Search

We consider the problem of non-rigid, point-to-point registration of two 3D surfaces. To avoid restrictions on the topology, we represent the surfaces as a level-set of their signed distance function. Correspondence is established by finding a displacement field that minimizes the sum of squared difference between the function values as well as their mean curvature. We use a variational formulation of the problem, which leads to a non-linear elliptic partial differential equation for the displacement field. The main contribution of this paper is the application of an adaptive finite element discretization for solving this non-linear PDE. Our code uses the software library DUNE, which in combination with pre- and post-processing through ITK leads to a powerful tool for solving this type of problem. This is confirmed by our experiments on various synthetic and medical examples. We show in this work that our numerical scheme yields accurate results using only a moderate number of elements even for complex problems. [ABSTRACT FROM AUTHOR]

We introduce a new approach for spline-based elastic image registration using both point landmarks and intensity information. As underlying deformation model we use Gaussian elastic body splines (GEBS), which are analytic solutions of the Navier equation under Gaus- sian forces and are represented by matrix-valued basis functions. We also incorporate landmark localization uncertainties represented by weight matrices. Our approach is formulated as an energy-minimizing functional that incorporates landmark and intensity information as well as a regularization based on GEBS. Since the approach is based on a physical deformation model, cross-effects in elastic deformations can be handled. We demonstrate the applicability of our scheme based on MR images of the human brain. It turns out that the new scheme is superior to a pure landmark-based as well as a pure intensity-based scheme. [ABSTRACT FROM AUTHOR]

In the research area of historical documents it is of high interest to reconstruct the process of the emergence of a historical typesetted document. Therefore, the chronological order of the different versions of a typesetted document has to be reconstructed. This is done by manually finding differences in two versions and then deciding on the order between these two versions. In this paper we present an approach to automate the search for differences in both images. This approach uses a globally optimal image matching technique to overlay both images and colors the differences accordingly. We also present a real-world application for this approach on digitized versions of a historical book. [ABSTRACT FROM AUTHOR]

Similarity measure is one of the main factors that affect the accuracy of intensity-based 2D/3D registration of X-ray fluoroscopy to CT images. Information theory has been used to derive similarity measure for image registration leading to the introduction of mutual information, an accurate similarity measure for multi-modal and mono-modal image registration tasks. However, it is known that the standard mutual information measure only takes intensity values into account without considering spatial information and its robustness is questionable. Previous attempt to incorporate spatial information into mutual information either requires computing the entropy of higher dimensional probability distributions, or is not robust to outliers. In this paper, we show how to incorporate spatial information into mutual information without suffering from these problems. Using a variational approximation derived from the Kullback-Leibler bound, spatial information can be effectively incorporated into mutual information via energy minimization. The resulting similarity measure has a least-squares form and can be effectively minimized by a multi-resolution Levenberg-Marquardt optimizer. Experimental results are presented on datasets of two applications: (a) intra-operative patient pose estimation from a few (e.g. 2) calibrated fluoroscopic images, and (b) post-operative cup alignment estimation from single X-ray radiograph with gonadal shielding. [ABSTRACT FROM AUTHOR]

We consider the problem of simultaneously registering several images to a 3D model. We propose a global approach based on mutual information that extends previous methods to incorporate the color, and does not require segmentation or feature extraction. We give a stochastic model for joint optimization of multiple image-to-model alignment and we propose a heuristic to solve it. Experiments with synthetic models showed that our algorithm is robust to varying illumination and surface characteristics. Experiments with real data showed that we can achieve very good accuracy even for an object with highly specular surface, in moderate lighting conditions. [ABSTRACT FROM AUTHOR]

Although lasers are widely used for welding in precision engineering industry, it is still a challenge to achieve high accuracy in creating and positioning welding spots at extremely high processing speed. Towards this end, we propose a system for monitoring the welding process in order to ensure good quality of the welding spots. Our technology enables high speed image acquisition confocally to the laser beam with a direct view onto the melt. This innovative system permits accurate estimation of the melt pool's position and radius, which, however, must be performed at frame rates above 200 fps. We therefore employ fast correlation based approaches for sampling the melt pool's contour and robustly fitting a circle to it. In addition, the approaches enable sputter detection via outlier classification. To assess the performance of each presented method, extensive experiments are conducted. The proposed paradigms can furthermore be conveniently adapted to a variety of problems dealing with rapid shape estimation in noisy environments. [ABSTRACT FROM AUTHOR]

The relationship between geometric folding of the chromatin fiber and genome function is a key issue in cell biology. We propose different approaches based on statistical shape theory to investigate the geometric variability of chromatin folding in nuclei of interphase human fibroblasts. Our main purpose is to assess the degree of variability of folding of the chromatin fiber, measured by fluorescent in situ hybridization, using BAC probes in combination with 3D confocal microscopy. We employ point-based registration, the complex Bingham distribution, generalized Procrustes analysis, and the Kendall spherical coordinate system. The approaches have been applied using 337 3D multi-channel microscopy images. We have analyzed the geometric structure formed by gene-rich highly expressed genomic regions and areas that are gene-poor and have a low transcriptional activity. It turned out that the structure formed by these genomic regions exhibit high shape variation, however, most of them can be characterized by a non-uniform shape distribution. [ABSTRACT FROM AUTHOR]

Model-based image interpretation extracts high-level information from images using a priori knowledge about the object of interest. The computational challenge is to determine the model parameters that best match a given image by searching for the global optimum of the involved objective function. Unfortunately, this function is usually designed manually, based on implicit and domain-dependent knowledge, which prevents the fitting task from yielding accurate results. In this paper, we demonstrate how to improve model fitting by learning objective functions from annotated training images. Our approach automates many critical decisions and the remaining manual steps hardly require domain-dependent knowledge. This yields more robust objective functions that are able to achieve the accurate model fit. Our evaluation uses a publicly available image database and compares the obtained results to a recent state-of-the-art approach. [ABSTRACT FROM AUTHOR]

This paper presents a real-time system for vision-based pedestrian recognition from a moving vehicle-mounted catadioptric camera. For efficiency, a rectification of the catadioptric image using a virtual cylindrical camera is employed. We propose a novel hybrid combination of a boosted cascade of wavelet-based classifiers with a subsequent texture-based neural network involving adaptive local features as final cascade stage. Within this framework, both fast object detection and powerful object classification are combined to increase the robustness of the recognition system. Further, we compare the hybrid cascade framework to a state-of-the-art multi-cue pedestrian recognition system utilizing shape and texture cues. Image distortions of the objects of interest due to the virtual cylindrical camera transformation are both explicitly and implicitly addressed by shape transformations and machine learning techniques. In extensive experiments, both systems under consideration are evaluated on a real-world urban traffic dataset. Results show the contributions of the various components in isolation and document superior performance of the proposed hybrid cascade system. [ABSTRACT FROM AUTHOR]

In this article we present EANT, a method that creates neural networks (NNs) by evolutionary reinforcement learning. The structure of NNs is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES. EANT can create NNs that are very specialised; they achieve a very good performance while being relatively small. This can be seen in experiments where our method competes with a different one, called NEAT, to create networks that control a robot in a visual servoing scenario. [ABSTRACT FROM AUTHOR]

We address the problem of describing the mean object for a set of planar shapes in the case that the considered dissimilarity measures are semi-metrics, i.e. in the case that the triangle inequality is generally not fulfilled. To this end, a matching of two planar shapes is computed by cutting an appropriately defined graph the edge weights of which encode the local similarity of respective contour parts on either shape. The cost of the minimum cut can be interpreted as a semi-metric on the space of planar shapes. Subsequently, we introduce the notion of a mean shape for the case of semi-metrics and show that this allows to perform a shape retrieval which mimics human notions of shape similarity. [ABSTRACT FROM AUTHOR]

We present a new technique for the extraction of features from 3D volumetric data sets based on group integration. The features are invariant to translation, rotation and global radial deformations. They are robust to local arbitrary deformations and nonlinear gray value changes, but are still sensitive to fine structures. On a data set of 389 confocally scanned pollen from 26 species we get a precision/recall of 99.2% with a simple 1NN classifier. On volumetric transmitted light data sets of about 180,000 airborne particles, containing about 22,700 pollen grains from 33 species, recorded with a low-cost optic in a fully automated online pollen monitor the mean precision for allergenic pollen is 98.5% (recall: 86.5%) and for the other pollen 97.5% (recall: 83.4%). [ABSTRACT FROM AUTHOR]

We present a model for learning convex kernel combinations in classification problems with structured output domains. The main ingredient is a hidden Markov model which forms a layered directed graph. Each individual layer represents a multilabel version of nonlinear kernel discriminant analysis for estimating the emission probabilities. These kernel learning machines are equipped with a mechanism for finding convex combinations of kernel matrices. The resulting kernelHMM can handle multiple partial paths through the label hierarchy in a consistent way. Efficient approximation algorithms allow us to train the model to large-scale learning problems. Applied to the problem of document categorization, the method exhibits excellent predictive performance. [ABSTRACT FROM AUTHOR]

Interest point detection in still images is a well-studied topic in computer vision. In the spatiotemporal domain, however, it is still unclear which features indicate useful interest points. In this paper we approach the problem by learning a detector from examples: we record eye movements of human subjects watching video sequences and train a neural network to predict which locations are likely to become eye movement targets. We show that our detector outperforms current spatiotemporal interest point architectures on a standard classification dataset. [ABSTRACT FROM AUTHOR]

This paper presents a reliable coin recognition system that is based on a registration approach. To optimally align two coins we search for a rotation in order to reach a maximal number of colinear gradient vectors. The gradient magnitude is completely neglected. After a quantization of the gradient directions the computation of the induced similarity measure can be done efficiently in the Fourier domain. The classification is realized with a simple nearest neighbor classification scheme followed by several rejection criteria to meet the demand of a low false positive rate. [ABSTRACT FROM AUTHOR]

Glaucoma is one of the most common causes of blindness and it is becoming even more important considering the ageing society. Because healing of died retinal nerve fibers is not possible early detection and prevention is essential. Robust, automated mass-screening will help to extend the symptom-free life of affected patients. We devised a novel, automated, appearance based glaucoma classification system that does not depend on segmentation based measurements. Our purely data-driven approach is applicable in large-scale screening examinations. It applies a standard pattern recognition pipeline with a 2-stage classification step. Several types of image-based features were analyzed and are combined to capture glaucomatous structures. Certain disease independent variations such as illumination inhomogeneities, size differences, and vessel structures are eliminated in the preprocessing phase. The "vessel-free" images and intermediate results of the methods are novel representations of the data for the physicians that may provide new insight into and help to better understand glaucoma. Our system achieves 86 % success rate on a data set containing a mixture of 200 real images of healthy and glaucomatous eyes. The performance of the system is comparable to human medical experts in detecting glaucomatous retina fundus images. [ABSTRACT FROM AUTHOR]

In this paper we propose a generative statistical approach for the three dimensional (3D) extraction of the branching structure of unfoliaged deciduous trees from urban image sequences. The trees are generatively modeled in 3D by means of L-systems. A statistical approach, namely Markov Chain Monte Carlo - MCMC is employed together with cross correlation for extraction. Thereby we overcome the complexity and uncertainty of extracting and matching branches in several images due to weak contrast, background clutter, and particularly the varying order of branches when projected into different images. First results show the potential of the approach. [ABSTRACT FROM AUTHOR]

Ever since the first fishermen ventured into the sea, tides have been the subject of intense human observation. As a result, computational models and ‘tide predicting machines', mechanical computers for predicting tides have been developed over 100 years ago. In this work we propose a statistical model for short-term prediction of sea levels at high tide in the tide influenced part of the Weser at Vegesack. The predictions made are based on water level measurements taken at different locations downriver and in the German Bight. The system has been integrated tightly into the decision making process at the Bremen Dike Association on the Right Bank of the Weser. [ABSTRACT FROM AUTHOR]

We propose an unsupervised "local learning" algorithm for learning a metric in the input space. Geometrically, for a given query point, the algorithm finds the minimum volume ellipsoid (MVE) covering its neighborhood which characterizes the correlations and variances of its neighborhood variables. Algebraically, the algorithm maximizes the determinant of the local covariance matrix which amounts to a convex optimization problem. The final matrix parameterizes a Mahalanobis metric yielding the MVE metric (MVEM). The proposed metric was tested in a supervised learning task and showed promising and competitive results when compared with state of the art metrics in the literature. [ABSTRACT FROM AUTHOR]

Most face recognition systems are based on some form of batch learning. Online face recognition is not only more practical, it is also much more biologically plausible. Typical batch learners aim at minimizing both training error and (a measure of) hypothesis complexity. We show that the same minimization can be done incrementally as long as some form of "scaffolding" is applied throughout the learning process. Scaffolding means: make the system learn from samples that are neither too easy nor too difficult at each step. We note that such learning behavior is also biologically plausible. Experiments using large sequences of facial images support the theoretical claims. The proposed method compares well with other, numerical calculus-based online learners. [ABSTRACT FROM AUTHOR]

Deblurring is important in many visual systems. This paper presents a novel approach for nonstationary blurred image reconstruction with ringing reduction in a variational Bayesian learning and regularization framework. Our approach makes effective use of the image statistical prior and image local spatial conditions through the whole learning scheme. A nature image statistics based marginal prior distribution is used not only for blur kernel estimation but also for image reconstruction. For an ill-posed blur estimation problem, variational Bayesian ensemble learning can achieve a tractable posterior using an image statistic prior which is translation and scale-invariant. During the deblurring, nonstationary blurry images have stronger ringing effects. We thus propose an iterative reweighted regularization function based on the use of an image statistical prior and image local spatial conditions for perceptual image deblurring. [ABSTRACT FROM AUTHOR]

A natural (human) eye can easily detect large visual patterns or objects emerging from spatially distributed discrete entities. This aspect of pattern analysis has been barely addressed in literature. We propose a biologically inspired approach derived from the concept of visual attention to associate together the distributed pieces of macro level patterns. In contrast to the usual approach practiced by the existing models of visual attention, this paper introduces a short-term excitation on the features and locations related to the current focus of attention in parallel to the spatial inhibition of return. This causes the attention system to fixate on analogous units in the scene that may formulate a meaningful global pattern. It is evident from the results of experiments that the outcome of this process can help in widening the scope of intelligent machine vision. [ABSTRACT FROM AUTHOR]

It is well known that linear filters are not powerful enough for many low-level image processing tasks. But it is also very difficult to design robust non-linear filters that respond exclusively to features of interest and that are at the same time equivariant with respect to translation and rotation. This paper proposes a new class of rotation-equivariant non-linear filters that is based on the principle of group integration. These filters become efficiently computable by an iterative scheme based on repeated differentiation of products and summations of the intermediate results. Our experiments show that the proposed filter detects pollen porates with only half as many errors than alternative approaches, when high localization accuracy is required. [ABSTRACT FROM AUTHOR]

In this paper, the properties of a novel color image filtering technique capable of impulse noise removal and edge enhancement are analyzed. The new filtering design is a generalization of the well known Vector Median Filter. The proposed filtering class is minimizing the cumulated dissimilarity measure of a group of pixels from the filtering window. The described filter is computationally efficient, easy to implement and very effective in suppressing impulsive noise, while preserving image details and strongly enhancing its edges. [ABSTRACT FROM AUTHOR]

Research on EEG based brain-computer-interfaces (BCIs) aims at steering devices by thought. Even for simple applications, BCIs require an extremely effective data processing to work properly because of the low signal-to-noise-ratio (SNR) of EEG signals. Spatial filtering is one successful preprocessing method, which extracts EEG components carrying the most relevant information. Unlike spatial filtering with Common Spatial Patterns (CSP), Adaptive Spatial Filtering (ASF) can be adapted to freely selectable regions of interest (ROI) and with this, artifacts can be actively suppressed. In this context, we compare the performance of ASF with ROIs selected using anatomical a-priori information and ASF with numerically optimized ROIs. Therefore, we introduce a method for data driven spatial filter adaptation and apply the achieved filters for classification of EEG data recorded during imaginary movements of the left and right hand of four subjects. The results show, that in the case of artifact-free datasets, ASFs with numerically optimized ROIs achieve classification rates of up to 97.7 % while ASFs with ROIs defined by anatomical heuristic stay at 93.7 % for the same data. Otherwise, with noisy datasets, the former brake down (66.7 %) while the latter meet 95.7 %. [ABSTRACT FROM AUTHOR]

Thinning on binary images is an iterative layer by layer erosion until only the "skeletons" of the objects are left. This paper presents an efficient parallel 3D surface-thinning algorithm. A three-subiteration strategy is proposed: the thinning operation is changed from iteration to iteration with a period of three according to the three deletion directions. [ABSTRACT FROM AUTHOR]

We describe a technique to detect and localize features on checkerboard calibration charts with high accuracy. Our approach is based on a model representing the sought features by a multiplicative combination of two edge functions, which, to allow for perspective distortions, can be arbitrarily oriented. First, candidate regions are identified by an eigenvalue analysis of the structure tensor. Within these regions, the sought checkerboard features are then detected by matched filtering. To efficiently account for the double-oriented nature of the sought features, we develop an extended version of steerable filters, viz., multi-steerable filters. The design of our filters is carried out by a Fourier series approximation. Multi-steerable filtering provides both the unknown orientations and the positions of the checkerboard features, the latter with pixel accuracy. In the last step, the feature positions are refined to subpixel accuracy by fitting a paraboloid. Rigorous comparisons show that our approach outperforms existing feature localization algorithms by a factor of about three. [ABSTRACT FROM AUTHOR]

This paper presents a bottom-up approach for fast segmentation of natural images. This approach has two main stages: firstly, it detects the homogeneous regions of the input image using a colour-based distance and then, it merges these regions using a more complex distance. Basically, this distance complements a contrast measure defined between regions with internal region descriptors and with attributes of the shared boundary. These two stages are performed over the same hierarchical framework: the Bounded Irregular Pyramid (BIP). The performance of the proposed algorithm has been quantitatively evaluated with respect to ground-truth segmentation data. [ABSTRACT FROM AUTHOR]

Autonomous collision avoidance in vehicles requires an accurate separation of obstacles from the background, particularly near the focus of expansion. In this paper, we present a technique for fast segmentation of stationary obstacles from video recorded by a single camera that is installed in a moving vehicle. The input image is divided into three motion segments consisting of the ground plane, the background, and the obstacle. This constrained scenario allows for good initial estimates of the motion models, which are iteratively refined during segmentation. The horizon is known due to the camera setup. The remaining binary partitioning problem is solved by a graph cut on the motion-compensated difference images. Obstacle segmentation in realistic scenes with a monocular camera setup has not been feasible up to now. Our experimental evaluation shows that the proposed approach leads to fast and accurate obstacle segmentation and distance estimation without prior knowledge about the size, shape or base point of obstacles. [ABSTRACT FROM AUTHOR]

Image segmentation based on pairwise pixel similarities has been a very active field of research in recent years. The drawbacks common to these segmentation methods are the enormous space and processor requirements. The contribution of this paper is a general purpose two-stage preprocessing method that substantially reduces the involved costs. Initially, an oversegmentation into small coherent image patches - or superpixels - is obtained through an iterative process guided by pixel similarities. A suitable pairwise superpixel similarity measure is then defined which may be plugged into an arbitrary segmentation method based on pairwise pixel similarities. To illustrate our ideas we integrated the algorithm into a spectral graph-partitioning method using the Normalized Cut criterion. Our experiments show that the time and memory requirements are reduced drastically (> 99%), while segmentations of adequate quality are obtained. [ABSTRACT FROM AUTHOR]

Variational methods are among the most successful approaches to calculate the optical flow between two image frames. A particularly appealing formulation is based on total variation (TV) regularization and the robust L1 norm in the data fidelity term. This formulation can preserve discontinuities in the flow field and offers an increased robustness against illumination changes, occlusions and noise. In this work we present a novel approach to solve the TV-L1 formulation. Our method results in a very efficient numerical scheme, which is based on a dual formulation of the TV energy and employs an efficient point-wise thresholding step. Additionally, our approach can be accelerated by modern graphics processing units. We demonstrate the real-time performance (30 fps) of our approach for video inputs at a resolution of 320×240 pixels. [ABSTRACT FROM AUTHOR]

Magnetic resonance spectral images provide information on metabolic processes and can thus be used for in vivo tumor diagnosis. However, each single spectrum has to be checked manually for tumorous changes by an expert, which is only possible for very few spectra in clinical routine. We propose a semi-supervised procedure which requires only very few labeled spectra as input and can hence adapt to patient and acquisition specific variations. The method employs a discriminative random field with highly flexible single-side and parameter-free pair potentials to model spatial correlation of spectra. Classification is performed according to the label set that minimizes the energy of this random field. An iterative procedure alternates a parameter update of the random field using a kernel density estimation with a classification by means of the GraphCut algorithm. The method is compared to a single spectrum approach on simulated and clinical data. [ABSTRACT FROM AUTHOR]

The ability of a segmentation algorithm to uncover an interesting partition of an image critically depends on its capability to utilize and combine all available, relevant information. This paper investigates a method to automatically weigh different data sources, such that a meaningful segmentation is uncovered. Different sources of information naturally arise in image segmentation, e.g. as intensity measurements, local texture information or edge maps. The data fusion is controlled by a regularization mechanism, favoring sparse solutions. Regularization parameters as well as the clustering complexity are determined by the concept of cluster stability yielding maximally reproducible segmentations. Experiments on the Berkeley segmentation database show that our segmentation approach outperforms competing segmentation algorithms and performs comparably to supervised boundary detectors. [ABSTRACT FROM AUTHOR]

Recursive estimation or Kalman filtering usually relies on explicit model functions, that directly and explicitly describe the effect of the parameters on the observations. However, many problems in computer vision, including all those resulting in homogeneous equation systems, are easier described using implicit constraints between the observations and the parameters. By implicit we mean, that the constraints are given by equations, that are not easily solvable for the observation vector. We present a framework, that allows to incorporate such implicit constraints as measurement equations into a Kalman filter. The algorithm may be used as a black-box, simplifying the process of specifying suitable measurement equations for many problems. As a byproduct, the possibility of specifying model equations non-explicitly, some non-linearities may be avoided and better results can be achieved for certain problems. [ABSTRACT FROM AUTHOR]

The extraction of a parametric global motion from a motion field is a task with several applications in video processing. We present two probabilistic formulations of the problem and carry out optimization using the RAST algorithm, a geometric matching method novel to motion estimation in video. RAST uses an exhaustive and adaptive search of transformation space and thus gives - in contrast to local sampling optimization techniques used in the past - a globally optimal solution. Among other applications, our framework can thus be used as a source of ground truth for benchmarking motion estimation algorithms. Our main contributions are: first, the novel combination of a state-of-the-art MAP criterion for dominant motion estimation with a search procedure that guarantees global optimality. Second, experimental results that illustrate the superior performance of our approach on synthetic flow fields as well as real-world video streams. Third, a significant speedup of the search achieved by extending the model with an additional smoothness prior. [ABSTRACT FROM AUTHOR]

In this paper we extend a multi-camera model for simultaneous estimation of 3d position, normals, and 3d motion of surface patches [17] to be able to handle brightness changes coming from changing illumination. In the target application only surface orientation and 3d motion are of interest. Thus color related surface properties like bidirectional reflectance distribution function do not need to be reconstructed. Consequently we characterize only changes of the brightness using a second-order power series. We test two new models within a total least squares estimation framework using synthetic data with ground truth available. Motion estimation results improve severely with respect to the brightness constancy model when brightness changes are present in the data. [ABSTRACT FROM AUTHOR]

Since years variational methods belong to the most accurate techniques for computing the optical flow in image sequences. However, if based on the grey value constancy assumption only, such techniques are not robust enough to cope with typical illumination changes in real-world data. In our paper we tackle this problem in two ways: First we discuss different photometric invariants for the design of illumination-robust variational optical flow methods. These invariants are based on colour information and include such concepts as spherical/conical transforms, normalisation strategies and the differentiation of logarithms. Secondly, we embed them into a suitable multichannel generalisation of the highly accurate variational optical flow technique of Brox et al. This in turn allows us to access the true potential of such invariants for estimating the optical flow. Experiments with synthetic and real-world data demonstrate the success of combining accuracy and robustness: Even under strongly varying illumination, reliable and precise results are obtained. [ABSTRACT FROM AUTHOR]

This article introduces a technique for region-based pose tracking of multiple objects. Our algorithm uses surface models of the objects to be tracked and at least one calibrated camera view, but does not require color, texture, or other additional properties of the objects. By optimizing a joint energy defined on the pose parameters of all objects, the proposed algorithm can explicitly handle occlusions between different objects. Tracking results in simulated as well as real world scenes demonstrate the effects of occlusion and how they are handled by the proposed method. [ABSTRACT FROM AUTHOR]

Confidence measures are important for the validation of optical flow fields by estimating the correctness of each displacement vector. There are several frequently used confidence measures, which have been found of at best intermediate quality. Hence, we propose a new confidence measure based on linear subspace projections. The results are compared to the best previously proposed confidence measures with respect to an optimal confidence. Using the proposed measure we are able to improve previous results by up to 31%. [ABSTRACT FROM AUTHOR]

Global optical flow techniques minimize a mixture of two terms: a data term relating the observable signal with the optical flow, and a regularization term imposing prior knowledge/assumptions on the solution. A large number of different data terms have been developed since the first global optical flow estimator proposed by Horn and Schunk [1]. Recently [2], these data terms have been classified with respect to their properties. Thus, for image sequences where certain properties about image as well as motion characteristics are known in advance, the appropriate data term can be chosen from this classification. In this contribution, we deal with the situation where the optimal data term is not known in advance. We apply the Bayesian evidence framework for automatically choosing the optimal relative weight between two data terms as well as the regularization term based only on the given input signal. [ABSTRACT FROM AUTHOR]

Tracking 3D objects from 2D image data often leads to jittery tracking results. In general, unsmooth motion is a sign of tracking errors, which, in the worst case, can cause the tracker to loose the tracked object. A straightforward remedy is to demand temporal consistency and to smooth the result. This is often done in form of a post-processing. In this paper, we present an approach for online smoothing in the scope of 3D human motion tracking. To this end, we extend an energy functional by a term that penalizes deviations from smoothness. It is shown experimentally that such online smoothing on pose parameters and joint angles leads to improved results and can even succeed in cases, where tracking without temporal consistency assumptions fails completely. [ABSTRACT FROM AUTHOR]

We propose a model-based camera pose estimation approach, which makes use of GPU-assisted analysis-by-synthesis methods on a very wide field of view (e.g. fish-eye) camera. After an initial registration, the synthesis part of the tracking is performed on graphics hardware, which simulates internal and external parameters of the camera, this way minimizing lens and perspective differences between a model view and a real camera image. We show how such a model is automatically created from a scene and analyze the sensitivity of the tracking to the model accuracy, in particular the case when we represent free-form surfaces by planar patches. We also examine accuracy and show on synthetic and on real data that the system does not suffer from drift accumulation. The wide field of view of the camera and the subdivision of our reference model into many textured free-form surfaces make the system robust against moving persons and other occlusions within the environment and provide a camera pose estimate in a fixed and known coordinate system. [ABSTRACT FROM AUTHOR]

The measurement of fluid flows is an emerging field for optical flow computation. In a number of such applications, a tracer is visualized with modern digital cameras. Due to the projective nature of the imaging process, the tracer is integrated across a velocity profile. In this contribution, a novel technique is presented that explicitly models brightness changes due to this integration. Only through this modeling is an accurate estimation of the flow velocities feasible. Apart from an accurate measurement of the fluid flow, also the underlying velocity profile can be reconstructed. Applications from shear flow, microfluidics and a biological applications are presented. [ABSTRACT FROM AUTHOR]

The detection of moving objects is crucial for robot navigation and driver assistance systems. In this paper the detectability of moving objects is studied. To this end, image correspondences over two and three frames are considered whereas the images are acquired by a moving monocular camera. The detection is based on the constraints linked to static 3D points. These constraints (epipolar, positive depth, positive height, and trifocal constraint) are discussed briefly, and an algorithm incorporating all of them is proposed. The individual constraints differ in their action depending on the motion of the object. Thus, the detectability of a moving object is influenced by its motion. Three types of motions are investigated: parallel, lateral, and circular motion. The study of the detection limits is applied to real imagery. [ABSTRACT FROM AUTHOR]

This paper presents a novel multi-view camera system that produces real-time single view scene video which sees through the static objects to observe the dynamic objects. The system employs a training phase to recover the correspondences and occlusions between the views to determine the image positions where seeing through would be necessary. During the runtime phase, each dynamic object is detected and automatically registered between the views. The registered objects are learned using an appearance based method and they are later used to superimpose the occluded dynamic objects on the desired view. The occlusion detection is done using a very efficient and effective method. The system is very practical and can be used in real life applications including video surveillance, communication, activity analysis, and entertainment. We validated the system by running various tests in office and outdoor environments. [ABSTRACT FROM AUTHOR]

Typical tracking algorithms exploit temporal coherence, in the sense of expecting only small object motions. Even without exact knowledge of the scene, additional spatial coherence can be exploited by expecting only a rigid 3d motion. Feature tracking will benefit from knowing about this rigidity of the scene, especially if individual features cannot be tracked by themselves due to occlusions or illumination changes. We present and compare different approaches of dealing with the spatial coherence in the context of tracking planar scenes. We also show the benefits in scenes with occlusions and changes in illumination, even without models of these distortions. [ABSTRACT FROM AUTHOR]

This contribution presents a novel approach to the challenging problem of model selection in motion estimation from sequences of images. New light is cast on parametric models of local optical flow. These models give rise to parameter estimation problems with highly correlated errors in variables (EIV). Regression is hence performed by equilibrated total least squares. The authors suggest to adaptively select motion models by testing local empirical regression residuals to be in accordance with the probability distribution that is theoretically predicted by the EIV model. Motion estimation with residual-based model selection is examined on artificial sequences designed to test specifically for the properties of the model selection process. These simulations indicate a good performance in the exclusion of inappropriate models and yield promising results in model complexity control. [ABSTRACT FROM AUTHOR]

A simple, stable and generic approach for estimation of relative positions and orientations of multiple rigidly coupled cameras is presented in this paper. The algorithm does not impose constraints on the field of view of the cameras and works even in the extreme case when the sequences from the different cameras are totally disjoint (i.e. when no part of the scene is captured by more than one camera). The influence of the rig motion on the existence of a unique solution is investigated and degenerate rig motions are identified. Each camera captures an individual sequence which is afterwards processed by a structure and motion (SAM) algorithm resulting in positions and orientations for each camera. The unknown relative transformations between the rigidly coupled cameras are estimated utilizing the rigidity constraint of the rig. [ABSTRACT FROM AUTHOR]

We present an approach for estimating the 3D position and in case of articulated objects also the joint configuration from segmented 2D images. The pose estimation without initial information is a challenging optimization problem in a high dimensional space and is essential for texture acquisition and initialization of model-based tracking algorithms. Our method is able to recognize the correct object in the case of multiple objects and estimates its pose with a high accuracy. The key component is a particle-based global optimization method that converges to the global minimum similar to simulated annealing. After detecting potential bounded subsets of the search space, the particles are divided into clusters and migrate to the most attractive cluster as the time increases. The performance of our approach is verified by means of real scenes and a quantative error analysis for image distortions. Our experiments include rigid bodies and full human bodies. [ABSTRACT FROM AUTHOR]

In the two-view case, point matching constraints are represented by the fundamental matrix. In the three-view case, the point matching constraints are indirectly represented by three trifocal tensors corresponding to the three camera matrices. A direct representation of the point matching constraints can be obtained by applying suitable transformations on the trifocal tensors. This paper discusses some issues related to point matching constraints. First, it presents a novel approach for deriving the constraints in terms of a generator space. Second, it shows that the resulting set of linearly independent constraints is 10-dimensional for the three-view case, a result which deviates from the literature on this subject. Third, in the case that the cameras have non-co-linear focal points, 9 of these 10 constraints can be obtained in a straight-forward way from the three fundamental matrices which we have in the three-view case. The last constraint can be obtained from the fundamental matrices but in a non-trivial way. The main result of the paper is a better understanding of the properties related to point matching constraints in three dimensions and how they are related to the corresponding two-view constraints. [ABSTRACT FROM AUTHOR]