运动场目标检测结果表明:本文设计的目标检测定位系统能够在前端实现目标快速检测定位,具有较高检测精度,并可有效管理检测信息,为深度学习循环再利用提供数据支撑。  相似文献   

测绘地理信息档案管理对策研究     

李明 《测绘与空间地理信息》2020,(3):9-11,15

国民经济建设对测绘地理信息档案的需求旺盛,如何对测绘地理信息数据进行归档管理,提高测绘地理信息档案存储的安全性及方便再利用,已经成为测绘地理信息档案管理部门需要研究的重要课题。本文通过分析当前测绘地理信息档案管理的现状,指出存在的问题,提出有力的改进措施。  相似文献   

MEEMD-Elman神经网络的电离层TEC预报模型     

汤俊  高鑫 《大地测量与地球动力学》2020,40(4):395-399

利用IGS中心提供的不同纬度的电离层TEC值,建立基于改进的集总平均经验模态分解(MEEMD)算法和Elman回归神经网络(ERNN)模型相结合的电离层TEC预报模型。实验结果表明,在低、中、高不同纬度采用本文方法预报5 d电离层TEC的预测值的均方根误差最优可达到0.96 TECu,相对精度最优达到95.4%,精度较EMD-ERNN模型及单一ERNN模型有显著提高。  相似文献   

基于国产高分遥感的人工种植红树林种间分类方法研究——以广西茅尾海红树林为例          下载免费PDF全文

马云梅  吴培强  任广波  傅宇  马毅  包玉海 《海洋技术学报》2019,38(4):1-8

红树林的种间结构组成对红树林生态系统的健康和发展至关重要,而红树林种间分类问题一直以来都是基于遥感手段的红树林监测中的难点。针对该问题,以人工种植为特点的广西茅尾海红树林遥感种间分类为例,基于面向对象的分类思想,提出了一种现场样本与分割对象相结合的红树林种间分类方法。利用GF-2 PMS1高分辨率卫星遥感影像数据,开展了广西茅尾海红树林湿地典型植被精细分类和空间分布研究,并将分类结果与基于像素和传统面向对象SVM分类方法进行了对比。结果显示:总体上,面向对象分类方法更适合用于茅尾海红树林湿地典型植被分类;对于局部混生明显的区域使用基于像素SVM分类方法效果会更好;传统面向对象分类方法中将整个影像分割对象单元作为训练样本可能会在某种程度上造成负面影响。因此,使用文中提出的样本选择新方法进行面向对象分类精度最高,总体精度达到了93.13%,Kappa为0.89。  相似文献   

Research on the Method of De-noising the Short-wave Time Signal at Low SNR     

《Chinese Astronomy and Astrophysics》2019,43(4):579-589

A voice enhancement algorithm based on the Empirical Mode Decomposition (EMD) and the improved spectral subtraction is proposed for the low-SNR (Signal Noise Ratio) shortwave time signal. This method is proposed to solve the problem that the shortwave time signal cannot be used for timing in complex noisy environments. The core idea of this method is to use the Hilbert-Huang Transform (HHT) algorithm to make the empirical mode decomposition on the noisy shortwave signal, and to select the intrinsic mode functions containing the shortwave signal information for the signal reconstruction by through the maximum correlation. Then, to make the spectral subtraction on the reconstructed signal to achieve the purpose of noise reduction. The experimental result shows that this method has a better noise reduction than the traditional methods.  相似文献   

一种基于M估计的Robust-ELM滑坡位移预测方法     

高彩云  高宁 《大地测量与地球动力学》2019,39(2):153-157

采用传统ELM算法进行滑坡位移预测时，其网络输出权值由最小二乘估计得出，导致ELM抗差能力较差，从而造成网络训练参数不准确。为此，将M估计与ELM相结合，提出一种基于M估计的Robust-ELM滑坡变形预测方法。该方法利用加权最小二乘方法来取代最小二乘法计算ELM输出权值，以减少滑坡监测数据中粗差对ELM预测的干扰。分别以链子崖、古树屋滑坡体为例，将Robust-ELM进行了单维、多维粗差的抵御性验证。结果表明，该方法能够有效降低粗差对预测的影响，具有良好的抗差能力。  相似文献