共查询到20条相似文献，搜索用时 281 毫秒
1.
Full-waveform topographic LiDAR data provide more detailed information about objects along the path of a laser pulse than discrete-return (echo) topographic LiDAR data. Full-waveform topographic LiDAR data consist of a succession of cross-section profiles of landscapes and each waveform can be decomposed into a sum of echoes. The echo number reveals critical information in classifying land cover types. Most land covers contain one echo, whereas topographic LiDAR data in trees and roof edges contained multi-echo waveform features. To identify land-cover types, waveform-based classifier was integrated single-echo and multi-echo classifiers for point cloud classification.The experimental area was the Namasha district of Southern Taiwan, and the land-cover objects were categorized as roads, trees (canopy), grass (grass and crop), bare (bare ground), and buildings (buildings and roof edges). Waveform features were analyzed with respect to the single- and multi-echo laser-path samples, and the critical waveform features were selected according to the Bhattacharyya distance. Next, waveform-based classifiers were performed using support vector machine (SVM) with the local, spatial features of waveform topographic LiDAR information, and optical image information. Results showed that by using fused waveform and optical information, the waveform-based classifiers achieved the highest overall accuracy in identifying land-cover point clouds among the models, especially when compared to an echo-based classifier. 相似文献
2.
激光雷达技术(LiDAR)已广泛应用于数字高程模型(DEM)的快速获取和三维城市模型的建立中,但仍有许多不足之处,需要做更深入的研究。本文介绍了一种新的建筑物提取方法,称之为Fc-S法。该方法首先利用等高线特征进行滤波,从LIDAR数据内插的数字表面模型(DSM)中提取出DEM,利用DSM与DEM的高差阈值和DSM边缘特征参数去掉地面点和汽车等矮小物体,获得主要包含植被和建筑物的地物点群,然后对地物点群进行分割,利用二次梯度和面积等参数去掉植被点,并采用迭代逼近的方法精化建筑物。文章通过实验对所提方法进行验证,并借助高分辨率的航空影像对建筑物提取结果进行评估,评估结果表明该方法能够在地形起伏的区域中较准确地提取出建筑物。 相似文献
3.
A. Mohan Vamsee P. Kamala Tapas R. Martha K. Vinod Kumar G. Jai sankar E. Amminedu 《Journal of the Indian Society of Remote Sensing》2018,46(1):31-41
Image segmentation to create representative objects by region growing image segmentation techniques such as multi resolution segmentation (MRS) is mostly done through interactive selection of scale parameters and is still a subject of great research interest in object-based image analysis. In this study, we developed an optimum scale parameter selector (OSPS) tool for objective determination of multiple optimal scales in an image by MRS using eCognition software. The ready to use OSPS tool consists of three modules and determines optimum scales in an image by combining intrasegment variance and intersegment spatial autocorrelation. The tool was tested using WorldView-2 and Resourcesat-2 LISS-IV Mx images having different spectral and spatial resolutions in two areas to find optimal objects for ground features such as water bodies, trees, buildings, road, agricultural fields and landslides. Quality of the objects created for these features using scale parameters obtained from the OSPS tool was evaluated quantitatively using segmentation goodness metrics. Results show that OSPS tool is able determine optimum scale parameters for creation of representative objects from high resolution satellite images by MRS method. 相似文献
4.
Airborne LiDAR has found application in an increasing number of mapping and Geo-data acquisition tasks. Apart from terrain
information generation, applications such as automatic detection and modeling of objects like buildings or vegetation for
the generation of 3-D city models have been explored. Besides the height itself, height texture defined by local variations
of the height is a significant parameter for object recognition. The paper explores the potential of the analysis of height
texture as a cue for the automatic detection of objects in LiDAR datasets. A number of texture measures were computed. Based
on their definition and computation these measures were used as bands in a classification algorithm, and objects like buildings,
single trees, and roads could be recognized. 相似文献
5.
激光雷达森林参数反演研究进展 总被引：6，自引：0，他引：6
激光雷达通过发射激光能量和接收返回信号的方式,来获取高精度的森林空间结构和林下地形信息。全波形激光雷达通过记录返回信号的全部能量,得到亚米级植被垂直剖面;离散回波激光雷达记录的单个或多个回波,表示来自不同冠层的回波信号。星载激光雷达一般采用全波形或光子计数激光剖面系统,仅能获取卫星轨道下方的单波束或多波束数据,用于区域/全球范围的森林垂直结构及变化观测。机载激光雷达多采用离散回波或全波形激光扫描系统,能够获取飞行轨迹下方特定视场范围内的扫描数据,用于林分/区域范围的森林结构观测。地基激光雷达多采用离散回波激光扫描系统,获取以测站为中心的球形空间内扫描数据,用于单木/样地范围的森林结构观测。激光雷达单木因子估测方法可分为CHM单木法、NPC单木法和体元单木法3类。CHM单木法通过局部最大值识别树冠顶点,采用区域生长或图像分割算法识别树冠边界或树冠主方向,NPC单木法一般通过空间聚类或形态学算法识别单木,体元单木法在3维体元空间采用区域生长或空间聚类算法识别树冠。根据激光雷达冠层高度分布可以估测林分因子,冠层高度分布特征来自于离散点云或全波形。多时相激光雷达可用于森林生长量、生物量变化等监测,以及森林采伐、灾害等引起的结构变化监测。随着激光雷达技术的发展,它将在森林调查、生态环境建模等生产与科学研究领域中得到更为广泛的应用。 相似文献
6.
应用面向对象的决策树模型提取橡胶林信息 总被引：4，自引：0，他引：4
橡胶林的无序和不合理种植引发了一系列的生态问题,快速监测橡胶林空间分布及动态变化,对橡胶的合理种植、区域生态环境保护以及有关部门的规划决策有重要的指导意义。以MODIS归一化植被指数NDVI时间序列数据和多时相的Landsat TM数据为基础分析橡胶林的季相和光谱特征,确定橡胶识别的关键时期和特征参数,构建面向对象的决策树分类模型,开展橡胶信息提取研究。结果表明,多时相的遥感数据可反映橡胶的季相特征,以TM数据为基础计算得到的陆表水分指数LSWI和归一化植被指数NDVI可作为橡胶识别的光谱特征参数,橡胶休眠期是利用遥感方法进行橡胶提取的最佳时期。相比于单时相数据,利用包含橡胶关键物候期的多时相遥感数据能得到更高的橡胶林提取精度。 相似文献
7.
Automatic urban object detection from airborne remote sensing data is essential to process and efficiently interpret the vast amount of airborne imagery and Laserscanning (ALS) data available today. This paper combines ALS data and airborne imagery to exploit both: the good geometric quality of ALS and the spectral image information to detect the four classes buildings, trees, vegetated ground and sealed ground. A new segmentation approach is introduced which also makes use of geometric and spectral data during classification entity definition. Geometric, textural, low level and mid level image features are assigned to laser points which are quantified into voxels. The segment information is transferred to the voxels and those clusters of voxels form the entity to be classified. Two classification strategies are pursued: a supervised method, using Random Trees and an unsupervised approach, embedded in a Markov Random Field framework and using graph-cuts for energy optimization. A further contribution of this paper concerns the image-based point densification for building roofs which aims to mitigate the accuracy problems related to large ALS point spacing.Results for the ISPRS benchmark test data show that to rely on color information to separate vegetation from non-vegetation areas does mostly lead to good results, but in particular in shadow areas a confusion between classes might occur. The unsupervised classification strategy is especially sensitive in this respect. As far as the point cloud densification is concerned, we observe similar sensitivity with respect to color which makes some planes to be missed out, or false detections still remain. For planes where the densification is successful we see the expected enhancement of the outline. 相似文献
8.
高光谱-LiDAR多级融合城区地表覆盖分类 总被引：3，自引：3，他引：0
城市地区地表覆盖分类在城市研究中是一个十分重要的方向。遥感作为获取地物物理属性的一种重要技术手段,已初步应用于分类研究中。然而,随着城镇化的不断推进,城市内部地物类型越来越复杂,单一的遥感影像已无法满足城区地表覆盖分类中高精度的要求。高光谱影像和LiDAR数据能够分别表征地物的光谱信息及高程而被广泛应用。因此,根据两者之间互补的优势,本文提出了基于高光谱影像和LiDAR数据多级融合的城区地表覆盖分类方法。首先对两幅影像分别进行特征提取,将提取到的光谱、空间及高程信息进行层叠实现特征级融合。对得到的特征影像的所有像素点进行分类,然后利用LiDAR点云数据提取的建筑物掩膜,对非建筑物部分进行分类,再次实现特征级融合,以此改善建筑物区域与非建筑物区域的混淆。然后将未使用掩膜得到的分类结果与利用掩膜得到的分类结果进行投票实现决策级融合。最后利用条件随机场模型对分类结果进行后处理操作,达到平滑图像去除噪声点的目的。 相似文献
9.
在分析LiDAR点云数据分类现状的基础上,针对植被与建筑物重叠区域分类困难的问题,提出了一种基于面向对象的点云分类方法.首先采用三角网渐进内插的滤波方法将点云分为地面点和非地面点,并得到DTM;然后对高出DTM一定高度的非地面点建立三角网,删除较长的三角网的边(地物间的边),从而将非地面点云分割成多个对象;再利用各个对象内的三角网坡度信息熵大小判断该对象属于植被或建筑物;最后对于难以区分的对象(植被与建筑物重叠区)根据建筑物几何规则形状延伸扩充,从而提高植被和建筑物重叠区的点云分类准确率.实验结果表明,该方法能够很好地区分建筑物和植被点,分类准确率达到87％. 相似文献
10.
High resolution digital airborne imagery offers unprecedented opportunities for observation and monitoring of vegetation, providing the potential to identify, locate and track individual vegetation objects over time. Analytical tools are required to quantify relevant information. In this paper, locations of trees over a large area of native woodland vegetation were identified using morphological image analysis techniques. Methods of spatial point process statistics were then applied to estimate the spatially-varying tree death risk, and to show that it is significantly non-uniform. [Tree deaths over the area were detected in our previous work (Wallace et al., 2008).] The study area is a major source of ground water for the city of Perth, and the work was motivated by the need to understand and quantify vegetation changes in the context of water extraction and drying climate. The influence of hydrological variables on tree death risk was investigated using spatial statistics (graphical exploratory methods, spatial point pattern modelling and diagnostics). 相似文献
11.
机载LiDAR点云的分类是利用其进行城市场景三维重建的关键步骤之一。为充分利用现有的图像领域性能较好的深度学习网络模型,提高点云分类精度,并降低训练时间和对训练样本数量的要求,本文提出一种基于深度残差网络的机载LiDAR点云分类方法。首先提取归一化高程、表面变化率、强度和归一化植被指数4种具有较高区分度的点云低层次特征;然后通过设置不同的邻域大小和视角,利用所提出的点云特征图生成策略,得到多尺度和多视角点云特征图;再将点云特征图输入到预训练的深度残差网络,提取多尺度和多视角深层次特征;最后构建并训练神经网络分类器,利用训练的模型对待分类点云进行预测,经后处理得到分类结果。利用ISPRS三维语义标记竞赛的公开标准数据集进行试验,结果表明,本文方法可有效区分建筑物、地面、车辆等8类地物,分类结果的总体精度为87.1%,可为城市场景三维重建提供可靠的信息。 相似文献
12.
估算森林地上生物量(AGB)对于全球实现碳中和目标至关重要。本文以美国缅因州Howland森林为研究区域,借助地面实测样地数据,对比分析协同不同数据源(高光谱和LiDAR)和机器学习算法(随机森林、支持向量机、梯度提升决策树和K最邻近回归)的研究,以改善Howland森林的生物量估计精度。结果表明,采用LiDAR和高光谱植被指数变量模型的最佳精度分别为0.874和0.868,协同高光谱和LiDAR变量并采用梯度提升决策树回归模型的精度为0.927,即多源遥感数据要优于单一数据源。高光谱和LiDAR数据的协同使用对于提高类似于Howland地区或更广泛区域的生物量估计的准确性,具有普遍的适用性与一定的应用前景。 相似文献
13.
This study examines the understorey information present in discrete-return LiDAR (Light Detection And Ranging) data acquired for temperate deciduous woodland in mid summer (leaf-on) and in early spring when the understorey had mostly leafed out, but the overstorey had only just begun budburst (referred to here as leaf-off). The woodland is ancient, semi-natural broadleaf and has a heterogeneous structure with a mostly closed canopy overstorey and a patchy understorey layer. In this study, the understorey was defined as suppressed trees and shrubs growing beneath an overstorey canopy. Forest mensuration data for the study site were examined to identify thresholds (taking the 95th percentile) for crown depth as a percentage of crown top height for the six overstorey tree species present. These data were used in association with a digital tree species map and leaf-on first return LiDAR data, to identify the possible depth of space available below the overstorey canopy in which an understorey layer could exist. The leaf-off last return LiDAR data were then examined to identify whether they contained information on where this space was occupied by suppressed trees or shrubs forming an understorey. Thus, understorey was mapped from the leaf-off last return data where the height was below the predicted crown depth. A height threshold of 1 m was applied to separate the ground vegetation layer from the understorey. The derived understorey model formed a discontinuous layer covering 46.4 ha (or 31% of the study site), with an average height of 2.64 m and a 77% correspondence with field data on the presence/absence of suppressed trees and shrubs (kappa 0.53). Because the first return data in leaf-on and leaf-off conditions were very similar (differing by an average of just 0.87 m), it was also possible to map the understorey layer using leaf-off data alone. The resultant understorey model covered 39.4 ha (or 26% of the study site), and had a 72% correspondence with field data on the presence/absence of suppressed trees and shrubs (kappa 0.45). This moderate reduction in the area of understorey mapped and associated accuracy came with a saving of half of all data acquisition and pre-processing costs. Whilst the understorey modelling presented here undoubtedly benefited from the specific timing of LiDAR data acquisition and from ancillary data available for the study site, the conclusions have resonance beyond this case study. Given that the understorey and overstorey canopies in lowland broadleaf woodland can merge into one another, the modelling of understorey information from discrete-return LiDAR data must consider overstorey canopy characteristics and laser penetration through the overstorey. It is not adequate in such circumstances to apply simple height thresholds to LiDAR height frequency distributions, as this is unlikely to distinguish whether a return has backscattered from the lower parts of the overstorey canopy or from near the surface of the understorey canopy. 相似文献
14.
用基于知识的决策树方法分层提取矿区土地类型——以湖北大冶为例 总被引：6，自引：0，他引：6
以湖北大冶为研究区,采用多时相陆地卫星遥感图像,通过不同波段组合,以及ironoxide指数和归一化差异植被指数(NDVI)等,详细分析了各地表地物光谱特征和空间特征,建立了研究区分类知识库表,采用决策二叉树法进行分类,得到了高精度分类结果图。基于不同时相分类结果的变化检测,通过对研究区水体污染、矿区复垦、耕地变化等分析,认为从1986～2002年,研究区水质虽有一定改善,但矿区植被退化严重,耕地大量减少,停产矿区复垦仅为20%,为合理保护矿区生态环境和科学管理采矿企业提供了有用资料。 相似文献
15.
Hyperspectral image and full-waveform light detection and ranging (LiDAR) data provide useful spectral and geometric information for classifying land cover. Hyperspectral images contain a large number of bands, thus providing land-cover discrimination. Waveform LiDAR systems record the entire time-varying intensity of a return signal and supply detailed information on geometric distribution of land cover. This study developed an efficient multi-sensor data fusion approach that integrates hyperspectral data and full-waveform LiDAR information on the basis of minimum noise fraction and principal component analysis. Then, support vector machine was used to classify land cover in mountainous areas. Results showed that using multi-sensor fused data achieved better accuracy than using a hyperspectral image alone, with overall accuracy increasing from 83% to 91% using population error matrices, for the test site. The classification accuracies of forest and tea farms exhibited significant improvement when fused data were used. For example, classification results were more complete and compact in tea farms based on fused data. Fused data considered spectral and geometric land-cover information, and increased the discriminability of vegetation classes that provided similar spectral signatures. 相似文献
16.
17.
针对现有LiDAR地面点滤波算法对复杂地形地物适应性不强的问题,本文提出了一种融合点云与地面影像分块滤波的方法。首先,将地面影像与点云匹配,使点云从影像中获取更多的光谱纹理信息。然后,分析地物光谱、林地相对密度、点云高程特征、地面DSM模型及其坡度,并基于决策级融合将原始点云切割成若干独立的区块。最后,根据每块区域不同的多元细节特征,对IPTD滤波算法进行改进并利用搜索法优化参数,得到最优且稳健的结果。利用滤波后的总地面点通过插值算法得到的DEM模型和相关试验验证了本文算法的优越性。 相似文献
18.
高分辨率遥感植被分类研究 总被引：16，自引：0，他引：16
以南京市区的植被覆盖为研究对象,基于IKONOS遥感影像,采用决策树分类算法,根据各种植被光谱特征建立知识库,提出基于光谱信息的植被分类方法,继而结合高分辨率影像特有的纹理特征引进局部一致性指数对该方法进行改进,提出结合纹理信息的高分辨率遥感植被分类方法,分类总体精度从仅利用光谱信息的83.16%显著提高到91.89%,Kappa系数达到0.8886。采用Quickbird遥感影像对该方法进行验证,分类总体精度为91.94%,Kappa系数为0.8783,表明该植被分类方法能有效地对植被进行分类与识别,精度较高,且对于不同数据源的植被分类具有一定的普适性,为实现植被的自动化提取提供了理论依据和有效的方法途径。 相似文献
19.
机载LiDAR数据能够准确提供对象的三维空间位置信息,无人机高分辨影像具备丰富的色彩信息与纹理信息,综合两种数据的优点,可进行数据集成融合。针对山区普遍存在的分布广泛的植被覆盖类型基质景观,本文通过构建可见光植被指数（VDVI）融合光谱信息点云数据,进行典型植被特征提取的研究。为了验证该方法提取信息的准确度,分别构建了3种数据源并依次进行山区地表植被提取试验。对试验结果定性定量分析表明,融合光谱点云数据的植被覆被率为56.8%,较另外两种数据类型的植被覆被率更加接近参考值（58.2%）,可信度相对较高,效果更好,植被图斑轮廓更加清晰,更适用于目标对象植被特征提取,使融合影像信息的点云数据分类优势得以体现,证实了该方法面向山区植被特征提取的可行性。 相似文献
20.
本文针对LiDAR点云与无人机影像数据特征的优缺点,利用LiDAR点云与无人机DOM影像融合,将影像数据光谱信息赋给LiDAR点云数据,使其不仅具备精准的空间结构信息,还能得到清晰的纹理信息。为验证融合数据应用的可行性与数据提取的准确性,对融合前后的点云数据进行地面点提取与DEM构建。试验表明：将无人机影像的光谱信息赋给LiDAR点云数据,可以实现LiDAR点云数据从四维度表达到七维度的拓展,融合后点云数据具有清晰的纹理信息,地物类型判读更加容易,地面点分离完整;通过DEM模型的对比分析,融合后点云数据构建的DEM模型表达更加接近真实地表。研究结果为多源点云数据的深化应用提供了一定的技术方法支持作用。 相似文献