COS 429 - Computer Vision

Suggested ideas

• Panorama Stitching. See M. Brown and D. G. Lowe, Recognising Panoramas, ICCV 2003.
• Real-Time Object detection. See P. Viola and M. J. Jones, Robust Real-Time Object Detection, , IJCV 2004.
• Car detection.
• Indoor scene classification.  See L. Fei-Fei and P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories, CVPR 2005.
  
• Image segmentation. There are many papers on this topic, e.g. J. Shi & J. Malik, Normalized Cuts and Image Segmentation, PAMI 2000.
• Cleaning images from Google search. See R. Fergus, L. Fei-Fei, P. Perona and A. Zisserman. Learning Object Categories from Google's Image Search, ICCV 2005; L.-J. Li, G. Wang and L. Fei-Fei, OPTIMOL: automatic Object Picture collecTion via Incremental MOdel Learning, CVPR 2007.
• Sorting photo albums.

 

Project proposal ( due 11:59pm, Friday, Nov 9 )

The project proposal is 5% of your entire grade for cos429. It should be no more than 1 page, written with this template ( Both word and latex versions are included. ). You should submit your proposal in pdf to moodle. Your proposal should describe the following, as best as you can.  (We understand that some details will have to be worked out as the project proceeds.)

• What is the computer vision problem that you will be investigating? Why is it interesting?
• What image or video data will you use? If you are collecting new datasets, how do you plan to collect them?
• What method or algorithm are you proposing? If there are existing implementations, will you use them and how? How do you plan to improve or modify such implementations?
• Which reading will you examine to provide context and background?
• How will you evaluate your results? Qualitatively, what kind of results do you expect (e.g. what kind of plots or figures do you want to see?)? Quantitatively, what kind of analysis will you use to evaluate and/or compare your results (e.g. what kind of performance metrics? statistical tests? etc.)
  

 

Project Write-up (due 11:59pm, Dean's Day, Jan 15)

The final writeup is 30% of your entire course grade. We have given you the write-up template. Given this format, your report should be between 8-10 pages (excluding the supplementary material, more later). You should submit your report in pdf to moodle. All of you are basing your project on someone's previous work. So you have read at least several papers. We're expecting your report to be written in the style of the papers you have read. The following is a suggested structure for your report.

• Title, author
• Abstract: It should not be more than 300 words;
• Introduction: this section introduces your problem, and the overall plan for approaching your problem;
• Background: This section discusses relevant literature for your project;
• Approach: This section details the framework of your project. Be specific, which means you might want to include equations, figures, plots, etc;
• Experiment: This section begins with what kind of experiments you're doing, what kind of dataset(s) you're using, and what is the way you measure or evaluate your results. It then shows in details the results of your experiments. By details, I mean both quantitative evaluations (show numbers, figures, tables, etc) as well as qualitative results (show images, example results, etc).
• Conclusion: What have you learned? Suggest future ideas.
• References: This is absolutely necessary. Reports without references will not receive a score higher than 10 points (total is 30 points).
• Supplementary materials: This is NOT counted toward your 8-10 page limit. Please submit your codes as supplementary materials.

   

Project Presentation (Monday Jan 14, 3-6pm, CS 102 )

The course presentation is 5% of your entire course grade. In addition, the winner team (judged by you) receives a prize of TBA. We are enforcing a very strict time limit to each presentation. For each team, you have a total of 6 minutes -- 5 minutes of presentation and 1 minute of Q&A. You are also going to act as reviewers for each of the presentation. Please take a look at the review form, in which you will also find the order of the presentation, which we have used a method to randomly determine. This should be very helpful for your own preparation of the presentation.