多源影像融合的建筑物三维模型无遮挡纹理自动贴图方法

介绍了倾斜摄影测量在数字城市建设中的应用,针对当前基于倾斜摄影测量的城市三维重建过程中纹理贴图存在遮挡问题,详细探究了纹理遮挡几何原理,并提出联合固定翼飞机高空倾斜摄影及无人机低空倾斜影像,设计了建筑物三维模型无遮挡影像优选算法,实现了高精度无遮挡纹理自动贴图,并通过试验进行了验证。     

Rapid texture mapping from image sequences for building geometry model

An effective approach, mapping the texture for building model based on the digital photogrammetric theory, is proposed. The easily-acquired image sequences from digital video camera on helicopter are used as texture resource, and the correspondence between the space edge in building geometry model and its line feature in image sequences is determined semiautomatically. The experimental results in production of three-dimensional data for car navigation show us an attractive future both in efficiency and effect.     

Rapid texture mapping from image sequences for building geometry model

An effective approach,mapping the texture for building model based on the digital photogrammetric theory, is proposed. The easily-ac-quired image sequences from digital video camera on helicopter are used as texture resource, and the correspon-dence between the space edge in build-ing geometry model and its line feature in image sequences is determined semi-automatically. The experimental re-sults in production of three-dimension-al data for car navigation show us an attractive future both in efficiency and effect.     

自适应分块加权Wallis并行匀色

针对区域范围内多幅待镶嵌影像之间的色彩差异问题,提出一种基于GPU的分块加权Wallis并行匀色算法。首先,根据变异系数对影像自适应分块并利用双线性插值确定每一个像素的变换参数,利用加权Wallis变换消除影像间的色彩差异。然后,为了控制区域整体的匀色质量,利用Voronoi图和Dijkstra算法确定影像间的处理顺序。最后,利用GPU技术进行并行任务设计并从配置划分、存储器访问和指令吞吐量等方面进行优化,提高算法运算效率。实验结果表明,本文方法既能有效地消除影像间色彩差异,又能消除影像间的对比度差异。与CPU串行算法相比,GPU并行算法显著减少了计算时间,加速比最高达到60倍以上。     

Efficient building facade structure extraction method using image-based laser point cloud

Facade structures from three-dimensional (3D) point cloud data (PCD) and two-dimensional (2D) optical images can provide significant information for 3D building modeling. However, a unified data model for integrating 2D imagery pixels and 3D PCD is absent in current methods, leading to a complex implementation process, large calculations, and inefficiency. An efficient facade structure extraction method for building facades is proposed in this study. Based on the conversion matrix, 2D image and 3D PCD information are merged to build an image-based laser point cloud (ILPC) data model first. Second, both the line segment detection and random sample consensus algorithms are improved according to the structure and characteristics of the ILPC data model. Finally, building facade structures are extracted and optimized. Facade structures can be extracted accurately and efficiently by the proposed method, which contains rich information support from the ILPC data model. The proposed method extracts fine building facade structures with accuracy over 0.68 in all experiments and recall up to 0.81, which are better than the Wang method. Extracted structures constitute valuable support for numerous fields, such as 3D building modeling and building information modeling construction.     

一种快速的无人机影像无缝拼接方法

本文针对传统的低空无人机影像拼接处理速度慢和几何精度低的问题,提出了一种快速的无人机影像无缝拼接方法:对输入的原始影像按一定尺度进行降采样,在降采样的影像上进行SURF特征提取和匹配,利用RANSAC方法估计初始的相对单应矩阵,然后用Levenberg-Marquardt方法精化单应矩阵,计算出初始的绝对单应矩阵后利用稀疏光束法平差估计出精确的单应矩阵,通过降采样影像与原始影像的单应关系传递单应矩阵到原始影像级,最后进行影像合成,形成整体拼接图.实验结果表明该方法可以有效地提高拼接速度,解决拼接错位问题.     

一种三维激光点云中建筑物立面渐进分割方法

针对建筑物立面分割的问题,该文提出了一种三维激光点云中建筑物立面渐进分割方法。建立三维格网索引,通过分析建筑物立面在三维格网内的空间分布特征和二维平面格网内投影的线性分布特征,确定立面种子格网和投影线的拟合点,拟合投影线并基于种子格网约束生长完成每层格网中立面粗分割;使用RANSAC算法对粗分割后的立面点云进行面拟合,实现精细分割,并将各层格网中的立面进行合并,实现建筑物立面的完整分割。实验结果表明,该方法能有效地实现建筑物立面的精细化分割,有助于后续的建筑物精细三维模型重建。     

以卫星影像为底图的无人机图像自动拼接方法

针对无人机影像受成像角度倾斜、光照不均匀等影响,导致常规匹配方法拼接效果较差的问题,该文提出一种基于现有卫星影像的由粗到精无人机图像自动拼接方法。首先,在对图像进行粗匹配阶段,提出了一种基于环状描述子的尺度不变特征变换,用于解决图像间旋转和尺度的差异,较好地克服了SIFT算法描述子维度较高且计算量大的不足。其次,引入分块互信息进行精匹配,减少拼接过程中的累计误差。最后,采用该文提出算法对无人机图像进行拼接,实验结果表明,该文提出的无人机图像拼接算法在满足实时性要求的同时可以达到较高精度。     

露采矿山近景影像光束法三维建模及动态监测系统

为满足采矿工程数字化监测和信息化管理的需求,研究一种应用近景摄影测量手段动态监测露采矿山储量变化的方法,并设计开发储量动态检测软件系统。利用标定过的普通数码相机采集矿山近景影像,采用光束法处理影像;针对普通数码影像的特点,研究一种基于SURF特征点提取和短核线搜索的一维匹配方法;通过多期影像建立的三维模型分析,实现对矿山的动态监测。工程实例证明该建模方法快速有效,软件系统极大地提高露采矿山的作业效率和精确度。     

近景影像三角网内插点密集匹配方法

针对目前密集匹配中依据种子点寻找新特征点存在计算复杂的问题,该文提出一种近景影像Delaunay三角网内插点密集匹配方法。该方法首先采用尺度不变特征变换算子匹配特征点,通过随机抽样一致性算法对特征点进行优化,以获取高精度同名点;依据同名点构建Delaunay三角网,在同名相似三角形内,以内插重心点作为匹配基元,并对内插点进行色彩信息相似性约束和极线约束,剔除粗差提高匹配结果精度;在匹配传播过程中,新特征点不断插入三角网中,对三角网进行动态更新,用于约束后续匹配。该方法能够避免繁琐计算,同时具有较高的可靠性,适用于不同类型的近景影像数据。     

Generalization of 3D building texture using image compression and multiple representation data structure

Textures are an essential part of 3D building models and often consume large portions of the data volume, thus making visualization difficult. Therefore, we propose a multi-resolution texture generalization method to compress the textures of 3D building models for dynamic visualization at different scales. It consists of two steps: image compression and texture coloring. In the first step, texture images are compressed using wavelet transformation in both the horizontal and the vertical direction. In the second step, a TextureTree is created to store building texture color for dynamic visualization from different distances. To generate a TextureTree, texture images are iteratively segmented by horizontal and vertical dividing zones, until each section is basically in the same color. Then the texture of each section is represented by their main color and the TextureTree is created based on the color difference between the adjacent sections. In dynamic visualization, the suitable compressed texture images or the TextureTree nodes are selected to generate 3D scenes based on the angle and the distance between the viewpoint and the building surface. The experimental results indicate that wavelet based image compression and the proposed TextureTree can effectively represent the visual features of the textured buildings with much less data.     

基于数字图像的车辆行驶跑偏在线测量方法

保证车辆在正常情况下沿直线行驶是汽车制造的基本要求,汽车制造厂商高度重视车辆行驶跑偏的检测.文章分析了车辆行驶跑偏量测量的一般方法并提出了一种基于数字图像的汽车行驶跑偏检测方法,实现了车辆行驶跑偏量的自动测量.通过实验,验证了该方法的可行性,且具有自动化程度高、效率高、测量精度高以及可靠性强等特点.基于数字图像的车辆行驶跑偏在线测量系统已投入汽车制造公司的实际生产使用.     

建筑物立面重复模式的点云投影直方图分割方法

针对建筑物的门、窗、梁、柱等具有规则几何形状的重复模式,提出基于投影点云特征直方图(PPFH)的边界语义分割方法.该方法首先利用PC A方法确定立面的主方向,然后根据点云分布特点,分别进行正立面、侧立面投影得到点云分布直方图,根据直方图的极值点对重复结构边界进行提取和语义分割,最后利用LS-TLS方法进行规则化及误差分析.通过对某建筑物立面窗户提取的算例表明:该方法直接利用重复结构的几何特性,算法简洁,对边缘部分遮蔽和缺失的点云也适用,通过对50个窗户的统计分析,长度和宽度平均误差约6 m m,可广泛用于建筑高精度BIM建模.     

高精度CORS站像控点自动提取方法

CORS站持续稳定运行产生了海量高精度定位点数据,如何挖掘提取高精度可用像控点,以替代部分像控点人工选择或外业测绘工作,具有重要推广价值。本文提出了一种基于高精度CORS定位数据的像控点自动提取方法,并研发了像控点自动提取工具。首先采用Douglas-Peucker算法实现轨迹简化;然后利用ST-DBSCAN提取聚类中心;最后进一步栅格化,优化提取得到高可用像控点集。试验结果表明,像控点提取结果的准确率在94%以上,大大减少了像控点采集的工作量,重复利用高精度像控点信息具有广阔应用前景。     

平行摄影序列影像的核线影像生成方法

针对平行摄影方式较传统航空摄影方式获取的影像在核线排列及采集方面存在较大差异,导致平行摄影序列影像难以生成核线影像的问题,该文在研究平行摄影方式的摄影基线与影像核点位置间几何关系的基础上,推导了平行摄影序列影像核点位置的严密计算公式,并根据相邻平行摄影序列影像重叠区域最大化原则选取核线生成的起始点和终止点,以此确定核线影像的生成区域,最后采用灰度双线性内插法完成核线影像的采集。以勘探洞平行摄影序列影像作为实验对象,首先基于该文算法生成其核线影像,然后采用密集匹配算法建立左、右核线影像像素间对应关系,最后结合前方交会算法生成洞室的三维点云,进而验证了该文核线影像生成算法的正确性。     

一种放电检测中紫外和可见光图像配准方法

为了将紫外图像和可见光图像进行融合让人们及时清晰地观测到设备故障,该文提出了一种基于相机模型和相机间透视变换的图像配准方法和相应的标定装置,能够实现高精度、小计算量的高效紫外图像和可见光图像的对齐。紫外和可见光的信息融合不仅能够探测目标发射的紫外光谱,还可以对目标进行清晰成像、精确定位,生成的多光谱图像改善单一光谱成像信息的局限性。利用多源图像的信息互补,提高图像检测的准确性、及时性,也更适合计算机的后续分析与处理。     

高分辨率遥感影像建筑物提取多路径RSU网络法

针对卷积神经网络在提取建筑物的过程中,存在建筑物边界不准确和建筑物内部空洞等问题,提出以RSU模块（residual U-block）为核心的MPRSU-Net （multi-path residual U-block network）。该模块利用编码器-解码器结构和残差连接,实现了局部特征和多尺度特征的融合。由于一个RSU模块提取的信息有限,MPRSU-Net进一步通过多路径结构并行了不同尺度的RSU模块,并在这些模块之间进行信息交换,提高了特征聚集效率。在分辨率为0.3 m的WHU和Inria建筑物数据集上进行试验,精度分别达95.65%和88.63%,IoU分别达91.17%和79.31%,验证了本文方法的有效性。此外,本文方法相较于U²Net,计算量明显降低,模型参数量减少68.63%,表明本文方法具有一定的应用价值。     

Automatic road extraction using high resolution satellite image based on texture progressive analysis and normalized cut method

In this paper the approach for automatic road extraction for an urban region using structural, spectral and geometric characteristics of roads has been presented. Roads have been extracted based on two levels: Pre-processing and road extraction methods. Initially, the image is pre-processed to improve the tolerance by reducing the clutter (that mostly represents the buildings, parking lots, vegetation regions and other open spaces). The road segments are then extracted using Texture Progressive Analysis (TPA) and Normalized cut algorithm. The TPA technique uses binary segmentation based on three levels of texture statistical evaluation to extract road segments where as, Normalized cut method for road extraction is a graph based method that generates optimal partition of road segments. The performance evaluation (quality measures) for road extraction using TPA and normalized cut method is compared. Thus the experimental result show that normalized cut method is efficient in extracting road segments in urban region from high resolution satellite image.     

Use of field reflectance data for crop mapping using airborne hyperspectral image

Recent developments in hyperspectral remote sensing technologies enable acquisition of image with high spectral resolution, which is typical to the laboratory or in situ reflectance measurements. There has been an increasing interest in the utilization of in situ reference reflectance spectra for rapid and repeated mapping of various surface features. Here we examined the prospect of classifying airborne hyperspectral image using field reflectance spectra as the training data for crop mapping. Canopy level field reflectance measurements of some important agricultural crops, i.e. alfalfa, winter barley, winter rape, winter rye, and winter wheat collected during four consecutive growing seasons are used for the classification of a HyMAP image acquired for a separate location by (1) mixture tuned matched filtering (MTMF), (2) spectral feature fitting (SFF), and (3) spectral angle mapper (SAM) methods. In order to answer a general research question “what is the prospect of using independent reference reflectance spectra for image classification”, while focussing on the crop classification, the results indicate distinct aspects. On the one hand, field reflectance spectra of winter rape and alfalfa demonstrate excellent crop discrimination and spectral matching with the image across the growing seasons. On the other hand, significant spectral confusion detected among the winter barley, winter rye, and winter wheat rule out the possibility of existence of a meaningful spectral matching between field reflectance spectra and image. While supporting the current notion of “non-existence of characteristic reflectance spectral signatures for vegetation”, results indicate that there exist some crops whose spectral signatures are similar to characteristic spectral signatures with possibility of using them in image classification.     

一种高分辨率卫星影像自动云检测方法

针对多数已有的卫星影像云检测方法利用云独特的光谱特征、构造指数图像进行云识别的方法,对传感器、环境参数、云层类型等比较敏感的问题,提出了一种改进HIS模型的高分辨率卫星影像自动云检测方法,以有效弥补传统纹理分析方法计算精度低、效率低下的问题.采用两景国产高分二号遥感影像进行试验.结果 表明,该方法错误率低于5％、查全率高于92％、查准率高于95％.