Projects can be done individually on in pairs.

Deadlines

• October 31: Send me email stating whom you will work with (or that you will work on the project alone), and describing the project in one or two paragraphs. This email counts for 10 percent of your project grade.
• November 7: Present a project plan in class describing what you plan to do and how. Include a discussion of possible pitfalls and difficulties, and workarounds for them.
  Your presentation will take five minutes. Prepare a few slides in Powerpoint or equivalent, and link them to an URL. Check from a remote computer that the URL is accessible and that all your links work. Rehearse youre presentation to make sure you do not exceed the allotted time. The presentation counts for 30 percent of your project grade.
• November 30 (by midnight): Send me email with your final project report. This can be a PDF or MS Word file, or a URL. In the latter case, make sure that all your links work. I cannot grade what I cannot access. An average project report is the equivalent of about five pages of text and figures. What counts is not whether the project was successful, but how much you show that you learned from it. Good form (including grammar and proper citations) counts as well. The final project report counts for 60 percent of your project grade.

Project Examples

The following project examples are intended to give you an idea of the scope of a typical project. You may choose to do one of the examples, but coming up with your own ideas is preferable. Variations on the project examples below can be obtained by replacing, say, "stereo" with "recognition," and so forth.

• Implement a fast median filtering algorithm and report its performance on images of various sizes.
• Calibrate one of the cameras in the vision lab using existing code from the web.
• Implement a simple stereo algorithm and test it on a few image pairs downloaded from the web.
• Download existing code for face detection and discuss its performance on a few video sequences acquired in the vision lab.
• Write code that tracks a single point feature in video from a hand-held webcam.
• Find a shortcoming of an existing texture classification algorithm and attempt to fix it.
• Use the condensation (particle filter) code in the OpenCV library (see the resources page) to track people from surveillance video downloaded from the web.

in all cases, the most important part of the final project report is a discussion of the results. Given your time constraints, you should not expect success with the more open-ended projects. However, do not be afraid to take risks: a good discussion of a failed attempt makes for a great project report.