Computer Vision [CV]
Computer Vision involves the (semi-) automatic extraction of
The Exercise page is located here.
Running Example: Tracking
As a running example a tracking application can be implemented during the course. The benefit of this application is, that it nicely incorporates a lot of the topics covered in the course and thus enables you to get an overall impression of the algorithmic design decisions which have to be made when implementing a more complex application-specific solution. Below you find a list of the basic ingredients for the tracking application along with some illustrative images to provide you a feeling for the basic skills which you will learn in the course and which (if properly stitched together) yield a tracking application.
1. Noise Reduction via Smoothing (images from Robert Fisher, http://homepages.inf.ed.ac.uk/rbf/CVonline/)
2. Edge Detection (images from Edan Lerner; http://www.cs.bgu.ac.il/~icbv071/StudentProjects/ICBV052/ICBV-2005-2-Lerner-Edan/)
3. Hough Transform (images from homepages.inf.ed.ac.uk/rbf/HIPR2/linedet.htm)
Lines detected via Hough Transform:
4. Bounding Box (images from Barazza, Beremind, Thonnat; http://www-sop.inria.fr/pulsar/personnel/Francois.Bremond/topicsText/eventlearner.html)
5. Color Histogram
RGB Color Histogram of the Image (thanks to Eva Eibenberger):
6. Background Subtraction (images from http://www.ee.oulu.fi/research/imag/proact/proact.php?page=demonstrations)
7. Tracking (images from Ashish Derhgawen; ashishrd.blogspot.com/2007/01/real-time-color-based-object-tracking.html )