深度学习支持下的宅基地复垦项目真实性智能审查技术研究与应用     

向煜  黄志  华媛媛  邓剑峰 《测绘通报》2023,(1):163-167

全域综合整治背景下的宅基地复垦项目审查是保证复垦项目合法性合规性的有效手段,针对当前宅基地复垦项目审查效率低的问题,本文提出了基于遥感影像的农村宅基地复垦项目立项真实性审查方法。首先以重庆市农村宅基地复垦项目为例,建立宅基地复垦项目立项真实性审查模型,利用改进的U-Net模型准确提取建筑物,然后与复垦红线叠加实现复垦项目真实性的智能审查。试验结果表明,该方法能够快速准确地审查复垦项目真实性,对优化土地结构、促进土地流转、实现乡村振兴具有重要意义,可为全域综合整治背景下宅基地复垦项目真实性审查提供技术参考。  相似文献   

基于残差神经网络改进的密集人群计数方法     

史劲霖  周良辰  闾国年  林冰仙 《地球信息科学学报》2021,23(9):1537-1547

为避免密集人群踩踏事件发生,从监控图像中准确获取密集人群人数信息非常重要。针对密集人群计数难度大、人群目标小、场景尺度变化大等特点,本文提出一种新型神经网络结构VGG-ResNeXt。本网络使用VGG-16的前10层作粗粒度特征提取器,使用改进的残差神经网络作为细粒度特征提取器。利用改进的残差神经网络“多通道,共激活”的特点,使得单列式人群计数神经网络获得了多列式人群计数网络的优点（即从小目标、多尺度的密集人群图像中提取更多人群特征）,同时避免了多列式人群计数网络训练难度大、结构冗余等缺点。实验结果表明本模型在UCF-CC-50数据集、ShangHaiTech B数据集和UCF-QNRF数据集中取得了最高精度,MAE指标分别优于其他同期模型7.5%、18.8%和2.4%,证明了本模型的在计数精度方面的有效性。本研究成果可以有效帮助城市管理,有效缓解公安疏导压力,保障人民生命财产安全。  相似文献   

基于深度学习的滑坡灾害易发性分析     

王毅  方志策  牛瑞卿  彭令 《地球信息科学学报》2021,23(12):2244-2260

滑坡灾害成因机理复杂、影响因素众多,深度学习作为当前人工智能领域的热点,能够更好地模拟滑坡灾害的形成并准确预测潜在的斜坡。为了挖掘深度学习在滑坡易发性的应用潜能,本文构建了一维、二维和三维的滑坡数据表达形式,并提出3种基于卷积神经网络模型（Convolutional Neural Networks, CNN）的滑坡易发性分析处理框架：基于CNN分类器、基于CNN与逻辑回归的融合和基于CNN集成,最后以江西省铅山县为研究对象进行验证,结果表明：所有基于CNN的易发性模型都能够获得准确且可靠的滑坡易发性分析结果。其中,基于二维数据的CNN模型在所有单分类器中预测精度最高,为78.95%。此外,二维CNN特征提取能够显著提升逻辑回归的预测精度,其准确率提升7.9%。最后,异质集成策略能够大幅度提升基于CNN分类器的滑坡预测精度,其准确率提升4.35%~8.78%。  相似文献   

基于卷积神经网络的ICESat-2光子点云去噪分类     

陆大进  黎东  朱笑笑  聂胜  周国清  张兴忆  杨超 《地球信息科学学报》2021,23(11):2086-2095

ICESat-2（Ice, Cloud, and land Elevation Satellite-2）是美国NASA（National Aeronautics and Space Administration）在2018年发射的激光测高卫星,其上搭载的激光测高系统ATLAS（Advanced Topographic Laser Altimeter System）采用微脉冲多波束光子计数激光雷达系统,因其低能耗、高探测灵敏度、高重复频率的特性极大改善了沿轨采样密度,但也使获取的数据中包含大量的噪声,如何有效实现光子点云去噪分类成为后续应用的关键,也是当前研究的热点和难点,为此本文提出一种基于卷积神经网络的光子点云去噪和分类算法。首先将光子点云按照沿轨和高程方向划分格网,去除明显的噪声光子,并将每个粗信号光子点栅格化为影像;然后基于少量样本构建的卷积神经网络分类模型实现光子点云精去噪和分类;最后利用机载激光雷达数据进行验证,并与ATL08产品的去噪分类结果进行对比。结果表明,对于裸地和森林区域,卷积神经网络算法均能有效去除噪声光子,特别对于森林区域,可同时实现去噪和分类;其中,裸地区域地表计算的R²和RMSE分别为1.0和0.72 m,森林区域地表和树冠计算的R²分别为1.0和0.70, RMSE分别为1.11 m和4.99 m。本文利用深度学习算法实现光子点云去噪分类,在裸地和森林区域均取得了较好的结果,为后续光子点云数据处理提供了参考。  相似文献   

An artificial neural network-based snow cover predictive modeling in the higher Himalayas     

Bhogendra Mishra  Nitin K. Tripathi  Mukand S. Babel 《山地科学学报》2014,11(4):825-837

With trends indicating increase in temperature and decrease in winter precipitation, a significant negative trend in snow-covered areas has been identified in the last decade in the Himalayas. This requires a quantitative analysis of the snow cover in the higher Himalayas. In this study, a nonlinear autoregressive exogenous model, an artificial neural network （ANN）, was deployed to predict the snow cover in the Kaligandaki river basin for the next 30 years. Observed climatic data, and snow covered area was used to train and test the model that captures the gross features of snow under the current climate scenario. The range of the likely effects of climate change on seasonal snow was assessed in the Himalayas using downscaled temperature and precipitation change projection from - HadCM3, a global circulation model to project future climate scenario, under the AIB emission scenario, which describes a future world of very rapid economic growth with balance use between fossil and non-fossil energy sources. The results show that there is a reduction of 9% to 46% of snow cover in different elevation zones during the considered time period, i.e., 2Oll to 2040. The 4700 m to 52oo m elevation zone is the most affected area and the area higher than 5200 m is the least affected. Overall, however, it is clear from the analysis that seasonal snow in the Kaligandaki basin is likely to be subject to substantialchanges due to the impact of climate change.  相似文献   

Knowledge diffusion from GIScience to other fields: the example of the usage of weighted surface networks in nanotechnology     

Gert W. Wolf 《International journal of geographical information science》2014,28(7):1401-1424

This article demonstrates how the generalisation of topographic surfaces has been formalised by means of graph theory and how this formalised approach has been integrated into an ISO standard that is employed within nanotechnology. By applying concepts from higher-dimensional calculus and topology, it is shown that Morse functions are those mappings that are ideally suited for the formal characterisation of topographic surfaces. Based on this result, a data structure termed weighted surface network is defined that may be applied for both the characterisation and the generalisation of the topological structure of a topographic surface. Hereafter, the focus is laid on specific issues of the standard ISO 25178-2; within this standard change trees, a data structure similar to weighted surface networks, are applied to portray the topological information of topographic surfaces. Furthermore, an approach termed Wolf pruning is used to simplify the change tree, with this pruning method being equivalent to the graph-theoretic contractions by which weighted surface networks can be simplified. Finally, some practical applications of the standard ISO 25178-2 within nanotechnology are discussed.  相似文献   

信息物理系统研究与应用综述     

李伯宇  高飞  朱建平  韩瑞艳 《成都信息工程学院学报》2014,29(4):388-393

信息物理系统是以信息世界与物理世界的紧密结合为显著特征的,集计算、通信与控制为一体的网络系统。首先介绍信息物理系统的起源与发展。比较分析几个比较有代表性的信息物理系统定义,给出对信息物理系统的概念的理解与定义。在文献梳理的基础上,总结信息物理系统的主要特征。简要介绍3个典型的信息物理系统应用方案,即智能电网、生物与医疗、智能高速公路与无人驾驶。最后总结信息物理系统研究与应用中所面临的挑战,提出今后信息物理系统可能的研究热点。为更好地了解信息物理系统相关知识,为信息物理系统领域的研究提供有价值的参考。  相似文献   

����IPSO-BPģ�͵Ĵ�Ӷ�Դ�������Ԥ���뷴��     

胡纪元  文鸿雁  周吕  陈冠宇 《大地测量与地球动力学》2014,34(4):67-70

???????????????????IPSO??????????????????????м??????????????????????????????????????????????????????????????????????????????BP?????????γ?IPSO_BP??????????????????μ????????????????????????IPSO_BP???????????????Ч??????????????????????????????  相似文献   

Verifying Fossil-Fuel Carbon Dioxide Emissions Forecasted by an Artificial Neural Network with the GEOS-Chem Model          下载免费PDF全文

WANG Yi-Nan  Lü Da-Ren  LI Qian  PAN Yu-Bing 《大气和海洋科学快报》2014,(5):377-381

In this study, the authors developed an en- semble of Elman neural networks to forecast the spatial and temporal distribution of fossil-fuel emissions （ff） in 2009. The authors built and trained 29 Elman neural net- works based on the monthly average grid emission data （1979-2008） from different geographical regions. A three-dimensional global chemical transport model, God- dard Earth Observing System （GEOS）-Chem, was applied to verify the effectiveness of the networks. The results showed that the networks captured the annual increasing trend and interannual variation of ff well. The difference between the simulations with the original and predicted ff ranged from -1 ppmv to 1 ppmv globally. Meanwhile, the authors evaluated the observed and simulated north-south gradient of the atmospheric CO2 concentrations near the surface. The two simulated gradients appeared to have a similar changing pattern to the observations, with a slightly higher background CO2 concentration, - 1 ppmv. The results indicate that the Elman neural network is a useful tool for better understanding the spatial and tem- poral distribution of the atmospheric C02 concentration and ft.  相似文献   

基于遗传小波神经网络的海底声学底质识别分类   总被引：4，自引：3，他引：1  

熊明宽  吴自银  李守军  尚继宏 《海洋学报》2014,36(5):90-97

分割海底声纳探测图像,提取单元特征向量进行主成份分析,选取均值、标准差、对比度、相关系数、能量及同质性作为训练特征向量,构建小波神经网络。利用遗传算法优化小波神经网络的初始权值及小波参数,对砂、礁石、泥3种底质类型分别进行训练,并得到3种底质的测试精度都在90%以上,优于单独利用小波神经网络进行训练时的测试精度,克服了小波神经网络训练时易陷入局部极小的固有缺陷,表明基于遗传算法的小波神经网络可有效用于海底底质声纳图像的识别和分类。  相似文献