Joachim Denzler

Information theoretic sensor data selection for active object recognition and state estimation

We introduce a formalism for optimal sensor parameter selection for iterative state estimation in static systems. Our optimality criterion is the reduction of uncertainty in the state estimation process, rather than an estimator-specific metric (e.g., minimum mean squared estimate error). The claim is that state estimation becomes more reliable if the uncertainty and ambiguity in the estimation process can be reduced. We use Shannons information theory to select information-gathering actions that maximize mutual information, thus optimizing the information that the data conveys about the true state of the system. The technique explicitly takes into account the a priori probabilities governing the computation of the mutual information. Thus, a sequential decision process can be formed by treating the a priori probability at a certain time step in the decision process as the a posteriori probability of the previous time step. We demonstrate the benefits of our approach in an object recognition application using an active camera for sequential gaze control and viewpoint selection. We describe experiments with discrete and continuous density representations that suggest the effectiveness of the approach.

Model based extraction of articulated objects in image sequences for gait analysis

This paper describes an approach to the extraction of articulated objects which will be used for gait analysis. In most medical applications markers are used to determine trajectories of different body parts. This approach works without any markers. Monotony operators which compute the displacement vector field are used to initialize a contour based tracking algorithm called active rays-for several body parts which are important for gait analysis. The contours of different parts of the human body are extracted and tracked. These parts are approached by simple 3D geometric objects (blocks), which 3D position and motion are estimated for the each image of the image sequence. Then, the trajectories of the moving parts represented by the 3D blocks can be determined and used for classification of different gait disorders.

Fractal-Like Image Statistics in Visual Art: Similarity to Natural Scenes

Both natural scenes and visual art are often perceived as esthetically pleasing. It is therefore conceivable that the two types of visual stimuli share statistical properties. For example, natural scenes display a Fourier power spectrum that tends to fall with spatial frequency according to a power-law. This result indicates that natural scenes have fractal-like, scale-invariant properties. In the present study, we asked whether visual art displays similar statistical properties by measuring their Fourier power spectra. Our analysis was restricted to graphic art from the Western hemisphere. For comparison, we also analyzed images, which generally display relatively low or no esthetic quality (household and laboratory objects, parts of plants, and scientific illustrations). Graphic art, but not the other image categories, resembles natural scenes in showing fractal-like, scale-invariant statistics. This property is universal in our sample of graphic art; it is independent of cultural variables, such as century and country of origin, techniques used or subject matter. We speculate that both graphic art and natural scenes share statistical properties because visual art is adapted to the structure of the visual system which, in turn, is adapted to process optimally the image statistics of natural scenes.

Plenoptic Modeling and Rendering from Image Sequences Taken by Hand-Held Camera

In this contribution we focus on plenoptic scene modeling and rendering from long image sequences taken with a hand-held camera. The image sequence is calibrated with a structure-from-motion approach that considers the special viewing geometry of plenoptic scenes. By applying a stereo matching technique, dense depth maps are recovered locally for each viewpoint.

One-class classification with Gaussian processes

Detecting instances of unknown categories is an important task for a multitude of problems such as object recognition, event detection, and defect localization. This article investigates the use of Gaussian process (GP) priors for this area of research. Focusing on the task of one-class classification, we analyze different measures derived from GP regression and approximate GP classification. We also study important theoretical connections to other approaches and discuss their underlying assumptions. Experiments are performed using a large number of datasets and different image kernel functions. Our findings show that our approaches can outperform the well-known support vector data description approach indicating the high potential of Gaussian processes for one-class classification. Furthermore, we show the suitability of our methods in the area of attribute prediction, defect localization, bacteria recognition, and background subtraction. These applications and experiments highlight the easy applicability of our method as well as its state-of-the-art performance compared to established methods.

Nonparametric Part Transfer for Fine-Grained Recognition

In the following paper, we present an approach for fine-grained recognition based on a new part detection method. In particular, we propose a nonparametric label transfer technique which transfers part constellations from objects with similar global shapes. The possibility for transferring part annotations to unseen images allows for coping with a high degree of pose and view variations in scenarios where traditional detection models (such as deformable part models) fail. Our approach is especially valuable for fine-grained recognition scenarios where intraclass variations are extremely high, and precisely localized features need to be extracted. Furthermore, we show the importance of carefully designed visual extraction strategies, such as combination of complementary feature types and iterative image segmentation, and the resulting impact on the recognition performance. In experiments, our simple yet powerful approach achieves 35.9% and 57.8% accuracy on the CUB-2010 and 2011 bird datasets, which is the current best performance for these benchmarks.

Progressive attenuation fields : Fast 2D-3D image registration without precomputation

This paper introduces the progressive attenuation field (PAF), a method to speed up computation of digitally reconstructed radiograph (DRR) images during intensity-based 2D-3D registration. Unlike traditional attenuation fields, a PAF is built on the fly as the registration proceeds. It does not require any precomputation time, nor does it make any prior assumptions of the patient pose that would limit the permissible range of patient motion. We use a cylindrical attenuation field parameterization, which is better suited for medical 2D-3D registration than the usual two-plane parameterization. The computed attenuation values are stored in a hash table for time-efficient storage and access. Using a clinical gold-standard spine image dataset, we demonstrate a speedup of 2D-3D image registration by a factor of four over ray-casting DRR with no decrease of registration accuracy or robustness.

Kernel Null Space Methods for Novelty Detection

Detecting samples from previously unknown classes is a crucial task in object recognition, especially when dealing with real-world applications where the closed-world assumption does not hold. We present how to apply a null space method for novelty detection, which maps all training samples of one class to a single point. Beside the possibility of modeling a single class, we are able to treat multiple known classes jointly and to detect novelties for a set of classes with a single model. In contrast to modeling the support of each known class individually, our approach makes use of a projection in a joint subspace where training samples of all known classes have zero intra-class variance. This subspace is called the null space of the training data. To decide about novelty of a test sample, our null space approach allows for solely relying on a distance measure instead of performing density estimation directly. Therefore, we derive a simple yet powerful method for multi-class novelty detection, an important problem not studied sufficiently so far. Our novelty detection approach is assessed in comprehensive multi-class experiments using the publicly available datasets Caltech-256 and Image Net. The analysis reveals that our null space approach is perfectly suited for multi-class novelty detection since it outperforms all other methods.

An Information Theoretic Approach for Next Best View Planning in 3-D Reconstruction

We present an algorithm for optimal view point selection for 3D reconstruction of an object using 2D image points. Since the image points are noisy, a Kalman filter is used to obtain the best estimate of the objects geometry. This Kalman filter allows us to efficiently predict the effect of any given camera position on the uncertainty, and therefore quality, of the estimate. By choosing a suitable optimization criterion, we are able to determine the camera positions which minimize our reconstruction error. We verify our results using two experiments with real images: one experiment uses a calibration pattern for comparison to a ground-truth state, the other reconstructs a real world object

Selecting Influential Examples: Active Learning with Expected Model Output Changes

In this paper, we introduce a new general strategy for active learning. The key idea of our approach is to measure the expected change of model outputs, a concept that generalizes previous methods based on expected model change and incorporates the underlying data distribution. For each example of an unlabeled set, the expected change of model predictions is calculated and marginalized over the unknown label. This results in a score for each unlabeled example that can be used for active learning with a broad range of models and learning algorithms. In particular, we show how to derive very efficient active learning methods for Gaussian process regression, which implement this general strategy, and link them to previous methods. We analyze our algorithms and compare them to a broad range of previous active learning strategies in experiments showing that they outperform state-of-the-art on well-established benchmark datasets in the area of visual object recognition.