结合颜色信息的 Census变换半全局立体匹配算法

针对传统单一Census变换未充分利用影像信息且精度不高的问题,该文提出了一种结合颜色信息的Census变换半全局立体匹配算法。该算法联合像素点间RGB颜色绝对差值与其Census变换值的匹配代价计算方法,采用八方向半全局视差获取方法获得初始稠密视差图。为进一步提高匹配精度,利用左右一致性交叉检测确定初始视差图中不稳定视差;采用基于均值偏移图像分割的视差优化算法对视差图中不稳定视差进行优化,获得最终视差图。选取4组middlebury立体图片库经典立体像对进行视差获取实验并检测。结果表明,本算法能够获得较高精度且可靠视差图,且在遮挡、视差不连续处的视差精度明显优于单一Census变换立体匹配算法及一些改进半全局立体匹配算法。     

基于特征点的影像视差分析

本文介绍了一种基于特征点的数字立体影像匹配方法。该法采用Frstner算子提取特征点,然后应用一种松驰迭代算法,实现了同名特征点之间的立体匹配。为实现立体像对的自动相对定向和数字地形模型自动生成提供了一种切实可行的方法。     

一种星载激光测高仪光斑内定位方法

提出一种利用铅垂线轨迹法及高程结构信息约束的星载激光测高仪光斑内定位方法。在星载激光测高仪辅助立体摄影测量体制下，以激光回波中包含的高精度高程结构信息作为约束条件，在足印光斑内，配合立体图像匹配生成的数字高程模型，选取定位候选点，并通过铅垂线轨迹法优化定位候选点高程值，消除立体图像定位误差引起的高程误差，获取符合高程结构约束的一系列位置的三维坐标。试验结果表明，该方法能够实现大光斑星载激光测高仪足印内的定位，高程定位精度为0.16 m，平面定位精度与立体图像一致。     

单幅图像地理信息提取方法

针对单幅图像难以提取地理信息的问题,该文提出了一种基于场景结构或单一坐标值约束的地理信息提取方法。面向地形起伏不大或结构化场景,基于几何关系约束,该文设计了单幅图像地理信息提取的总体框架。分别针对结构化和非结构化场景,采用场景结构约束、图像EXIF信息等,实现了摄像机内参及部分外参的求解。基于该信息,通过单一坐标值约束,构建了单幅图像地理信息的提取方法。最后,在平面或垂面约束下,对室内外地理场景进行了二、三维地理信息提取实验。结果表明,该方法能够将单幅图像中的特征点、线或面转换为地理空间数据。     

近景图像序列线特征约束的建筑物立面重建

针对单纯利用近景图像序列点特征进行建筑物立面重建存在的问题,该文提出一种线特征约束下建筑物建模方法。首先利用运动恢复结构技术恢复相机参数和空间点云数据,并在此基础上利用多视图立体方法生成三维稠密点云;然后对图像序列进行基于梯度方向的边缘检测及顾及方向和长度的直线特征拟合;再利用多约束条件实现直线特征匹配及提取;最后基于三维点、线特征实现建筑物立面的三维重建。实验结果表明,该方法能有效利用近景图像序列点、线特征的优势互补重建建筑物的几何立面,更好地恢复建筑物立面的轮廓信息。     

基于刃边法与正则化方法的遥感影像复原

提出了一种基于刃边法PSF估计和保边缘正则化方法的遥感影像复原方法,利用刃边法,建立正则化复原模型,以及最速下降法进行复原,实现了优于传统的维纳滤波、约束最小平方等方法的复原效果。     

各向异性正则化的多帧遥感图像盲复原算法

在大气湍流较强时,一般的遥感图像复原算法难以取得较好的复原效果.针对这种情况,提出了一种基于各向异性约束的多帧遥感图像盲复原算法.该算法不需要成像过程的先验信息,仅根据图像及点扩散函数的非负约束和支持域约束,即可得到较好的复原结果;同时该算法能够自适应地调整正则化参数,在实现图像复原的同时,保持边缘并抑制噪声.试验结果...     

加权约束代价聚合的立体匹配算法

针对动态规划立体匹配算法存在的条纹瑕疵问题,提出了一种加权约束代价聚合的立体匹配算法。首先利用图像灰度与梯度信息联合计算匹配代价,并进行引导图像滤波;再通过四方向加权代价聚合的方式进行视差优化,得到最终视差图。标准测试数据实验结果证明,该算法能很好地改善传统动态规划算法的条纹瑕疵现象,且视差精度优于多数局部算法和动态规划改进算法,提高了立体匹配的精度。     

各向异性正则化的多帧遥感图像盲复原算法

在大气湍流较强时,一般的遥感图像复原算法难以取得较好的复原效果。针对这种情况,提出了一种基于各向异性约束的多帧遥感图像盲复原算法。该算法不需要成像过程的先验信息,仅根据图像及点扩散函数的非负约束和支持域约束,即可得到较好的复原结果;同时该算法能够自适应地调整正则化参数,在实现图像复原的同时,保持边缘并抑制噪声。试验结果验证了该算法的良好性能,复原后图像的质量得到较大提高。     

基于深度学习的立体影像密集匹配方法综述

三维重建可用于数字高程模型制作、机器人导航、增强现实和自动驾驶等。视差图是三维重建中一种重要的表达方式,而立体密集匹配是使用最广泛的获取视差图的技术。近年来,随着硬件、数据集、算法的发展,基于深度学习的立体匹配方法受到了广泛关注并取得了巨大成功。然而,这些方法通常在近景立体像对中进行测试,很少被用于遥感影像中。回顾了双目立体匹配的深度学习方法,选出了代表性的5种经典深度学习模型——GC-Net(geometry and context network)模型、PSM-Net(pyramid stereo matching network)模型、GWC-Net(group-wise correlation stereo network)模型、GA-Net(guided aggregation network)模型、HSM-Net(hierarchical deep stereo matching network)模型,将其应用于一套开源街景数据集(KITTI2015)和两套航空遥感影像数据集(München、WHU);分析了各种网络的实现方法,探讨了深度学习在遥感影像立体匹配中的性能,并与传统方法进行了对比。     

Stereo analysis of high-resolution SAR images for building height estimation in cases of orthogonal aspect directions

SAR stereo image analysis for 3D information extraction is mostly carried out based on imagery taken under same-side or opposite-side viewing conditions. For urban scenes in practice stereo is up to now usually restricted to the first configuration, because increasing image dissimilarity connected with rising illumination direction differences leads to a lack of suitable features for matching, especially in the case of low or medium resolution data. However, due to two developments SAR stereo from arbitrary viewing conditions becomes an interesting option for urban information extraction. The first one is the availability of airborne sensor systems, which are capable of more flexible data acquisition in comparison to satellite sensors. This flexibility enables multi-aspect analysis of objects in built-up areas for various kinds of purpose, such as building recognition, road network extraction, or traffic monitoring. The second development is the significant improvement of the geometric resolution providing a high level of detail especially of roof features, which can be observed from a wide span of viewpoints. In this paper, high-resolution SAR images of an urban scene are analyzed in order to infer buildings and their height from the different layover effects in views taken from orthogonal aspect angles. High level object matching is proposed that relies on symbolic data, representing suitable features of urban objects. Here, a knowledge-based approach is applied, which is realized by a production system that codes a set of suitable principles of perceptual grouping in its production rules. The images are analyzed separately for the presence of certain object groups and their characteristics frequently appearing on buildings, such as salient rows of point targets, rectangular structures or symmetries. The stereo analysis is then accomplished by means of productions that combine and match these 2D image objects and infer their height by 3D clustering. The approach is tested using real SAR data of an urban scene.     

基于零立体像对立体匹配的配后质量控制

立体匹配的质量控制对数字摄影测量产品的质量起着关键的作用。本文首先分析了现有的各种质量控制策略，然后根据正射影像同ＤＴＭ及匹配点位存在的固有关系，提出了用零立体像对再匹配作为立体匹配的配后质量控制方案，为立体匹配质量控制开辟了崭新的途径。     

Limitations of high resolution satellite stereo imagery for estimating canopy height in Australian tropical savannas

Obtaining reliable measures of tree canopy height across large areas is a central element of forest inventory and carbon accounting. Recent years have seen an increased emphasis on the use of active sensors like Radar and airborne LiDAR (light detection and scanning) systems to estimate various 3D characteristics of canopy and crown structure that can be used as predictors of biomass. However, airborne LiDAR data are expensive to acquire, and not often readily available across large remote landscapes. In this study, we evaluated the potential of stereo imagery from commercially available Very High Resolution (VHR) satellites as an alternative for estimating canopy height variables in Australian tropical savannas, using a semi-global dense matching (SGM) image-based technique. We assessed and compared the completeness and vertical accuracy of extracted canopy height models (CHMs) from GeoEye 1 and WorldView 1 VHR satellite stereo pairs and summarised the factors influencing image matching effectiveness and quality.Our results showed that stereo dense matching using the SGM technique severely underestimates tree presence and canopy height. The highest tree detection rates were achieved by using the near-infrared (NIR) band of GE1 (8–9%). WV1-GE1 cross-satellite (mixed) models did not improve the quality of extracted canopy heights. We consider these poor detection rates and height retrievals to result from: i) the clumping crown structure of the dominant Eucalyptus spp.; ii) their vertically oriented leaves (affecting the bidirectional reflectance distribution function); iii) image band radiometry and iv) wind induced crown movement affecting stereo-pair point matching. Our detailed analyses suggest that current commercially available VHR satellite data (0.5 m resolution) are not well suited to estimating canopy height variables, and therefore above ground biomass (AGB), in Eucalyptus dominated north Australian tropical savanna woodlands.     

Tri-Stereo Image Matching using Watershed Segmentation on Disparity Space Image

Local stereo matching algorithms use winner-take-all approach to get the disparity. Many times they end up at an erroneous result. To solve this, in the present work, a novel stereo image matching technique has been developed that identifies the most likely local minimum from the several possible local minima that corresponds to true disparity. The technique uses properties of the physical continuity of the land surface by the watershed lines applied to the disparity space volume. This helps to minimize the search for the most probable local minima as the correct solution for the matching. The matching is further improved by combining the watershed lines of disparity space volume of two stereo pairs from the tri-stereo. In the present study, experiments have been carried out using the standard Middlebury stereo datasets and remotely sensed tri-stereo images. Based on this approach, the experiments are successfully carried out using the test dataset. The experimental results are compared with the results from the currently contemporary techniques of dynamic programming and semi-global matching which resulted in 2–10% improvement in density of matched points for different datasets.     

基于边缘的多尺度立体匹配算法

提出了一种面向对象的多尺度递进的立体匹配算法,实现了由粗到细的快速立体匹配。首先对参考图进行粗分割获取目标对象,针对目标区域采用边缘线动态规划的方法获取视差,根据精度需求进一步判断该目标是否需要细分以获取更加精细的视差,得到有效的视差图。实验结果表明此方法快速有效。     

GIS空间数据采集中概率松弛与神经网络的组合模型

本文介绍一种ＧＩＳ空间数据采集中概率松弛与神经网络的组合模型，该模型用于地图分色和立体影像的整体匹配。     

月面巡视探测器立体影像的多核CPU并行快速匹配

月面巡视探测器立体影像的摄影测量处理是获取月面三维信息实现巡视器定位导航的重要手段之一。影像匹配是地面近景摄影测量实现自动化处理的关键,本文研究了基于积分影像的单机多核并行匹配算法,实现了月面巡视器模拟影像的快速匹配。试验表明该方法能显著地缩短匹配时间,达到较高的加速比和效率。     

引入自适应窗口的立体图像匹配算法

基于灰度的数字图像立体匹配算法的中心问题是选择一个适当尺寸的窗口。窗口尺寸既要尽可能地大，以便为可靠匹配包容足够的灰度变化；又要尽可能地小，以避开投影畸变的影响。本文介绍一种通过测算局部灰度和视差变化来选取适当窗口的方法。该方法引入一个窗口范围内的视差分布统计模型（随机模型）。利用该模型可确定，在窗口内的视差变化及灰度变化引起的窗口中心点视差估值的统计误差。以此为基础，文中提出一种窗口搜索方法，以对整幅图像上每一像素求出一个统计误差为最小的视差估值。这种算法不仅能自适应地调节窗口的尺寸，而且亦能同时调整窗口的形状（矩形）。     

Change detection on LOD 2 building models with very high resolution spaceborne stereo imagery

Due to the fast development of the urban environment, the need for efficient maintenance and updating of 3D building models is ever increasing. Change detection is an essential step to spot the changed area for data (map/3D models) updating and urban monitoring. Traditional methods based on 2D images are no longer suitable for change detection in building scale, owing to the increased spectral variability of the building roofs and larger perspective distortion of the very high resolution (VHR) imagery. Change detection in 3D is increasingly being investigated using airborne laser scanning data or matched Digital Surface Models (DSM), but rare study has been conducted regarding to change detection on 3D city models with VHR images, which is more informative but meanwhile more complicated. This is due to the fact that the 3D models are abstracted geometric representation of the urban reality, while the VHR images record everything. In this paper, a novel method is proposed to detect changes directly on LOD (Level of Detail) 2 building models with VHR spaceborne stereo images from a different date, with particular focus on addressing the special characteristics of the 3D models. In the first step, the 3D building models are projected onto a raster grid, encoded with building object, terrain object, and planar faces. The DSM is extracted from the stereo imagery by hierarchical semi-global matching (SGM). In the second step, a multi-channel change indicator is extracted between the 3D models and stereo images, considering the inherent geometric consistency (IGC), height difference, and texture similarity for each planar face. Each channel of the indicator is then clustered with the Self-organizing Map (SOM), with “change”, “non-change” and “uncertain change” status labeled through a voting strategy. The “uncertain changes” are then determined with a Markov Random Field (MRF) analysis considering the geometric relationship between faces. In the third step, buildings are extracted combining the multispectral images and the DSM by morphological operators, and the new buildings are determined by excluding the verified unchanged buildings from the second step. Both the synthetic experiment with Worldview-2 stereo imagery and the real experiment with IKONOS stereo imagery are carried out to demonstrate the effectiveness of the proposed method. It is shown that the proposed method can be applied as an effective way to monitoring the building changes, as well as updating 3D models from one epoch to the other.