一种全自动提取居民地的方法     

王明孝  翟辉琴  马淑宇 《地理空间信息》2008,6(1):22-25

对遥感影像中居民地提取的各种方法作了一般性的阐述,并在吸收这些算法优势的同时,提出了一种全自动实现遥感影像中居民地目标的提取方法：先求取非最大值抑制后的梯度图,而后进行高斯模糊处理,以提高影像上居民地区域纹理特征一致性;通过增强大津法和形态学的方法全方位腐蚀与膨胀,完成面状地物居民地的提取;最后进行图象矢量化处理。论述方法的同时,展示和分析了实验结果。  相似文献   

Automatic classification of volcanic earthquakes by using Multi-Layered neural networks     

S. Falsaperla  S. Graziani  G. Nunnari  S. Spampinato 《Natural Hazards》1996,13(3):205-228

The application of neural networks as classifiers of seismic events is described with the aim of developing an automatic system for the classification of explosion quakes at the Stromboli volcano. The architecture of the network that we trained to identify four different classes of shocks was a Multi-Layer Perceptron, using the Back Error Propagation algorithm. Five different approaches for representing the information embedded in the seismograms, both in the time and in the frequency domain, were considered, and the results compared. The direct use of the time series of the shocks was not satisfactory. The auto-correlation function worked well, but in some cases it was misleading. A better performance was obtained with a frequency domain representation. Finally, the use of the envelope function did not work well. Combining parameters such as the auto-correlation and envelope functions can improve one source of error, but it may introduce new ones. The performance obtained highlights the importance of the data attributes used for the training of the network. Topologies with eight neurons in a single hidden layer gave, on average, the best results among the considered neural network structures. The overall results provide a large number of events (89% with the best performance) correctly classified, indicating that this automatic technique is reliable, and encouraging further applications in the field of volcanic seismology.  相似文献   

华北地台晚古生代含煤地层多重划分   总被引：11，自引：0，他引：11  

汪曾荫  刘汉男 《华北地质矿产杂志》1996,11(1):9-23

以６０个大体均匀分布于华北地台的地层剖面为基础,以晚古生代聚煤盆地的整体性为依托,对华北晚古生代地层进行多重划分研究,在岩石地层方面,研究了地层分区、划分了１８个岩石地层单位“组”,分析了组的穿时性,在生物地层方面,重点介绍了蜒、古植物和孢粉生物地层,划分了各个组合带、延限带和顶峰带,分析了生物演化系列,空间展布和对比,提出了多方面的新认识,在年代地层方面,应用界线层型概念以及与首要门类生物地层单  相似文献   

Overbreak and underbreak in underground openings Part 2: causes and implications   总被引：7，自引：0，他引：7  

J. A. Ibarra  N. H. Maerz  J. A. Franklin 《Geotechnical and Geological Engineering》1996,14(4):325-340

Summary The newly developed light sectioning method has been used to investigate some of the causes and costs of overbreak and underbreak. Investigations at the Aquamilpa Hydroelectric Project in Mexico have shown decreased overbreak and increased underbreak as a result of increased rock quality and decreased explosive energy. A new measure of explosive energy, the perimeter powder factor (PPF), has been defined and shown to be useful in the context of tunnel-wall rock damage. Tentative results indicate that explosive energy (PPF) may be a more important factor in producing underbreak, whereas rock quality may be a greater factor in producing overbreak. A site-specific equation is given for predicting overbreak or underbreak as a function of rock quality and explosive energy, with an evaluation of the cost of underbreak and overbreak.  相似文献   

基于FPN Res-Unet的高分辨率遥感影像建筑物变化检测     

王明常  朱春宇  陈学业  王凤艳  李婷婷  张海明  韩有文 《吉林大学学报(地球科学版)》2021,51(1):296-306

针对城市土地资源变化检测工作繁杂、工作量大、自动化程度低等问题，本文提出一种基于深度学习模型的高分辨率遥感影像建筑物变化检测方法，将语义分割的思想引入到遥感变化检测。基于残差结构特征较卷积层提取性能更优和特征金字塔网络多尺度预测的特点，将残差结构和特征金字塔网络融合到Unet模型中，建立FPN Res-Unet模型。该模型以Unet为基础，引入ResNet18的残差结构作为编码路径特征提取层，在每次卷积后使用边界填充，使得输入图像和输出图像尺寸一致；在解码路径每级上采样过程中，拓展支路径将特征金字塔网络融合到模型的网络主干中，将残差结构、Unet及特征金字塔网络的优点相互融合，增强了Unet的特征提取，弥补了语义分割网络对小目标检测的欠缺；在获取深层语义信息的同时关注细节信息，提高建筑物变化检测精度。实验表明，该方法在所用数据集，准确率、召回率、F₁ 3种指标均达到90%以上。  相似文献   

Grain size and grain shape analysis of fault rocks   总被引：4，自引：0，他引：4  

Rene Heilbronner  Nynke Keulen 《Tectonophysics》2006,427(1-4):199

  相似文献   

Engineering geological studies and tunnel support design at Sulakyurt dam site, Turkey   总被引：2，自引：0，他引：2  

H. Basarir 《Engineering Geology》2006,86(4):225-237

This paper presents the results of engineering geological investigations and tunnel support design studies, carried out at the Sulakyurt dam site, northeast of Ankara, Turkey. The Sulakyurt dam will be used for flow control and water storage for irrigation projects. Studies were carried out both in the field and the laboratory. Field studies include engineering geological mapping, intensive discontinuity surveying, core drilling and sampling for laboratory testing. The diversion tunnel will be driven in rock mass, consisting of granite and diorite. Empirical, analytical and numerical methods were combined for safe tunnel design. Rock mass rating (RMR), Rock mass quality (Q) and Geological strength index (GSI) systems were used for empirical rock mass quality determination, site characterization and support design. The convergence–confinement method was used as analytical method and software called Phase², a 2D finite element program, was utilized as numerical method. According to the results acquired from the empirical, analytical and numerical methods, tunnel stability problems were expected in both granite and diorite rock masses. The support system, suggested by empirical methods, was applied and the performance of suggested support system was evaluated by means of numerical modelling. It was concluded that the suggested support systems were adequate, since after applying the suggested support system to granite and diorite, tunnel deformation and the yielded elements around the tunnel decreased significantly. Thus, it is suggested that for more reliable support design empirical, numerical and analytical methods should be combined.  相似文献   

Modeling of the classification behavior of the diaphragms used in multi-chamber cement mills     

C.E. Özer  S¸.L. ErgünA.H. Benzer 《International Journal of Mineral Processing》2006

A new approach has been developed for describing the classification that arises at the diaphragm in multi-chamber ball mills. Fourteen industrial scale cement mills have been sampled in this study and after mass balancing, model fits of the equipment were done. Successive mill product predictions for the sampled conditions were achieved, and requirements to build up an optimization capable model are discussed.  相似文献   

GIS技术支持下的招远市金矿区崩塌遥感调查     

吴泉源  姜春玲  邹敏  杨圣军  张祖陆 《山地学报》2006,24(6):672-677

在总结前人研究成果的基础上,全面系统地分析了诱发招远市金矿区崩塌的自然和人为因数,然后运用遥感技术对金矿区遥感图像进行处理,提取诱发崩塌的条件因子,聘请有经验的专家对各项诱发因子进行诊断分析,以此作为判断条件,在G IS技术的支持下对诱发崩塌的条件因子进行空间分析,预测出招远金矿区发生崩塌的危害程度,为防治崩塌提供科学依据。预测结果表明,招远金矿区崩塌有进一步发展的可能,其中,高危险区有36820 m2,中易发区有50 610 m2,低易发区有67 200 m2,需要采取有效措施加以防治。  相似文献   

1993～2003年厦门市湿地动态变化及其驱动因素分析   总被引：1，自引：3，他引：1  

林巧莺  林广发  陈志鸿  杨陈照  游丽平 《湿地科学》2006,4(4):298-303

通过对厦门市1993年TM遥感影像和2003年ETM 遥感影像的解译分析和数据统计,从湿地面积动态变化和湿地消长情况等方面,用单一土地利用动态度等指标对1993~2003年期间厦门市的湿地变化进行了研究。结果表明,1993~2003年期间厦门市天然湿地面积减少了2103hm2,其中有954hm2(滩涂864hm2)转变为非湿地,有1149hm2转变为人工湿地;而人工湿地面积增加了2775hm2,其中养殖场面积从1993年的5778hm2迅猛增加到2003年的9768hm2,年均增长率为6.91%,水库与水塘和盐田则分别减少了961hm2和254hm2。有27.74%、11.41%、9.33%和3.63%的养殖场面积分别是由非湿地、滩涂、盐田和水库与水塘转变而来的;有54.37%的盐田转变成了养殖场,有33.24%、30.24%的红树林转变为非湿地、养殖场,有10.35%、8.64%的滩涂转变为养殖场、非湿地。对社会经济驱动因素的分析表明,经济发展、人口增长和农业生产比较利益因素极大影响着厦门市湿地的动态变化。  相似文献