Aktuelles

Beschreibung

The course aims to provide a structured overview of model-based object tracking, with the purpose of estimating and following in real-time the spatial pose (rotation, translation etc.) of one or more objects, by using digital cameras and fast computer vision techniques.

Among the many visual modalities available, we will focus in particular on the following ones:

1. Keypoint-based: Tracking of single point features, followed by least-squares pose estimation.

2. Contour-based: Detection of the object boundary line (also called Active Contours) as it deforms with the object roto-translation.

3. Template-based: Registration of a fully textured surface (Template) to the image gray-level intensities.

For more information, see also our Wiki page.

Pre-requisites

The course will also provide the following pre-requisites in a self-contained fashion (a basic knowledge would be in any case recommended):

• Basic math and algebra (nonlinear functions and derivatives, matrix computation)

• Basic geometry: 3D transformations, projective geometry, camera imaging

• Probability theory and statistics

• Basic image processing (representation, filtering etc.)

• System theory: state-space representation, dynamics, Bayesian filtering

Material

(for the slides, see the most recent edition of this Lectures).

Matlab exercises and bibliographic references are the same of the previous year (WS 06/07).