Wolfgang Förstner's research while affiliated with University of Bonn and other places

Publications (161)

Chapter
Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography, essential and fundamental matrix estimation. The main advantage of such solvers is that their sample size is small...
Preprint
Full-text available
Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography, essential and fundamental matrix estimation. The main advantage of such solvers is that their sample size is small...
Chapter
Estimating uncertainty of camera parameters computed in Structure from Motion (SfM) is an important tool for evaluating the quality of the reconstruction and guiding the reconstruction process. Yet, the quality of the estimated parameters of large reconstructions has been rarely evaluated due to the computational challenges. We present a new algori...
Preprint
Full-text available
Estimating uncertainty of camera parameters computed in Structure from Motion (SfM) is an important tool for evaluating the quality of the reconstruction and guiding the reconstruction process. Yet, the quality of the estimated parameters of large reconstructions has been rarely evaluated due to the computational challenges. We present a new algori...
Conference Paper
Full-text available
Bundle adjustment is a central part of most visual SLAM and Structure from Motion systems and thus a relevant component of UAVs equipped with cameras. This paper makes two contributions to bundle adjustment. First, we present a novel approach which exploits trifocal constraints, i.e., constraints resulting from corresponding points observed in thre...
Conference Paper
Full-text available
Bundle adjustment is a central part of most visual SLAM and Structure from Motion systems and thus a relevant component of UAVs equipped with cameras. This paper makes two contributions to bundle adjustment. First, we present a novel approach which exploits trifocal constraints, i.e., constraints resulting from corresponding points observed in thre...
Chapter
Bundle adjustment is a unified method to simultaneously estimate the internal and external camera parameters and the 3D coordinates of the scene points in a statistically optimal manner.
Chapter
This chapter assembles the necessary tools for performing parameter estimation from redundant measurements in the context of geometric computation within photogrammetric computer vision, with an emphasis placed on tools for evaluating the results of parameter estimation.
Chapter
A single image of a scene is useful in various applications, such as ego-motion determination or partial scene reconstruction. We discuss models for cameras, develop methods for determining their parameters and provide tools for inferring 3D information from a single image.
Chapter
This chapter collects the basic terms from probability theory and statistics. It motivates the axiomatic approach for the concept of probability, introduces the concept of a random variable, describes the key properties of the main distributions of random variables occurring when modelling observational uncertainties and testing hypotheses, and pro...
Chapter
This chapter discusses the representation of uncertain homogeneous. We introduce a representation of the uncertainty which is minimal, thus does not contain singular covariance matrices, and develop methods for the estimation of geometric elements and transformation parameters.
Chapter
This chapter discusses transformations of geometric entities.
Chapter
While classical projective geometry in general does not distinguish between the two opposite directions of a line or the two sides of a plane, oriented projective geometry provides a framework that accounts for situations where it is very useful to take the orientation of entities into account.
Chapter
A pair of perspective images taken from two positions such that they show the scene from different directions is sufficient to reconstruct it without having pre-knowledge about it. We provide algorithms for recovering the orientation of the image pair and for determining the 3D coordinates of scene points.
Chapter
This chapter addresses the problem of reconstructing the visible surface from the 3D points of the photogrammetric models derived from two or more images.
Chapter
This chapter discusses the basic geometry and orientation of image triplets. The higher redundancy caused by observing the scene in three instead of only two images, as before, leads to a number of advantages, so it is useful to treat the image triplet in detail.
Chapter
This chapter motivates and introduces homogeneous coordinates for representing geometric entities. We aim at exploiting the algebraic properties of the representations of geometric entities and at giving geometrically intuitive interpretations.
Chapter
This chapter provides the necessary tools for performing hypothesis tests, evaluates their performance and provides lower bounds for detectable deviations from a given hypothesis. For the most relevant testing tasks we collect the adequate tests. These will be used in order to evaluate estimation results applied to geometric reasoning tasks.
Chapter
This chapter discusses rotations in 3D as special transformations of points.
Chapter
This chapter discusses geometric operations of geometric entities. It covers a wide range of constructions, constraints, and functions based on points, lines, planes, conics, and quadrics, including elements at infinity.
Article
Full-text available
Our objective is the interpretation of facade images in a top-down manner, using a Markov marked point process formulated as a Gibbs process. Given single rectified facade images, we aim at the accurate detection of relevant facade objects as windows and entrances, using prior knowledge about their possible configurations within facade images. We r...
Article
Full-text available
Our objective is the interpretation of facade images in a top-down manner, using a Markov marked point process formulated as a Gibbs process. Given single rectified facade images, we aim at the accurate detection of relevant facade objects as windows and entrances, using prior knowledge about their possible configurations within facade images. We r...
Conference Paper
Full-text available
Online pose estimation and mapping in unknown environments is essential for most mobile robots. Especially autonomous unmanned aerial vehicles require good pose estimates at comparably high frequencies. In this paper, we propose an effective system for online pose and simultaneous map estimation designed for lightweight UAVs. Our system consists of...
Chapter
This book is about concepts and methods for developing computer vision systems for automatically analysing images, with a focus on the main application areas of photogrammetry, specifically mapping and image-based metrology.
Book
This textbook offers a statistical view on the geometry of multiple view analysis, required for camera calibration and orientation and for geometric scene reconstruction based on geometric image features. The authors have backgrounds in geodesy and also long experience with development and research in computer vision, and this is the first book to...
Chapter
This chapter gives an overview of the specific models required for orientation and reconstruction based on images of a scene.
Article
Full-text available
Fisheye cameras offer a large field of view, which is important for several robotics applications as a larger field of view allows for covering a large area with a single image. In contrast to classical cameras, however, fisheye cameras cannot be approximated well using the pinhole camera model and this renders the computation of depth information...
Conference Paper
Full-text available
This paper presents a system for direct geo-localization of a MAV in an unknown environment using visual odometry and precise real time kinematic (RTK) GPS information. Visual odometry is performed with a multi-camera system with four fisheye cameras that cover a wide field of view which leads to better constraints for localization due to long trac...
Conference Paper
Full-text available
In this paper we present our system for visual odometry that performs a fast incremental bundle adjustment for real-time structure and motion estimation in an unknown scene. It is applicable to image streams of a calibrated multi-camera system with omnidirectional cameras. In this paper we use an autonomously flying octocopter that is equipped for...
Conference Paper
Full-text available
This paper presents a system for direct geo-localization of a MAV in an unknown environment using visual odometry and precise real time kinematic (RTK) GPS information. Visual odometry is performed with a multi-camera system with four fisheye cameras that cover a wide field of view which leads to better constraints for localization due to long trac...
Conference Paper
Full-text available
Automated image interpretation is a powerful instrument for the acquisition of objective and precise phenotypic data with high throughput. Cluster length, cluster width, berry size and cluster compactness are four important phenotypic traits with impact on cluster morphology, health status and yield. For the image-based evaluation of this grapevine...
Conference Paper
Full-text available
For situations, where mapping is neither possible from high altitudes nor from the ground, we are developing an autonomous micro aerial vehicle able to fly at low altitudes in close vicinity of obstacles. This vehicle is based on a MikroKopter octocopter platform (maximum total weight: 5kg), and contains a dual frequency GPS board, an IMU, a compas...
Article
Full-text available
The berry size is one of the most important fruit traits in grapevine breeding. Non-invasive, image-based phenotyping promises a fast and precise method for the monitoring of the grapevine berry size. In the present study an automated image analyzing framework was developed in order to estimate the size of grapevine berries from images in a high-th...
Article
Full-text available
The evaluation of phenotypic characters of grapevines is required directly in vineyards and is strongly limited by time, costs and the subjectivity of person in charge. Sensor-based techniques are prerequisite in order to allow non-invasive phenotyping of individual plant traits, to increase the quantity of object records and to reduce error variat...
Conference Paper
Full-text available
This paper presents a concept and first experiments on a keyframe-based incremental bundle adjustment for real-time structure and motion estimation in an unknown scene. In order to avoid periodic batch steps, we use the software iSAM2 for sparse nonlinear incremental optimization, which is highly efficient through incremental variable reordering an...
Article
Many vision applications rely on local features for image analysis, notably in the areas of object recognition, image registration and camera calibration. One important example in photogrammetry are fully automatic algorithms for relative image orientation. Such applications rely on a matching algorithm to extract a sufficient number of correct fea...
Article
Full-text available
We present a calibration method for multi-view cameras that provides a rigorous maximum likelihood estimation of the mutual orientation of the cameras within a rigid multi-camera system. No calibration targets are needed, just a movement of the multi-camera system taking synchronized images of a highly textured and static scene. Multi-camera system...
Article
Data partitioning is a common problem in the field of point cloud and image processing applicable to segmentation and clustering. The general principle is to have high similarity of two data points, e.g.pixels or 3D points, within one region and low similarity among regions. This pair-wise similarity between data points can be represented in an att...
Article
Full-text available
QTL-analysis (quantitative trait loci) and marker development rely on efficient phenotyping techniques. Objectivity and precision of a phenotypic data evaluation is crucial but time consuming. In the present study a high-throughput image interpretation tool was developed to acquire automatically number, size, and volume of grape berries from RGB (r...
Article
Full-text available
In this paper, we propose an incremental learning strategy for import vector machines (IVM), which is a sparse kernel logistic regression approach. We use the procedure for the concept of self-training for sequential classification of hyperspectral data. The strategy comprises the inclusion of new training samples to increase the classification acc...
Article
Up-to-date digital photogrammetry involves operations on huge data sets, and with classical image processing procedures it might be time consuming to find out the best solution. One of the key tasks is to detect outliers in given data, eg for curve fitting or image matching. The problem is hard as the number of outliers is usually large, possibly l...
Conference Paper
Full-text available
Our objective is the categorization of the most dominant objects in facade images, like windows, entrances and balconies. In order to execute an image interpretation of complex scenes we need an interaction between low level bottom-up feature detection and highlevel inference from top-down. A top-down approach would use results of a bottom-up detec...
Article
Full-text available
The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color featu...
Article
Full-text available
Automatic building extraction from remotely sensed images is a research topic much more significant than ever. One of the key issues is object and image representation. Markov random fields usually referring to the pixel level can not represent high-level knowledge well. On the contrary, marked point processes can not represent low-level informatio...
Article
Full-text available
We propose a framework for operator guidance during the image acquisition process for reliable multi-view stereo reconstruction. Goal is to achieve full coverage of the object and sufficient overlap. Multi-view stereo is a commonly used method to reconstruct both camera trajectory and 3D object shape. After determining an initial solution, a globa...
Conference Paper
Full-text available
We present a novel approach for a rigorous bundle adjustment for omnidirectional and multi-view cameras, which enables an efficient maximum-likelihood estimation with image and scene points at infinity. Multi-camera systems are used to increase the resolution, to combine cameras with different spectral sensitivities (Z/I DMC, Vexcel Ultracam) or –...
Article
Te sting and estimation using homogeneous coordinates and matrices has to cope with obstacles such as singularities of covariance matrices and redundant parametrisations. The paper proposes a representation of the uncertainty of all types of geometric entities which (1) only requires the minimum number of parameters, (2) is free of singularities, (...
Article
Automatic scene interpretation of aerial images is a major purpose of photogrammetry. Therefore, we want to improve building detection by exploring the "life-time" of stable and relevant image features in scale space. We use watersheds for feature extraction to gain a topologically consistent map. We will show that characteristic features for build...
Article
We introduce an innovative incremental learner called incremental import vector machines (I2VM). The kernel-based discriminative approach is able to deal with complex data distributions. Additionally, the learner is sparse for an efficient training and testing and has a probabilistic output. We particularly investigate the reconstructive component...
Article
We propose a framework for object tracking in image sequences, following the concept of tracking-by-segmentation. The separation of object and background is achieved by a consecutive semantic superpixel segmentation of the images, yielding tight object boundaries. I.e., in the first image a model of the object's characteristics is learned from an i...
Conference Paper
Semantic scene interpretation as a collection of meaningful regions in images is a fundamental problem in both photogrammetry and computer vision. Images of man-made scenes exhibit strong contextual dependencies in the form of spatial and hierarchical structures. In this paper, we introduce a hierarchical conditional random field to deal with the p...
Conference Paper
Full-text available
The classification of large areas consisting of multiple scenes is challenging regarding the handling of large and therefore mostly inhomogeneous data sets. Moreover, large data sets demand for computational efficient methods. We propose a method, which enables the efficient multi-class classification of large neighboring Landsat scenes. We use an...
Conference Paper
Full-text available
We present a novel surface model and reconstruction method for man-made environments that take prior knowledge about topology and geometry into account. The model favors but is not limited to horizontal and vertical planes that are pairwise orthogonal. The reconstruction method does not require one particular class of sensors, as long as a triangul...
Chapter
We propose a surface segmentation method based on Fast Marching Farthest Point Sampling designed for noisy, visually reconstructed point clouds or laser range data. Adjusting the distance metric between neighboring vertices we obtain robust, edge-preserving segmentations based on local curvature. We formulate a cost function given a segmentation in...
Article
We develop a qualitative measure for the completeness and complementarity of sets of local features in terms of covering relevant image information. The idea is to interpret feature detection and description as image coding, and relate it to classical coding schemes like JPEG. Given an image, we derive a feature density from a set of local features...
Conference Paper
We propose a concept for scene interpretation with integrated hierarchical structure. This hierarchical structure is used to detect mereological relations between complex objects as buildings and their parts, e. g., windows. We start with segmenting regions at many scales, arranging them in a hierarchy, and classifying them by a common classifier....
Conference Paper
Full-text available
Literally thousands of articles on optical flow algorithms have been published in the past thirty years. Only a small subset of the suggested algorithms have been analyzed with respect to their performance. These evaluations were based on black-box tests, mainly yielding information on the average accuracy on test-sequences with ground truth. No th...
Article
Three methods of automatic classification of leaf diseases are described based on high-resolution multispectral stereo images. Leaf diseases are economically important as they can cause a loss of yield. Early and reliable detection of leaf diseases has important practical relevance, especially in the context of precision agriculture for localized t...
Conference Paper
Full-text available
Wir stellen einen Ansatz für eine strenge Bündelausgleichung für Multikamerasysteme vor. Hierzu verwenden wir eine minimale Repräsentation von homogenen Koordinatenvektoren für eine Maximum-Likelihood-Schätzung. Statt den Skalierungsfaktor von homogenen Vektoren durch Verwendung von euklidischen Größen zu eliminieren, werden die homogenen Koordinat...
Article
Wir präsentieren einen Ansatz, um lange Bildfolgen einer omnidirektionalen Kamera mittels Bündelausgleichung auszuwerten. Wir nutzen Bilder des Multikamerasystems Ladybug3 von PointGrey, welches aus sechs Einzelkameras besteht. Die gegenseitige Überdeckung aufeinanderfolgender Bilder ist groß; Verknüpfungen zwischen weit entfernten Bildern kommen n...
Conference Paper
In recent years, the classification task of building facade images receives a great deal of attention in the photogrammetry community. In this paper, we present an approach for regionwise classification using an efficient randomized decision forest classifier and local features. A conditional random field is then introduced to enforce spatial consi...
Article
Full-text available
High-dimensional data structures occur in many fields of computer vision and machine learning. Transformation between two high-dimensional spaces usually involves the determination of a large amount of parameters and requires much labeled data to be given. There is much interest in reducing dimensionality if a lower-dimensional structure is underly...
Conference Paper
This paper presents a novel scheme for automatically aligning two widely separated 3D scenes via the use of viewpoint invariant features. The key idea of the proposed method is following. First, a number of dominant planes are extracted in the SfM D point cloud using a novel method integrating RANSAC and MDL to describe the underlying 3D geometry i...
Conference Paper
Full-text available
We discuss the utility of dimensionality reduction algorithms to put data points in high dimensional spaces into correspondence by learning a transformation between assigned data points on a lower dimensional structure. We assume that similar high dimensional feature spaces are characterized by a similar underlying low dimensional structure. To ena...
Conference Paper
Estimation using homogeneous entities has to cope with obstacles such as singularities of covariance matrices and redundant parametrizations which do not allow an immediate definition of maximum likelihood estimation and lead to estimation problems with more parameters than necessary. The paper proposes a representation of the uncertainty of all ty...
Conference Paper
Full-text available
Logistic Regression has become a commonly used classifier, not only due to its probabilistic output and its direct usage in multi-class cases. We use a sparse Kernel Logistic Regression approach - the Import Vector Machines - for land cover classification. We improve our segmentation results applying a Discriminative Random Field framework on the p...
Conference Paper
A multi-class traffic scene segmentation approach based on scene flow data is presented. Opposed to many other approaches using color or texture features, our approach is purely based on dense depth and 3D motion information. Using prior knowledge on tracked objects in the scene and the pixel-wise uncertainties of the scene flow data, each pixel i...
Conference Paper
In this paper we propose a novel approach to bundle adjust-ment for large-scale camera configurations. The method does not need to include the 3D points in the optimization as parameters. Additionally, we model the parameters of a camera only relative to a nearby camera to achieve a stable estimation of all cameras. This guarantees to yield a norma...
Conference Paper
This paper presents a generic framework for curb detection and reconstruction in the context of driver assistance systems. Based on a 3D point cloud, we estimate the parameters of a 3D curb model, incorporating also the curb adjacent surfaces, e.g. street and sidewalk. We apply an iterative two step approach. First, the measured 3D points, e.g., ob...
Article
The paper presents a method for automatically and optimally de-termining the vanishing points of a single image, and in case the interior orientation is given, the rotation of an image with respect to the intrinsic coordinate system of a lego land scene. We per-form rigorous testing and estimation in order to be as independent on control parameters...
Article
We present a fast automatic reproducible method for 3d se-mantic segmentation of magnetic resonance images of the knee. We for-mulate a single global model that allows to jointly segment all classes. The model estimation was performed automatically without manual in-teraction and parameter tuning. The segmentation of a magnetic reso-nance image wit...
Conference Paper
graph, region hierarchy graph. Abstract: Multi-class image classification has made significant advances in recent years through the combination of local and global features. This paper proposes a novel approach called hierarchical conditional random field (HCRF) that explicitly models region adjacency graph and region hierarchy graph structure of a...