CS-672

Advanced Topics in Computational Vision

Postgraduate

The goal of this course is the in-depth study of selected topics on Computer Vision so that the students that attend it have the necessary background in order to perform research in the area of Computer Vision.The selection of the topics varies in each semester and is determined by the current trends in the computer vision literature, as well as the special interests of the instructor and the students. The selected topics fall in broader areas such as: image acquisition and optical sensors, low level vision algorithms, image and video features, feature grouping and image segmentation, image color and texture, motion perception and object tracking, multi-view geometry, 3D reconstruction, shape representation and object modeling, feature correspondence, object recognition, statistical models and learning method in vision, active vision systems, robotic vision, detection and recognition of faces, gestures and actions, cognitive and biologically inspired vision.

LEARNING OUTCOMES
1. Knowledge: Having attended and succeeded in the course, the student is able to describe how specific, selected computer vision problems are addressed in the recent relevant literature.
 
2. Understanding: Having attended and succeeded in the course, the student has achieved an in-depth understanding of the mechanisms for solving specific computer vision problems and is able to explain if/why these mechanisms are adequate for solving other problems.
 
3. Application: Having attended and succeeded in the course, the student is able to reuse existing methodologies and tools to produce other solutions for solving specific versions of specific computer vision problems or developing applications.
 
4. Analysis: Having attended and succeeded in the course, the student is able to take a critical view of specific problems and perceive them as a composition of a series of individual sub-problems.
 
5. Synthesis: Having attended and succeeded in the course, the student is able to combine individual tools and methodologies to successfully solve complex computer vision problems.
 
6. Evaluation: Having attended and succeeded in the course, the student is able to measure/quantify the quality of solutions to computer vision problems and compare these solutions to other existing ones.

STUDENT PERFORMANCE EVALUATION

• Class attendance/participation
• Exercises/projects
• Oral/written exams

 
Students are informed about the evaluation process during the first lecture of the course. This information is also made available on the course website.



 

6

CS-472

http://www.csd.uoc.gr/~hy672