期刊文献+
共找到5篇文章
< 1 >
每页显示 20 50 100
结合显著性检测和超像素分割的遥感信息提取算法研究 被引量:3
1
作者 闫琦 李慧 +2 位作者 荆林海 唐韵玮 丁海峰 《计算机应用研究》 CSCD 北大核心 2018年第7期2207-2210,2218,共5页
针对目前显著性检测算法在复杂多目标遥感图像中检测能力不足的问题,提出一种结合显著性检测和超像素分割的遥感信息提取算法。该算法通过GBVS(graph-based visual saliency)方法检测出原始影像中部分显著性较高的区域,然后利用SLIC(sim... 针对目前显著性检测算法在复杂多目标遥感图像中检测能力不足的问题,提出一种结合显著性检测和超像素分割的遥感信息提取算法。该算法通过GBVS(graph-based visual saliency)方法检测出原始影像中部分显著性较高的区域,然后利用SLIC(simple linear iterative clustering)方法分割显著区域,并修正显著区域边缘得到训练样本数据,进一步对训练样本进行统计学习,构造显著目标提取的阈值区间,最后实现对整幅超像素图像的显著目标提取。实验结果表明,该算法具有较高的准确率和召回率,能更加有效地检测出遥感图像中的显著目标,比目前主流的显著区域检测算法提取效果更好,可以很好地应用于具有明显显著区域的复杂多目标遥感图像信息提取中。 展开更多
关键词 遥感信息提取 GBVS显著性检测 SLIC超像素分割 训练样本 统计学习
下载PDF
Research on the different content of weathered sand influence on expansive characteristic of a highway expansive soil in Yichang 被引量:1
2
作者 Yang Jun Li Xinchun +2 位作者 Zhang Guodong tang yunwei Xie Zhigang 《Engineering Sciences》 EI 2013年第5期84-90,共7页
This paper aims at widespread presence of expansive soil which can be obtained in the project from Xiaoxita to Yaqueling first-class highway rebuilding engineering in Yichang City of Hubei Province and weathered sand ... This paper aims at widespread presence of expansive soil which can be obtained in the project from Xiaoxita to Yaqueling first-class highway rebuilding engineering in Yichang City of Hubei Province and weathered sand which can be made full use locally,many experiments have been made. Compaction experiments and expansibility index indoor experiments of undisturbed expansive soil and expansive soil mixed with sand ranging from 10 % to 50 % have been made. Through the test mixing undisturbed expansive soil with different content of weathered sand,it can change the expansive soil water characteristics and compaction characteristics. It can influence the expansibility of the expansive soil index and significantly inhibit the expansibility of the expansive soil and reach the standard of roadbed filler. 展开更多
关键词 膨胀特性 膨胀土 风化砂 宜昌市 高速公路 公路改建工程 室内实验 可扩展性
下载PDF
Experimental research on the mixed sand ratio and initial dry density of weathered sand improved expansive soil free load swelling rate
3
作者 Yang Jun Yang Zhi +2 位作者 Zhang Guodong tang yunwei Chen Hongping 《Engineering Sciences》 EI 2014年第3期77-82,共6页
In this paper, through the indoor free load swelling rate test, expansive soil in a section of a first- class highway reconstruction project in Yichang City was studied. It emphatically analyzed the interrelations amo... In this paper, through the indoor free load swelling rate test, expansive soil in a section of a first- class highway reconstruction project in Yichang City was studied. It emphatically analyzed the interrelations among free load swelling rate, non-load time, the proportion of mixed sand and initial dry density. Experimen- tal studies have shown that: Free load swelling deformation is mainly divided into three stages of rapid expan- sion, slow expansion and final stability; when the initial dry density is constant, free load swelling rate of the weathered sand modified soil will reduce rapidly before they slow down with the increase of sand proportion, and weathered sand modified soil free load swelling rate is not sensitive to the large amount of sand mixed; in the same mixed sand ratio, weathered sand modified soil free load swelling rate increases rapidly with the in- crease of initial dry density, there is a good linear correlation between them. To take appropriate control of the initial dry density during the expansive soil subgrade construction helps to reduce its swelling deformation and ensures the stability of the embankment. 展开更多
关键词 expansive soil weathered SAND INITIAL DRY density MIXING SAND ratio free LOAD SWELLING rate
下载PDF
基于卷积神经网络的高分遥感影像单木树种分类 被引量:7
4
作者 欧阳光 荆林海 +3 位作者 阎世杰 李慧 唐韵玮 谭炳香 《激光与光电子学进展》 CSCD 北大核心 2021年第2期341-354,共14页
树种调查一直面临着成本高、效率低、精度不高等问题。利用遥感手段能大大提高树种类型调查的工作效率、节省成本;卷积神经网络(CNN)虽然已经在自然图像分类领域取得了许多突破,但是较少有人将CNN模型用于单木树种分类。基于上述考虑,... 树种调查一直面临着成本高、效率低、精度不高等问题。利用遥感手段能大大提高树种类型调查的工作效率、节省成本;卷积神经网络(CNN)虽然已经在自然图像分类领域取得了许多突破,但是较少有人将CNN模型用于单木树种分类。基于上述考虑,搭建出CNN模型,并与高分遥感影像相结合,进行单木树种分类。在利用高分影像半自动化构建单木树种遥感影像样本集过程中,采用了影像冠层切片(CSI)圈定、人工标注、数据增强等方法;同时为了训练单木树种遥感影像样本集,对5个CNN模型进行针对性改写。通过对比分析发现:LeNet5_relu和AlexNet_mini都未取得最佳分类效果;GoogLeNet_mini56、ResNet_mini56和DenseNet_BC_mini56分别对不同的树种具有最佳分类效果;DenseNet_BC_mini56总体精度最高(94.14%),Kappa系数最高(0.90),是总体最佳分类模型。该研究证明了CNN在单木树种分类中的有效性,能为森林资源调查提供重要的解决方案。 展开更多
关键词 图像处理 单木树种分类 卷积神经网络 高分遥感影像 深度学习
原文传递
Misclassification error propagation in land cover change categorization
5
作者 ZHANG Jingxiong tang yunwei 《Geo-Spatial Information Science》 SCIE EI 2012年第3期171-175,共5页
It is important to describe misclassification errors in land cover maps and to quantify their propagation through geo-processing to resultant information products,such as land cover change maps.Geostatistical simulati... It is important to describe misclassification errors in land cover maps and to quantify their propagation through geo-processing to resultant information products,such as land cover change maps.Geostatistical simulation is widely used in error modeling,as it can generate equal-probable realizations of the fields being considered,which can be summarized to facilitate error propagation analysis.To fix noninvariance in indicator simulation,discriminant space-based methods were proposed to enhance consistency in area-class mapping and replicability in uncertainty modeling,as the former is achieved by imposing means while the latter is ensured by projecting spatio-temporal correlated residuals in discriminant space to geographic space through a mapping process.This paper explores discriminant models for error propagation in land cover change detection,followed by experiments based on bi-temporal remote sensing images.It was found that misclassification error propagation is effectively characterized with discriminant covariate-based stochastic simulation,where spatio-temporal interdependence is taken into account. 展开更多
关键词 error propagation area-class maps land cover change discriminant space data class information class stochastic simulation
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部