Seeing the Objects Behind the Dots: Recognition in Videos from a Moving Camera

Category-level object recognition, segmentation, and tracking in videos becomes highly challenging when applied to sequences from a hand-held camera that features extensive motion and zooming. An additional challenge is then to develop a fully automatic video analysis system that works without manual initialization of a tracker or other human intervention, both during training and during recognition, despite background clutter and other distracting objects. Moreover, our working hypothesis states that category-level recognition is possible based only on an erratic, flickering pattern of interest point locations without extracting additional features. Compositions of these points are then tracked individually by estimating a parametric motion model. Groups of compositions segment a video frame into the various objects that are present and into background clutter. Objects can then be recognized and tracked based on the motion of their compositions and on the shape they form. Finally, the combination of this flow-based representation with an appearance-based one is investigated. Besides evaluating the approach on a challenging video categorization database with significant camera motion and clutter, we also demonstrate that it generalizes to action recognition in a natural way. Electronic Supplementary Material  The online version of this article () contains supplementary material, which is available to authorized users. This work was supported in part by the Swiss national science foundation under contract no. 200021-107636.     

On the Implicit Anti-Aliasing Feature of Continuous-Time Cascaded Sigma–Delta Modulators

This paper deals with one of the most outstanding advantages of continuous-time (CT) sigma-delta modulators compared to their discrete-time counterparts: the implicit anti-aliasing feature (AAF). Although inherent in any CT architecture, analysis of anti-aliasing properties has mostly been restricted to single-stage modulators in the past. In this contribution, extensions on analysis methods for the study of the AAF of CT multistage noise-shaping architectures are covered. A theoretical model is introduced and confirmed through simulation results. Contrary to previous belief, the results indicate that usually all stages of a cascaded architecture are involved in the anti-aliasing behaviour and hence that it is not solely determined by the first stage.     

Microscopic Origin of Casimir-Polder Forces

We establish a general relation between dispersion forces. First, based on QED in causal media, leading-order perturbation theory is used to express both the single-atom Casimir-Polder and the two-atom van der Waals potentials in terms of the atomic polarizabilities and the Green tensor for the body-assisted electromagnetic field. Endowed with this geometry-independent framework, we then employ the Born expansion of the Green tensor together with the Clausius-Mosotti relation to prove that the macroscopic Casimir-Polder potential of an atom in the presence of dielectric bodies is due to an infinite sum of its microscopic many-atom van der Waals interactions with the atoms comprising the bodies. This theorem holds for inhomogeneous, dispersing, and absorbing bodies of arbitrary shapes and arbitrary atomic composition on an arbitrary background of additional magnetodielectric bodies.     

Path-based clustering for grouping of smooth curves and texture segmentation

Perceptual grouping organizes image parts in clusters based on psychophysically plausible similarity measures. We propose a novel grouping method in this paper, which stresses connectedness of image elements via mediating elements rather than favoring high mutual similarity. This grouping principle yields superior clustering results when objects are distributed on low-dimensional extended manifolds in a feature space, and not as local point clouds. In addition to extracting connected structures, objects are singled out as outliers when they are too far away from any cluster structure. The objective function for this perceptual organization principle is optimized by a fast agglomerative algorithm. We report on perceptual organization experiments where small edge elements are grouped to smooth curves. The generality of the method is emphasized by results from grouping textured images with texture gradients in an unsupervised fashion.     

Stability-based validation of clustering solutions

Data clustering describes a set of frequently employed techniques in exploratory data analysis to extract "natural" group structure in data. Such groupings need to be validated to separate the signal in the data from spurious structure. In this context, finding an appropriate number of clusters is a particularly important model selection question. We introduce a measure of cluster stability to assess the validity of a cluster model. This stability measure quantifies the reproducibility of clustering solutions on a second sample, and it can be interpreted as a classification risk with regard to class labels produced by a clustering algorithm. The preferred number of clusters is determined by minimizing this classification risk as a function of the number of clusters. Convincing results are achieved on simulated as well as gene expression data sets. Comparisons to other methods demonstrate the competitive performance of our method and its suitability as a general validation tool for clustering solutions in real-world problems.     

Nonparametric Bayesian Image Segmentation

Image segmentation algorithms partition the set of pixels of an image into a specific number of different, spatially homogeneous groups. We propose a nonparametric Bayesian model for histogram clustering which automatically determines the number of segments when spatial smoothness constraints on the class assignments are enforced by a Markov Random Field. A Dirichlet process prior controls the level of resolution which corresponds to the number of clusters in data with a unique cluster structure. The resulting posterior is efficiently sampled by a variant of a conjugate-case sampling algorithm for Dirichlet process mixture models. Experimental results are provided for real-world gray value images, synthetic aperture radar images and magnetic resonance imaging data.     

DISCO: a graphical methodology for the design of Sigma-Delta modulators

A MATLAB^TM toolbox for the design and simulation of continuous time (CT) and discrete time Sigma-Delta modulators is presented. The design of Sigma-Delta modulators is performed by placing the poles and zeros of the loop filter and estimating the resulting noise transfer function and signal transfer function. For this, the toolbox offers a graphical user interface for direct user interaction. Several additional functions, e.g. excess loop delay compensation, are made available to the designer. Further, the designed loop filter can be synthesized in CIFF and CIFB topology or CRFF and CRFB in the case of a bandpass modulator. Additionally, the toolbox offers the design of a closed loop Sigma-Delta sensor readout having the sensor as part of the loop filter. Furthermore, several typical non-idealities of CT Sigma-Delta modulators such as real opamp behavior, excess loop delay, and jitter, are simulated with a tremendously speed up via the application of the lifting approach.     

Dithered Color Quantization

Image quantization and digital halftoning are fundamental problems in computer graphics, which arise when displaying high-color images on non-truecolor devices. Both steps are generally performed sequentially and, in most cases, independent of each other. Color quantization with a pixel-wise defined distortion measure and the dithering process with its local neighborhood optimize different quality criteria or, frequently, follow a heuristic without reference to any quality measure.
In this paper we propose a new method to simultaneously quantize and dither color images. The method is based on a rigorous cost-function approach which optimizes a quality criterion derived from a generic model of human perception. A highly efficient algorithm for optimization based on a multiscale method is developed for the dithered color quantization cost function. The quality criterion and the optimization algorithms are evaluated on a representative set of artificial and real-world images as well as on a collection of icons. A significant image quality improvement is observed compared to standard color reduction approaches.     

Robust image segmentation using resampling and shape constraints

Automated segmentation of images has been considered an important intermediate processing task to extract semantic meaning from pixels. We propose an integrated approach for image segmentation based on a generative clustering model combined with coarse shape information and robust parameter estimation. The sensitivity of segmentation solutions to image variations is measured by image resampling. Shape information is included in the inference process to guide ambiguous groupings of color and texture features. Shape and similarity-based grouping information is combined into a semantic likelihood map in the framework of Bayesian statistics. Experimental evidence shows that semantically meaningful segments are inferred even when image data alone gives rise to ambiguous segmentations.