Search

In recent decades, the geospatial domain has benefitted from technological advances in sensors, methodologies, and processing tools to expand capabilities in mapping applications. Airborne techniques (LiDAR and aerial photogrammetry) generally provide most of the data used for this purpose. However, despite the relevant accuracy of these technologies and the high spatial resolution of airborne data, updates are not sufficiently regular due to significant flight costs and logistics. New possibilities to fill this information gap have emerged with the advent of Very High Resolution (VHR) optical satellite images in the early 2000s. In addition to the high temporal resolution of the cost-effective datasets and their sub-meter geometric resolutions, the synoptic coverage is an unprecedented opportunity for mapping remote areas, multi-temporal analyses, updating datasets and disaster management. For all these reasons, VHR satellite imagery is clearly a relevant study for National Mapping and Cadastral Agencies (NMCAs). This work, supported by EuroSDR, summarises a series of experimental analyses carried out over diverse landscapes to explore the potential of VHR imagery for large-scale mapping. [ABSTRACT FROM AUTHOR]

In the context of the development of an autonomous tower crane, the usage of crane cameras to map the respective workspace as basis for autonomous path planning is investigated. The goal is to generate an up-to-date DEM as input for the crane control. As construction sites are highly dynamic scenes, it is crucial to be able to react to any changes. Thus, real-time mapping with a visual SLAM solution is aspired. As the quality of the DEM is important for such a safety critical application, we are evaluating the mapping quality of four state-of-the-art SLAM solutions, namely ORB-SLAM3, LDSO, DSM and DROID-SLAM. The results show that all approaches can handle our specific crane camera setup and thus are generally suited for our application. The DEM accuracies of all tested methods are even competitive with the result from standard offline photogrammetric processing, at least for the major part of the test site. However, there are limitations with regards to the DEM completeness. Consequently, our investigations show that the tested methods deliver a good basis for real-time accurate mapping, but for their application for autonomous path planning further refinements have to be made. [ABSTRACT FROM AUTHOR]

Point cloud registration algorithms have been studied for several decades. In the SLAM domain, dense local convergence based methods are typically used to register consecutive scans. Since these procedures are not globally optimal, it happens that they converge to a wrong local minimum. This can lead to gross errors during mapping and can make entire datasets unusable. We introduce a new branch and bound based point cloud registration method that is globally optimal. The method is able to reliably determine the global optimum within a given parameter search space. We show how this method can be used in a mapping system as a fallback function to correct gross errors. Using various public datasets, we demonstrate the capabilities of the method. [ABSTRACT FROM AUTHOR]

Automatic photogrammetric processing of historical (or archival) aerial photos is still a challenging task, particularly in cases of missing ancillary information, low radiometric and image quality, limited stereo coverage or large temporal span. However, with recent advances in photogrammetry and Artificial Intelligence (AI) algorithms for image processing and interpretation, an increasing number of applications are now feasible. The article presents the TIME (hisTorical aerIal iMagEs) benchmark (https://time.fbk.eu/), promoted by EuroSDR to explore the potential of historical aerial images. Realized in collaboration with various European NMCAs, the benchmark has garnered aerial image blocks and time series imagery captured since the 1950s. To support the photogrammetric processing of the digitized photos, ancillary data are supplied with available information about flight missions, taking cameras, and ground control points (GCPs). Several diverse investigations have been undertaken with the benchmark datasets, all captured over historical urban areas or landscapes. The paper describes the benchmark datasets and some potential research topics, presenting several tests and analyses realized with the collated and shared data. [ABSTRACT FROM AUTHOR]

The semantic segmentation of the huge amount of acquired 3D data has become an important task in recent years. Meshes have evolved into a standard representation next to Point Clouds (PCs) – not least because of their great visualization possibilities. Compared to PCs, meshes have commonly smaller memory footprints while jointly providing geometrical and high-resolution textural information. For this reason, we opt for semantic mesh segmentation, which is a widely overlooked topic in photogrammetry and remote sensing yet. In this work, we perform an extensive ablation study on multi-modal handcrafted features adapting the Point Cloud Mesh Association (PCMA) (Laupheimer et al., 2020) which establishes explicit connections between faces and points. The multi-modal connections are used in a two-fold manner: (i) to extend per-face descriptors with features engineered on the PC and (ii) to annotate meshes semi-automatically by propagating the manually assigned labels from the PCs. In this way, we derive annotated meshes from the ISPRS benchmark data sets Vaihingen 3D (V3D) and Hessigheim 3D (H3D). To demonstrate the effectiveness of the multi-modal approach, we use well-established and fast Random Forest (RF) models deploying various feature vector compositions and analyze their performances for semantic mesh segmentation. The feature vector compositions consider features derived from the mesh, the PC or both. The results indicate that the combination of radiometric and geometric features outperforms feature sets of a single feature type only. Besides, we observe that relative height is the most crucial feature. The main finding is that the multi-modal feature vector integrates the complementary strengths of the underlying modalities. Whereas the mesh provides outstanding textural information, the dense PCs are superior in geometry. The multi-modal feature descriptor achieves the best performance on both data sets. It significantly outperforms feature sets that incorporate only features derived from the mesh by +7.37 pp and +2.38 pp for mF1 and Overall Accuracy (OA) on V3D. The registered improvement is +9.23 pp and +4.33 pp for mF1 and OA on H3D. [ABSTRACT FROM AUTHOR]

Mobile robots are being increasingly employed in various indoor scenarios. The fundamental prerequisite is that the robot can reconstruct an accurate and complete map of the observed environment and estimate the track of its movements in this map. Current visual SLAM methods can perform this task reasonably well, but mostly in small spaces, such as a single room, and often tested in well-textured environments. In real-world applications of large indoor scenes, they lack robustness and fail to build a globally consistent map. To this end, we propose a novel system that can robustly solve the problem encountered by existing visual SLAM methods, such as weak texture and long-term drift. By combining information from a wheel odometer, the robot poses can be predicted smoothly in the absence of texture. The geometric cues are leveraged by aligning Truncated Signed Distance Function (TSDF) based submaps to minimize the long-term drift. To reconstruct a more complete and accurate dense map, we refine the sensor depth maps by taking advantage of color information and the optimization result of global bundle adjustment. As a result, the system can provide precise trajectory estimation and a globally consistent map for the downstream tasks. We validate the accuracy and robustness of the proposed method on both public and self-collected datasets and show the complementary nature of each module. Evaluation results based on high precision ground-truth show an improvement in the mean Absolute Trajectory Error (ATE) from 21 cm to 2 cm for the trajectory estimation, and the reconstructed map has a mean accuracy of 8 cm. [ABSTRACT FROM AUTHOR]

Semantic interpretation of multi-modal datasets is of great importance in many domains of geospatial data analysis. However, when training models for automated semantic segmentation, labeled training data is required and in case of multi-modality for each representation form of the scene. To completely avoid the time-consuming and cost-intensive involvement of an expert in the annotation procedure, we propose an Active Learning (AL) pipeline where a Random Forest classifier selects a subset of points sufficient for training and where necessary labels are received from the crowd. In this AL loop, we aim on coupled semantic segmentation of an Airborne Laser Scanning (ALS) point cloud and the corresponding 3D textured mesh generated from LiDAR data and imagery in a hybrid manner. Within this work we pursue two main objectives: i) We evaluate the performance of the AL pipeline applied to an ultra-high resolution ALS point cloud and a derived textured mesh (both benchmark datasets are available at https://ifpwww.ifp.uni-stuttgart.de/benchmark/hessigheim/default.aspx). ii) We investigate the capabilities of the crowd regarding interpretation of 3D geodata and observed that the crowd performs about 3 percentage points better when labeling meshes compared to point clouds. We additionally demonstrate that labels received solely by the crowd can power a machine learning system only differing in Overall Accuracy by less than 2 percentage points for the point cloud and less than 3 percentage points for the mesh, compared to using the completely labeled training pool. For deriving this sparse training set, we ask the crowd to label 0.25 % of available training points, resulting in costs of 190 $. [ABSTRACT FROM AUTHOR]

This paper presents a study on the potential of ultra-high accurate UAV-based 3D data capture by combining both imagery and LiDAR data. Our work is motivated by a project aiming at the monitoring of subsidence in an area of mixed use. Thus, it covers built-up regions in a village with a ship lock as the main object of interest as well as regions of agricultural use. In order to monitor potential subsidence in the order of 10 mm/year, we aim at sub-centimeter accuracies of the respective 3D point clouds. We show that hybrid georeferencing helps to increase the accuracy of the adjusted LiDAR point cloud by integrating results from photogrammetric block adjustment to improve the time-dependent trajectory corrections. As our main contribution, we demonstrate that joint orientation of laser scans and images in a hybrid adjustment framework significantly improves the relative and absolute height accuracies. By these means, accuracies corresponding to the GSD of the integrated imagery can be achieved. Image data can also help to enhance the LiDAR point clouds. As an example, integrating results from Multi-View Stereo potentially increases the point density from airborne LiDAR. Furthermore, image texture can support 3D point cloud classification. This semantic segmentation discussed in the final part of the paper is a prerequisite for further enhancement and analysis of the captured point cloud. [ABSTRACT FROM AUTHOR]

The semantic segmentation of the huge amount of acquired 3D data has become an important task in recent years. We propose a novel association mechanism that enables information transfer between two 3D representations: point clouds and meshes. The association mechanism can be used in a two-fold manner: (i) feature transfer to stabilize semantic segmentation of one representation with features from the other representation and (ii) label transfer to achieve the semantic annotation of both representations. We claim that point clouds are an intermediate product whereas meshes are a final user product that jointly provides geometrical and textural information. For this reason, we opt for semantic mesh segmentation in the first place. We apply an off-the-shelf PointNet++ to a textured urban triangle mesh as generated from LiDAR and oblique imagery. For each face within a mesh, a feature vector is computed and optionally extended by inherent LiDAR features as provided by the sensor (e.g. intensity). The feature vector extension is accomplished with the proposed association mechanism. By these means, we leverage inherent features from both data representations for the semantic mesh segmentation (multi-modality). We achieve an overall accuracy of 86:40% on the face-level on a dedicated test mesh. Neglecting LiDAR-inherent features in the per-face feature vectors decreases mean intersection over union by ∼2%. Leveraging our association mechanism, we transfer predicted mesh labels to the LiDAR point cloud at a stroke. To this end, we semantically segment the point cloud by implicit usage of geometric and textural mesh features. The semantic point cloud segmentation achieves an overall accuracy close to 84% on the point-level for both feature vector compositions. [ABSTRACT FROM AUTHOR]

Lightweight unmanned aerial vehicles (UAVs) have been widely used in image acquisition for 3D reconstruction. With the availability of compact and high-end imaging sensors, UAVs can be the platform for precise photogrammetric reconstruction. However, the completeness and precision of complex environment or targets highly rely on the flight planning due to the self-occlusion of structures. Flight paths with back-and-forth pattern and nadir views will result in incompleteness and precision loss of the 3D reconstruction. Therefore, multiple views from different directions are preferred in order to eliminate the occlusion. We propose a 3D path planning method for multirotor UAVs aiming at capturing images for complete and precise photogrammetric 3D reconstructions. This method takes the coarse model from an initial flight as prior knowledge and estimates its completeness and precision. New imaging positions are then planned taking photogrammetric constraints into account. The real-world experiment on a ship lock shows that the proposed method can acquire a more complete result with similar precision compared with an existing 3D planning method. [ABSTRACT FROM AUTHOR]

We propose a feature-based approach for semantic mesh segmentation in an urban scenario using real-world training data. There are only few works that deal with semantic interpretation of urban triangle meshes so far. Most 3D classifications operate on point clouds. However, we claim that point clouds are an intermediate product in the photogrammetric pipeline. For this reason, we explore the capabilities of a Convolutional Neural Network (CNN) based approach to semantically enrich textured urban triangle meshes as generated from LiDAR or Multi-View Stereo (MVS). For each face within a mesh, a feature vector is computed and fed into a multi-branch 1D CNN. Ordinarily, CNNs are an end-to-end learning approach operating on regularly structured input data. Meshes, however, are not regularly structured. By calculating feature vectors, we enable the CNN to process mesh data. By these means, we combine explicit feature calculation and feature learning (hybrid model). Our model achieves close to 80% Overall Accuracy (OA) on dedicated test meshes. Additionally, we compare our results with a default Random Forest (RF) classifier that performs slightly worse. In addition to slightly better performance, the 1D CNN trains faster and is faster at inference. [ABSTRACT FROM AUTHOR]

This document is a preface to a workshop titled "Semantics3D - Semantic Scene Analysis and 3D Reconstruction from Images and Image Sequences." The workshop focused on the research topics of automated 3D reconstruction and extraction of semantic information from images and image sequences in the fields of Photogrammetry, Remote Sensing, GIS, and Computer Vision. The workshop received 11 full papers and 9 extended abstracts for review, with 7 full papers and 6 papers based on selected abstracts accepted for publication. The document also lists the members of the Program Committee and expresses gratitude to the contributing authors and the ISPRS Geospatial Week. [Extracted from the article]

This paper presents a study on the potential of ultra-high accurate UAV-based 3D data capture. It is motivated by a project aiming at the deformation monitoring of a ship lock and its surrounding. This study is part of a research and development project initiated by the German Federal Institute of Hydrology (BfG) in Koblenz in partnership with the Office of Development of Neckar River Heidelberg (ANH). For this first official presentation of the project, data from the first flight campaign will be analysed and presented. Despite the fact that monitoring aspects cannot be discussed before data from additional flight campaigns will be available later this year, our results from the first campaign highlight the potential of high-end UAV-based image and LiDAR sensors and their data fusion. So far, only techniques from engineering geodesy could fulfil the aspired accuracy demands in the range of millimetres. To the knowledge of the authors, this paper for the first time addresses such ultra-high accuracy applications by combing high precision UAV-based LiDAR and dense image matching. As the paper is written at an early stage of processing only preliminary results can be given here. [ABSTRACT FROM AUTHOR]

This work addresses the automatic reconstruction of objects useful for BIM, like walls, floors and ceilings, from meshed and textured mapped 3D point clouds of indoor scenes. For this reason, we focus on the semantic segmentation of 3D indoor meshes as the initial step for the automatic generation of BIM models. Our investigations are based on the benchmark dataset ScanNet, which aims at the interpretation of 3D indoor scenes. For this purpose it provides 3D meshed representations as collected from low cost range cameras. In our opinion such RGB-D data has a great potential for the automated reconstruction of BIM objects. [ABSTRACT FROM AUTHOR]

Urban environments with extended areas of poor GNSS coverage as well as indoor spaces that often rely on real-time SLAM algorithms for camera pose estimation require sophisticated georeferencing in order to fulfill our high requirements of a few centimeters for absolute 3D point measurement accuracies. Since we focus on image-based mobile mapping, we extended the structure-from-motion pipeline COLMAP with georeferencing capabilities by integrating exterior orientation parameters from direct sensor orientation or SLAM as well as ground control points into bundle adjustment. Furthermore, we exploit constraints for relative orientation parameters among all cameras in bundle adjustment, which leads to a significant robustness and accuracy increase especially by incorporating highly redundant multi-view image sequences. We evaluated our integrated georeferencing approach on two data sets, one captured outdoors by a vehicle-based multi-stereo mobile mapping system and the other captured indoors by a portable panoramic mobile mapping system. We obtained mean RMSE values for check point residuals between image-based georeferencing and tachymetry of 2 cm in an indoor area, and 3 cm in an urban environment where the measurement distances are a multiple compared to indoors. Moreover, in comparison to a solely image-based procedure, our integrated georeferencing approach showed a consistent accuracy increase by a factor of 2-3 at our outdoor test site. Due to pre-calibrated relative orientation parameters, images of all camera heads were oriented correctly in our challenging indoor environment. By performing self-calibration of relative orientation parameters among respective cameras of our vehicle-based mobile mapping system, remaining inaccuracies from suboptimal test field calibration were successfully compensated. [ABSTRACT FROM AUTHOR]

Modern airborne sensors integrate laser scanners and digital cameras for capturing topographic data at high spatial resolution. The capability of penetrating vegetation through small openings in the foliage and the high ranging precision in the cm range have made airborne LiDAR the prime terrain acquisition technique. In the recent years dense image matching evolved rapidly and outperforms laser scanning meanwhile in terms of the achievable spatial resolution of the derived surface models. In our contribution we analyze the inherent properties and review the typical processing chains of both acquisition techniques. In addition, we present potential synergies of jointly processing image and laser data with emphasis on sensor orientation and point cloud fusion for digital surface model derivation. Test data were concurrently acquired with the RIEGL LMS-Q1560 sensor over the city of Melk, Austria, in January 2016 and served as basis for testing innovative processing strategies. We demonstrate that (i) systematic effects in the resulting scanned and matched 3D point clouds can be minimized based on a hybrid orientation procedure, (ii) systematic differences of the individual point clouds are observable at penetrable, vegetated surfaces due to the different measurement principles, and (iii) improved digital surface models can be derived combining the higher density of the matching point cloud and the higher reliability of LiDAR point clouds, especially in the narrow alleys and courtyards of the study site, a medieval city. [ABSTRACT FROM AUTHOR]

Global image orientation techniques aim at estimating camera rotations and positions for a whole set of images simultaneously. One of the main arguments for these procedures is an improved robustness against drifting of camera stations in comparison to more classical sequential approaches. Usually, the process consists of computation of absolute rotations and, in a second step, absolute positions for the cameras. Either the first or both steps rely on the network of transformations arising from relative orientations between cameras. Therefore, the quality of the obtained absolute results is influenced by tensions in the network. These may e.g. be induced by insufficient knowledge of the intrinsic camera parameters. Another reason can be found in local weaknesses of image connectivity. We apply a hierarchical approach with intermediate bundle adjustment to reduce these effects. We adopt efficient global techniques which register image triplets based on fixed absolute camera rotations and scaled relative camera translations but do not involve scene structure elements in the fusion step. Our variant employs submodels of arbitrary size, orientation and scale, by computing relative rotations and scales between - and subsequently absolute rotations and scales for - submodels and is applied hierarchically. Furthermore we substitute classical bundle adjustment by a structureless approach based on epipolar geometry and augmented with a scale consistency constraint. [ABSTRACT FROM AUTHOR]

Recent years have shown a shift from pure geometric 3D city models to data with semantics. This is induced by new applications (e.g. Virtual/Augmented Reality) and also a requirement for concepts like Smart Cities. However, essential urban semantic data like building use categories is often not available. We present a first step in bridging this gap by proposing a pipeline to use crawled urban imagery and link it with ground truth cadastral data as an input for automatic building use classification. We aim to extract this city-relevant semantic information automatically from Street View (SV) imagery. Convolutional Neural Networks (CNNs) proved to be extremely successful for image interpretation, however, require a huge amount of training data. Main contribution of the paper is the automatic provision of such training datasets by linking semantic information as already available from databases provided from national mapping agencies or city administrations to the corresponding façade images extracted from SV. Finally, we present first investigations with a CNN and an alternative classifier as a proof of concept. [ABSTRACT FROM AUTHOR]

Ongoing innovations in matching algorithms are continuously improving the quality of geometric surface representations generated automatically from aerial images. This development motivated the launch of the joint ISPRS/EuroSDR project "Benchmark on High Density Aerial Image Matching", which aims on the evaluation of photogrammetric 3D data capture in view of the current developments in dense multi-view stereo-image matching. Originally, the test aimed on image based DSM computation from conventional aerial image flights for different landuse and image block configurations. The second phase then put an additional focus on high quality, high resolution 3D geometric data capture in complex urban areas. This includes both the extension of the test scenario to oblique aerial image flights as well as the generation of filtered point clouds as additional output of the respective multiview reconstruction. The paper uses the preliminary outcomes of the benchmark to demonstrate the state-of-the-art in airborne image matching with a special focus of high quality geometric data capture in urban scenarios. [ABSTRACT FROM AUTHOR]

Image-based mobile mapping systems enable an efficient acquisition of georeferenced image sequences, which can be used for geodata capture in subsequent steps. In order to provide accurate measurements in a given reference frame while e.g. aiming at high fidelity 3D urban models, high quality georeferencing of the captured multi-view image sequences is required. Moreover, sub-pixel accurate orientations of these highly redundant image sequences are needed in order to optimally perform steps like dense multiimage matching as a prerequisite for 3D point cloud and mesh generation. While direct georeferencing of image-based mobile mapping data performs well in open areas, poor GNSS coverage in urban canyons aggravates fulfilling these high accuracy requirements, even with high-grade inertial navigation equipment. Hence, we conducted comprehensive investigations aiming at assessing the quality of directly georeferenced sensor orientations as well as the expected improvement by image-based georeferencing in a challenging urban environment. Our study repeatedly delivered mean trajectory deviations of up to 80 cm. By performing image-based georeferencing using bundle adjustment for a limited set of cameras and a limited number of ground control points, mean check point residuals could be lowered from approx. 40 cm to 4 cm. Furthermore, we showed that largely automated image-based georeferencing is capable of detecting and compensating discontinuities in directly georeferenced trajectories. [ABSTRACT FROM AUTHOR]

Due to good scalability, systems for image-based dense surface reconstruction often employ stereo or multi-baseline stereo methods. These types of algorithms represent the scene by a set of depth or disparity maps which eventually have to be fused to extract a consistent, non-redundant surface representation. Generally the single depth observations across the maps possess variances in quality. Within the fusion process not only preservation of precision and detail but also density and robustness with respect to outliers are desirable. Being prune to outliers, in this article we propose a local median-based algorithm for the fusion of depth maps eventually representing the scene as a set of oriented points. Paying respect to scalability, points induced by each of the available depth maps are streamed to cubic tiles which then can be filtered in parallel. Arguing that the triangulation uncertainty is larger in the direction of image rays we define these rays as the main filter direction. Within an additional strategy we define the surface normals as the principle direction for median filtering/integration. The presented approach is straight-forward to implement since employing standard oc- and kd-tree structures enhanced by nearest neighbor queries optimized for cylindrical neighborhoods. We show that the presented method in combination with the MVS (Rothermel et al., 2012) produces surfaces comparable to the results of the Middlebury MVS benchmark and favorably compares to an state-of-the-art algorithm employing the Fountain dataset (Strecha et al., 2008). Moreover, we demonstrate its capability of depth map fusion for city scale reconstructions derived from large frame airborne imagery. [ABSTRACT FROM AUTHOR]

Bundle adjustment based on collinearity is the most widely used optimization method within image based scene reconstruction. It incorporates observed image coordinates, exterior and intrinsic camera parameters as well as object space coordinates of the observed points. The latter dominate the resulting nonlinear system, in terms of the number of unknowns which need to be estimated. In order to reduce the size of the problem regarding memory footprint and computational effort, several approaches have been developed to make the process more efficient, e.g. by exploitation of sparsity or hierarchical subdivision. Some recent developments express the bundle problem through epipolar geometry and scale consistency constraints which are free of object space coordinates. These approaches are usually referred to as structureless bundle adjustment. The number of unknowns in the resulting system is drastically reduced. However, most work in this field is focused on optimization towards speed and considers calibrated cameras, only. We present our work on structureless bundle adjustment, focusing on precision issues as camera calibration and residual weighting. We further investigate accumulation of constraint residuals as an approach to decrease the number of rows of the Jacobian matrix. [ABSTRACT FROM AUTHOR]

The recent advances in the field of computer-vision have opened the doors of many opportunities for taking advantage of these techniques and technologies in many fields and applications. Having a high demand for these systems in today and future vehicles implies a high production volume of video cameras. The above criterions imply that it is critical to design test systems which deliver fast and accurate calibration and optical-testing capabilities. In this paper we introduce new generation of test-stands delivering high calibration quality in single-shot calibration of fisheye surround-view cameras. This incorporates important geometric features from bundle-block calibration, delivers very high (sub-pixel) calibration accuracy, makes possible a very fast calibration procedure (few seconds), and realizes autonomous calibration via machines. We have used the geometrical shape of a Spherical Helix (Type: 3D Spherical Spiral) with special geometrical characteristics, having a uniform radius which corresponds to the uniform motion. This geometrical feature was mechanically realized using three dimensional truncated icosahedrons which practically allow the implementation of a spherical helix on multiple surfaces. Furthermore the test-stand enables us to perform many other important optical tests such as stray-light testing, enabling us to evaluate the certain qualities of the camera optical module. [ABSTRACT FROM AUTHOR]

The paper presents the implementation of a dense multi-view stereo matching pipeline for the evaluation of image sequences from a camera-based mobile mapping system. For this purpose the software system SURE is taken as a basis. Originally this system was developed to provide 3D point clouds or DEM from standard airborne and terrestrial image blocks. Since mobile mapping scenarios typically include stereo configurations with camera motion predominantly in viewing direction, processing steps like image rectification and structure computation of the existing processing pipeline had to be adapted. The presented investigations are based on imagery captured by the mobile mapping system of the Institute of Geomatics Engineering in the city center of Basel, Switzerland. For evaluation, reference point clouds from terrestrial laser scanning are used. Our first results already demonstrate a considerable increase in reliability and completeness of both depth maps and point clouds as result of the matching process. [ABSTRACT FROM AUTHOR]

This paper aims at façade reconstruction for subsequent enrichment of LOD2 building models. We use point clouds from dense image matching with imagery both from Mobile Mapping systems and oblique airborne cameras. The interpretation of façade structures is based on a geometric reconstruction. For this purpose a pre-segmentation of the point cloud into façade points and non-façade points is necessary. We present an approach for point clouds with limited geometric accuracy where a geometric segmentation might fail. Our contribution is a radiometric segmentation approach. Via local point features, based on a clustering in hue space, the point cloud is segmented into façade-points and non-façade points. This way, the initial geometric reconstruction step can be bypassed and point clouds with limited accuracy can still serve as input for the façade reconstruction and modelling approach. [ABSTRACT FROM AUTHOR]

Dense image matching methods enable the retrieval of dense surface information using any kind of imagery. The best quality can be achieved for highly overlapping datasets, which avoids occlusions and provides highly redundant observations. Thus, images are acquired close to each other. This leads to datasets with increasing size - especially when large scenes are captured. While image acquisition can be performed in relatively short time, more time is required for data processing due to the computational complexity of the involved algorithms. For the dense surface reconstruction task, Multi-View Stereo algorithms can be used - which are typically beneficial due to the efficiency of image matching on stereo models. Our dense image matching solution SURE uses such an approach, where the result of stereo matching is fused using a multi-stereo triangulation in order to exploit the available redundancy. One key challenge of such Multi-View Stereo methods is the selection of suitable stereo models, where object space information should be considered to avoid unnecessary processing. Subsequently, the dense image matching step provides up to one 3D point for each pixel, which leads to massive point clouds. This large amount of 3D data needs to be filtered and integrated efficiently in object space. Within this paper, we present an out-of-core octree, which enables neighborhood and overlap analysis between point clouds. It is used on low-resolution point clouds to support the stereo model selection. Also, this tree is designed for the processing of massive point clouds with low memory requirements and thus can be used to perform outlier rejection, redundancy removal and resampling. [ABSTRACT FROM AUTHOR]

In this article we present an algorithm for the fusion of depth images derived by dense image matching (DIM). One key idea of our algorithm is to generate a 2D triangulation for each available depth map in the image sequence using a restricted quadtrees (RQT). On the one hand this guarantees matching triangulations, on the other hand this creates the possibility to reduce points in the noise range not contributing to the geometry in a controlled manner. By vertex decimation computational efforts in subsequent processing steps are eased. In order to reduce IO overhead, the algorithm is designed in an iterative way: an initial triangulation is lifted to 3D space and, if pixel footprints are comparable, updated using depths of the subsequent map in the sequence. Previously not observed surface regions or surface patches observed only with adverse precision are removed from the existing model and updated by more appropriate triangulations. Thereby differences in scale across depth maps are handled which is particularly important to preserve details and obtain surfaces with the best reconstruction geometry. To remove outliers visibility constraints are forced. The input is overlapping depth images and their poses in space, the output are point coordinates representing the surface, their respective normals and to some degree spatial neighbourhood information of points represented as a non-watertight mesh. The performance of the algorithm will be evaluated on a close range and a oblique aerial dataset. [ABSTRACT FROM AUTHOR]

Both, improvements in camera technology and new pixel-wise matching approaches triggered the further development of software tools for image based 3D reconstruction. Meanwhile research groups as well as commercial vendors provide photogrammetric software to generate dense, reliable and accurate 3D point clouds and Digital Surface Models (DSM) from highly overlapping aerial images. In order to evaluate the potential of these algorithms in view of the ongoing software developments, a suitable test bed is provided by the ISPRS/EuroSDR initiative Benchmark on High Density Image Matching for DSM Computation. This paper discusses the proposed test scenario to investigate the potential of dense matching approaches for 3D data capture from oblique airborne imagery. For this purpose, an oblique aerial image block captured at a GSD of 6 cm in the west of Zürich by a Leica RCD30 Oblique Penta camera is used. Within this paper, the potential test scenario is demonstrated using matching results from two software packages, Agisoft PhotoScan and SURE from University of Stuttgart. As oblique images are frequently used for data capture at building facades, 3D point clouds are mainly investigated at such areas. Reference data from terrestrial laser scanning is used to evaluate data quality from dense image matching for several facade patches with respect to accuracy, density and reliability. [ABSTRACT FROM AUTHOR]

The density and data volumes for recorded 3D surfaces increase steadily. In particular during photogrammetric surface reconstruction and laser scanning applications these volumes often exceed the limits of the available hardware and software. The large point clouds and meshes acquired during the projects contain billions of vertices and require scalable data handling frameworks for further processing. Beside the scalability to big data, these methods also should adapt to non-uniform data density and precision resulting from varying acquisition distances, as required for data from Photogrammetry and Laser Scanning. For this purpose, we present a framework called Pine Tree, which is based on an out-of-core octree. It enables fast local data queries, such as nearest neighbor queries for filtering, while dynamically storing and loading data from the hard disk. This way, large amounts of data can be processed on limited main memory. Within this paper, we describe the Pine Tree approach as well as its underlying methods. Furthermore, examples for a filtering task are shown, where overlapping point clouds are thinned out by preserving the locally densest point cloud only. By adding an optional redundancy constraint, point validation and outlier rejection can be applied. [ABSTRACT FROM AUTHOR]