下载频道  >  Dan510275的资源
  • 校园典型建筑物点云数据三维建模方法

    随着数字化测量的发展,三维激光扫描仪能够快速地以多角度、高效、高精度方式获取物体的表面三维数据,可以用于校园典型建筑物的三维建模。以云南师范大学呈贡校区内的国立西南联合大学纪念碑和国立昆明师范学院纪念柱为典型建筑物三维建模对象,首先采用徕卡P40三维激光扫描仪采集它的三维点云信息,然后利用Cyclone软件对多站式点云数据进行拼接、统一化和去燥,将处理后的点云数据导入Geomagic Studio软件,对其进行封装、孔洞填充、平滑等相关处理,构建其三维模型并对模型进行纹理映射,最终完成校园典型建筑物点云数据的三维模型构建。该三维建模流程方法对校园典型建筑物的三维建模可取得较好的效果。

    2020-03-24
    2
  • 基于改进特征点对选取的三维点云配准

    针对同一物体不同视角下获得的三维点云数据,提出一种基于改进特征点对选取的三维点云配准方法。在欧氏距离的基础上选取与目标点最近的三点均值为对应点,并应用邻域比值法来剔除错误点,结合K-d tree 提高搜索速度,实现最终点云配准。实验结果表明,该方法具有可行性,相比传统ICP 算法,其匹配精度和效率明显提升。

    2020-03-24
    9
  • 基于生态环境遥感解译的石河子市水资源优化配置研究

    水资源是维持一个地区经济社会发展和生态安全的重要因素,尤其对西部干旱半干旱区发展格局的构建、经济的高速提升、生态环境的可持续的作用更加凸显。通过以石河子市为例,利用遥感图像对不同生态系统的解译,采用面积定额法和生态系统单位面积当量估算法,对石河子市各种生态系统进行生态需水量计算和生态服务价值估算,并进一步与该市社会经济生产需水量和生产价值进行对比分析发现,石河子市的耕地在各生态系统类型中,所占比重最大、生态需水最多; 生态环境实际补水量,不足以维持本地区生态环境可持续; 在生态可持续性优先的背景下,需积极调整产业布局,优化水资源的配置,切实提高水资源利用效率

    2020-03-20
    8
  • 基于形态学色差的彩色遥感影像水域提取

    基于形态学变换的遥感图像分类提取技术在影像识别中得到了广泛应用, 也取得了令人满意的效果。但在处理多光谱、高光谱影像中, 由于较少考虑色差信息而使分类识别受到限制。本文在分析形态学算子特点的基础上, 提出了基于形态学变换色差的水域特征提取策略。实验表明, 该算法具有明显的优越性和较强的适应性。

    2020-03-20
    5
  • 基于PUL算法及高分辨率WorldView影像的城市不透水面提取

    准确提取城市不透水面对生态环境、水热循环及热岛效应等研究具有重要意义。该文利用WorldView高分辨遥感影像,提出基于PUL(Positive and Unlabeled Learning)算法的高分辨率影像城市不透水面提取方法,该方法不需要负样本数据,只需少量的正样本和未标记样本即可训练分类模型。结果显示,PUL算法的提取结果优于一类支持向量机(OCSVM)以及最大熵(MAXENT)模型。使用不同正样本量时,PUL的提取结果总体精度和kappa系数均优于OCSVM 和MAXENT,最高总体精度为91.27%,最高kappa系数可达0.8255,可快速、有效地从高分辨率遥感影像中提取不透水面。

    2020-03-20
    9
  • Eye feature point detection based on single convolutional neural network

    Feature point detection based on convolutional neural network (CNN) has been studied widely. The effective approaches for improving detection accuracy are building a deeper network or using a multi-network cascade structure. However, some potential capacity of CNN has not been excavated. In this study, the authors mainly analyse several factors influencing CNN performance from two aspects: (i) the position relationships between feature points and (ii) the normalisation methods of coordinates. Whether the network can learn the position relationships is also studied. For extracting the deep Abstract: Feature point detection based on convolutional neural network (CNN) has been studied widely. The effective approaches for improving detection accuracy are building a deeper network or using a multi-network cascade structure. However, some potential capacity of CNN has not been excavated. In this study, the authors mainly analyse several factors influencing CNN performance from two aspects: (i) the position relationships between feature points and (ii) the normalisation methods of coordinates. Whether the network can learn the position relationships is also studied. For extracting the deep features of images, a network containing three convolution layers is constructed. The specific geometric relationship constraints are applied during calibration to maximise the capability of the CNN for learning the position relationship between feature points. Considering that different feature points only appear in various local regions of an image, local normalisation is proposed, which increases the mapping scope of the feature points and decreases the mapping error. The experimental results prove that the specific position relationship and local normalisation obviously improve the feature point detection based on CNN. At the detection error of 5%, the average detection accuracy of eyelid feature points is improved by 7.1% and single-point detection receives a high accuracy of 97.96% features of images, a network containing three convolution layers is constructed. The specific geometric relationship constraints are applied during calibration to maximise the capability of the CNN for learning the position relationship between feature points. Considering that different feature points only appear in various local regions of an image, local normalisation is proposed, which increases the mapping scope of the feature points and decreases the mapping error. The experimental results prove that the specific position relationship and local normalisation obviously improve the feature point detection based on CNN. At the detection error of 5%, the average detection accuracy of eyelid feature points is improved by 7.1% and single-point detection receives a high accuracy of 97.96%

    2020-03-20
    6
  • 基于深度学习的高分辨率遥感影像目标检测

    传统的目标检测识别方法难以适应海量高分辨率遥感影像数据,需要寻求一种能够自动从海量影像数据中学习最有效特征的方法,充分复挖掘数据之间的关联。本文针对海量高分辨率遥感影像数据下典型目标的检测识别,提出一种分层的深度学习模型,通过设定特定意义的分层方法建立目标语义表征及上下文约束表征,以实现高精度目标检测。通过对高分遥感影像目标检测的试验,证明了该方法的有效性。

    2020-03-20
    30
  • 面向对象的那曲WorldView_2影像的分类

    摘要:随着WorldView-2卫星的发射,首次出现了8波段多光谱高分辨率商业卫星。高分辨率影像包含丰富的空间结构信息和地理特征信息,采用传统的基于像元的影像分析方法精度明显达不到要求。为了提高精度,本文以西藏那曲为研究区,利用面向对象的方法对那曲的WorldView-2影像进行分类,采用模糊分类法,利用所分地物的特征确定类别,针对西部地区干旱河流的特殊情况,提出了一种基于地物空间轮廓特征的分类方法,分类结果较好。

    2020-03-20
    6
  • 基于四元数的多光谱遥感影像水域提取

    特征提取是影像目标分类识别的重要步骤。通过研究四元数在多光谱遥感影像处理中应用的优势, 提出了一种基于四元数的多光谱遥感影像水域提取的算法。该算法把多光谱遥感影像的所有波段作为一个整体考虑, 充分利用了光谱信息, 同时也减少了计算量。实验表明, 该算法具有明显的优越性和适应性。

    2020-03-20
    5
  • 遥感信息在海洋水文上的应用简介

    近年来遥感技术在海洋上的应用得到较快的发展, 尤其对同步宏观的观察海洋各种信息, 使它占更重要地位。作为“E O P A P” 的一部分(地球海洋物理应用规划) , 美国在1 9 78 年6 月26 日专门为研究海洋发射的海洋卫星一“ S ae s a t 一A ” , 在当今还是领先。海洋卫星S c a s at 一A 每天观测面积为12 x t o 7 K m Z , 1 52 天将地球观测一遍, 装有四部为微波, 三部属主动式, 合成孔径雷达等传感器。但运行到1 05 天, 因技术故障而停止工作。海洋卫星取得的资料, 将对海洋水文、 气象、海洋工程、海洋环境等的研究有重要意义。

    2020-03-20
    6
img
dan510275

关注 私信