Prof. Dr. Mario Campos - UFMG

Presentation

Computational vision is a enchanting research that have produced great relevance results for innumerous society segments. The spectrum of these applications includes identification and segmentation of objects, real scene 3D reconstitution, real time object tracking, mobile robots guidance, manufacturing process control, and others. This short course has the goal to present fundamentals of the computational vision, a few robotics and automation applications (machine vision) and the great challenges of the area. In the end of this short course is expected that the student will be capable of understanding the paradigms of the area and also the methodologies, algorithms and heuristics for the approach of the computational vision problems.

Schedule:

The course will follow this structure:

1. Introduction: Overview, history and introduction of the computational vision problems, space representations: review of linear algebra and transformations.
2. Image Generation: Geometry and Radiometry;
3. Digital Images: Acquisition systems, image characteristics, deep images;
4. Image processing: noise, filtering;
5. Low Level Processing: border, edges, lines and curves detection;
6. Camera Modeling: perspective, weak-perspective, camera calibration;
7. Reconstrução 3D: Stereopse.
8. Applications:
    - Mobile Robotics,
    - Objects Tracking;
    - Machine Vision;

Bibliography:

- E. Trucco e A. Verri, "Introductory Techniques for 3D Computer Vision", Prentice-Hall, 1998.
- D. A. Forsyth and J. Ponce, "Computer Vision: A Modern Approach", Prentice Hall, 2003.
- B.K.P. Horn. Robot Vision, MIT Press, 1986.
- D. Ballard and C. Brown. Computer Vision, Prentice Hall, 1982.