An improved segmentation approach for planar surfaces from unstructured 3D point clouds     

Tarek M.  Awwad  Qing  Zhu  Zhiqiang  Du  Yeting  Zhang 《The Photogrammetric Record》2010,25(129):5-23

The extraction of object features from massive unstructured point clouds with different local densities, especially in the presence of random noisy points, is not a trivial task even if that feature is a planar surface. Segmentation is the most important step in the feature extraction process. In practice, most segmentation approaches use geometrical information to segment the 3D point cloud. The features generally include the position of each point (X, Y and Z), locally estimated surface normals and residuals of best fitting surfaces; however, these features could be affected by noisy points and in consequence directly affect the segmentation results. Therefore, massive unstructured and noisy point clouds also lead to bad segmentation (over-segmentation, under-segmentation or no segmentation). While the RANSAC (random sample consensus) algorithm is effective in the presence of noise and outliers, it has two significant disadvantages, namely, its efficiency and the fact that the plane detected by RANSAC may not necessarily belong to the same object surface; that is, spurious surfaces may appear, especially in the case of parallel-gradual planar surfaces such as stairs. The innovative idea proposed in this paper is a modification for the RANSAC algorithm called Seq-NV-RANSAC. This algorithm checks the normal vector (NV) between the existing point clouds and the hypothesised RANSAC plane, which is created by three random points, under an intuitive threshold value. After extracting the first plane, this process is repeated sequentially (Seq) and automatically, until no planar surfaces can be extracted from the remaining points under the existing threshold value. This prevents the extraction of spurious surfaces, brings an improvement in quality to the computed attributes and increases the degree of automation of surface extraction. Thus the best fit is achieved for the real existing surfaces.  相似文献   

Prerift and synrift sedimentation during early fault segmentation of a Tertiary carbonate platform, Indonesia     

Moyra E. J. Wilson   《Marine and Petroleum Geology》1999,16(8):262

Eocene carbonate deposits of the Barru area, Sulawesi, Indonesia, provide a rare insight into sedimentation prior to and during propagation of normal faults to the surface. Three main successions; late prerift, latest prerift/earliest synrift and synrift, are characterised by distinctive facies associations and sequence development. Shallow water foraminiferal shoals and intervening lower energy depositional environments occurred during the late prerift in areas which latter formed footwall highs and hangingwall depocentres, respectively. During the latest prerift/earliest synrift, shallow water shelves deepened laterally into slope environments in developing hangingwall depocentres. In both these sequences, sections in developing hangingwall areas are thickest, deepen up-section and thin laterally towards growing footwall highs. Active faulting resulted in rapid drowning of hangingwall depocentres and massive reworking of material derived from collapse of the platform margin and adjacent shallow water/emergent footwall highs.Differential subsidence, controlling water depths and accommodation space, types of carbonate producers and active faulting were the main factors affecting depositional environments and facies distributions. Carbonate producers are extremely sensitive indicators of depositional water depth and energy, hence rapid lateral and vertical facies variations in the Barru area provide quantifiable insight into environmental changes prior to and during active faulting.  相似文献   

面向对象的高分辨率影像城市建筑物提取   总被引：9，自引：1，他引：8  

乔程  骆剑承  吴泉源  沈占锋  王宏 《地理与地理信息科学》2008,24(5)

依据高分辨率遥感影像的特点,采用面向对象方法提出"自下而上"的多尺度分割方法,即按照由小尺度分割至大尺度分割的顺序,并结合掩膜操作对山东师范大学IKONOS影像进行了建筑物提取试验。结果表明,该方法较传统的"自上而下"的尺度分割方法精度有显著改善,其分类结果形状较为规整,更接近实际地物。  相似文献   

Ӧ��360��ȫ��Ӱ����������ⷽ��     

王海江  吴秀芸 《大地测量与地球动力学》2012,32(6):144-147

???360???????????????????????????????????????????????·???????????в???????????????????????YCbCr???????????????????????????????????????????Ч??????????????????????????????????????????????????????????????????????????????????Ч?????????????????÷????????360?????????е??????????????????????????????????????????????Ч?????????á?  相似文献   

市场分割与中国城市出口差异   总被引：3，自引：1，他引：2  

贺灿飞  马妍 《地理科学进展》2014,33(4):447-456

出口贸易是中国经济增长的引擎,也是影响城市经济发展的重要因素。中国城市出口活动强度呈现由东向西逐渐递减的趋势,东部沿海地区的城市群表现最为优异。经济转型背景下地方政府采取的市场分割政策对中国城市出口差异有显著影响。基于新经济地理理论,在企业微观层面使用Heckman选择模型分析的结果表明：① 短期内,国内市场分割程度加剧导致企业因国内市场受限而替代性地进入国际市场以追求规模经济效益,从而通过增加出口企业数量提升城市出口表现;长期来看,市场分割限制了企业的规模经济效益和专业化分工能力,降低了出口企业的生产率和国际竞争力,从而损害城市出口贸易的可持续发展;这一机制还受到企业所有制及地理区位的影响。② 市场分割对企业出口行为的扭曲程度依外资企业、国有企业、私营企业的顺序递增。③ 在中国中部地区,改善省际交通条件有助于缓解国内市场分割对企业出口行为的扭曲作用,在东部和西部地区则不明显。  相似文献   

面向对象的多特征分级CVA遥感影像变化检测   总被引：1，自引：0，他引：1  

赵敏  赵银娣 《遥感学报》2018,22(1):119-131

变化矢量分析CVA方法在中低分辨率遥感影像变化检测中已得到广泛应用,但由于高分辨率遥感影像存在不同地物尺度差异大、不同类别地物光谱相互重叠的问题,因此对于高分影像的变化检测具有局限性。为提高高分影像变化检测精度,提出了一种面向对象的多特征分级CVA变化检测方法,首先,利用基于区域邻接图的影像分割方法分别对两时相遥感影像进行多尺度分割,提取分割图斑的光谱、纹理和形状特征;然后,在各级尺度下,分别运用随机森林方法进行特征选择,计算CVA变化强度图;最后,根据信息熵对多级变化强度图进行自适应融合,利用Otsu阈值法检测变化区域,并与仅考虑光谱特征的分级CVA变化检测方法、像元级多特征CVA变化检测方法以及仅考虑光谱特征的像元级CVA变化检测方法进行比较分析。实验表明:与比较方法相比,本文方法的变化检测精度较高,误检率和漏检率较低。  相似文献   

基于图像分割的煤岩割理CT图像各向异性特征     

赵海燕  宫伟力 《煤田地质与勘探》2009,37(6):14-18

利用工业CT对自然煤岩样进行断层扫描观测。针对煤岩裂隙系统的多尺度、各向异性特征,应用Canny算子图像分割与方向性边缘检测技术,提取煤岩CT图像割理的总体特征、水平方向和垂直方向特征;根据特征图像计算了煤岩样的总体分形维数、孔隙度,各向异性分形维数与孔隙度及其在三维空间中的分布;讨论了分形维数与孔隙度、渗透率之间的关系,并根据煤岩样的分形维数、孔隙度对实际工程岩体的孔隙度和渗透率进行了外推计算。研究表明,煤岩样不同扫描断面的分形维数和孔隙度不同,同一煤样同一断面不同方向的分形维数与孔隙度亦不相同。利用图像分割与边缘检测对工业CT图像进行分析,可以对煤岩的各向异性分形维数与孔隙度在2D与3D空间进行精细描述。   相似文献   

基于Mean-shift影像分割算法的TM影像分类及城市扩展研究     

史晓霞  李京  周冠华  赵静 《地理与地理信息科学》2009,25(1)

以马来西亚雪兰莪州及首都吉隆坡为例,将Mean-shift算法的影像分割方法应用于研究区的TM影像分类中,较传统方法的分类精度更高,可满足应用需求.依据该分类结果对研究区的空间城市化特征进行分析.发现近期研究区一直处于高速扩展阶段,外延式扩展和填充式扩展并行发展成为该研究区城市扩展的主导模式.  相似文献   

交通地理信息系统中的时空动态分段模型研究          下载免费PDF全文

董传胜  郑伟安  凌晓春  张拥军  钟全宝  孟大鹏  张金营 《山东国土资源》2017,33(5)

动态分段技术是交通地理信息系统(GIS-T)中一项重要的线性要素动态显示与分析技术,该文提出了一种时空动态分段模型,使动态分段系统的组成成分融入时态因素,并将属性的时态信息作为属性信息表的字段存储,通过时态地理信息系统技术完成物理段的时态变化。利用统一建模语言(UML)的类图设计方式开发了物理模型,描述了时空动态分段模型中对象之间的关系,并定义了必要的属性和操作;同时基于线性参照系统(LRS)表达空间实体的方法,概括了模型中所涉及到的主要拓扑关系。实验表明,时空动态分段模型弥补其他模型将时空参考分为时间参考和空间参考所产生的不足,而且更明确地将多重属性和物理实体有机结合起来。  相似文献   

一种稀疏降噪自编码神经网络影像变化检测方法     

王斌  罗莉  刘金沧  黄小川  雷雳 《测绘与空间地理信息》2022,45(1):40-44

采用粤西2018—2019年优于0.5 m地理国情监测影像,结合2018年矢量化地表覆盖分类成果,使用稀疏降噪自编码神经网络深度学习方法,首先选取BJ、GF、ZY等各类高分辨率遥感影像训练生成多传感器训练模型;其次利用PCA主成分分析提取样本数据最大特征,实现样本数据白化降维;最后采用tanh函数作为神经元激活函数,选...  相似文献