Computer Vision

Higher education teachers: Kovačič Stanislav
Collaborators: Perš Janez

Subject description

Content (Syllabus outline):

• Introduction

The aims of computer vision, the origins of computer vision, and related fields.
Computer vision trends and application domains.

• Image formation

Perspective projection camera model.
Camera calibration, direct linear transform, lens distortion correction.
Propagation of light, photometry, photometric lens equation.
Cameras and lenses, lighting techniques.
Human eye, color perception, reproducing color, color spaces.

• Image analysis

Image filtering, histogramming.
Edge detection, corner detection.
Hough transform.
Connected components analysis.
Morphological filtering.
Active contour models (snakes).
Shape description.
Scale space and image pyramids.
Geometric image transformations, similarity measures.
Image registration, model fitting, RANSAC.

• Stereo vision

Basic concepts of stereo vision.
Stereo matching.
Modeling and calibration, epipolar geometry.
Active stereo, structured lighting.

• Visual motion analysis

Motion detection.
Time to collision.
Optic flow, motion field, velocity field.
Visual tracking, basic Kalman filtering.

Objectives and competences:

The aims of this course are to introduce basic concepts, underlying theory, algorithms, and applications of computer vision.

Intended learning outcomes:

• Be able to implement moderately complex computer vision algorithms.
• Be able to solve simple computer and machine vision problems.

Learning and teaching methods:

• Lectures,
• laboratory assignments,
• home work.

Study materials

Readings:

1. D. Forsyth, J. Ponce, Compuer vision, a modern approach, Prentice Hall, 2003.
2. E. Trucco, A. Verri, Introductory techniques for 3-D computer vision, Prentice Hall, 1998.
3. M. Sonka, V. Hlavac, R. Boyle, Image processing, analysis and machine vision, Chapman and Hall Computing series, 1993.