In this paper a motion estimation algorithm is presented, based on spatio-temporal warping of an image sequence. The motion field function is modeled by isoparametric cubic finite elements, depending on a set of elementary displacement vectors. A model refinement scheme is proposed for the adaptively higher bit allocation to motion information in locations with high motion activity. Keywords— M...

A stereo vision system for detecting 3D-objects is presented. The method uses a pair of externally uncalibrated cameras and is able t o detect objects located on a staircase. Detection is based on differencing stereo pair images, where a warping transform is used to overlay the left onto the right image, and vice versa. The 3D camera positions are obtained through model t~ased pose estimation a...

ÐAn effective fingerprint verification system is presented. It assumes that an existing reference fingerprint image must validate the identity of a person by means of a test fingerprint image acquired online and in real-time using minutiae matching. The matching system consists of two main blocks: The first allows for the extraction of essential information from the reference image offline, the...

Image warping is a transformation which maps all positions in one image plane to positions in a second plane. It arises in many image analysis problems, whether in order to remove optical distortions introduced by a camera or a particular viewing perspective, to register an image with a map or template, or to align two or more images. The choice of warp is a compromise between a smooth distorti...

We present an image-based technique to accelerate the navigation in complex static environments. We perform an image-space simpli cation of each sample of the scene taken at a particular viewpoint and dynamically combine these simpli ed samples to produce images for arbitrary viewpoints. Since the scene is converted into a bounded complexity representation in the image space, with the base imag...

Dynamic time warping (DTW) is a fundamental technique in time series analysis for comparing one curve to another using a flexible time-warping function. However, it was designed to compare a single pair of curves. In many applications, such as in metabolomics and image series analysis, alignment is simultaneously needed for multiple pairs. Because the underlying warping functions are often rela...

In this work we demonstrate the relationship existing between two important issues in vision: multi-scale local spectrum analysis, and log-polar foveatization. We show that, when applying a continuous set of self-similar (rotated and scaled) band-pass filters to estimate the local spectrum at a given point of attention of the image, the inverse Fourier transform of this local spectrum is a log-...

Observing that many visual effects (depth-of-field, motion blur, soft shadows, spectral effects) and several sampling modalities (time, stereo or light fields) can be expressed as a sum of many pinhole camera images, we suggest a novel efficient image synthesis framework that exploits coherency among those images. We introduce the notion of “distribution flow” that represents the 2D image defor...