COMP 776 Projects

COMP 776 Project Ideas

Project proposal due: February 28

The goal of the class project is to produce a rudimentary working vision system. The simplest way to accomplish this is to pick one paper from the list below, to distill the essential ideas of the approach presented in that paper, and to create a basic implementation of those ideas. I also encourage you to define your own problem or to combine ideas from several papers, but please try to keep the scope of your project as simple and well-defined as possible! As part of your project, you may use any code or executables that are freely available on the web, as long as your project goes beyond that code and implements something sufficiently significant on top of it or modifies it in some interesting way. Your first task is to write a project proposal. This proposal should be brief (around one page) and contain the following things:

Problem definition: Identify the paper(s) you plan to follow or the problem you plan to solve, and give a basic outline of what you propose to implement.
Resources: Specify what data you plan to use or whether you plan to acquire your own (e.g., for panorama stitching). Also specify whether you plan to use any outside code and how you plan to build on it.
Reservations: Try to anticipate which part of the implementation or testing may prove the most difficult. Possible stumbling blocks shouldn't necessarily prevent you from attempting a more ambitious project, but you should talk to me early on to make sure that you can still define the project in a satisfactory manner.

Please contact me in advance if you want to define your own project instead of following one of the options below!

Stereo

Yuri Boykov, Olga Veksler, Ramin Zabih. Fast Approximate Energy Minimization via Graph Cuts. In IEEE transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 23, no. 11, pp. 1222-1239, 2001.
D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, International Journal of Computer Vision, 47(1/2/3):7-42, April-June 2002.

Resources: Middlebury stereo page

Geometry

Panorama stitching: Matthew Brown and David G. Lowe, Recognising panoramas, International Conference on Computer Vision (ICCV 2003), Nice, France (October 2003), pp. 1218-25. Project page
Also see project description from a CMU class on Computational Photography: Part 1, Part 2
Space carving: K. N. Kutulakos and S. M. Seitz, A Theory of Shape by Space Carving, International Journal of Computer Vision, 2000, 38(3), pp. 199-218.
Structure from motion (advanced): Implement a rudimentary structure-from-motion system using techniques described in Chapters 12 and 13 of the Forsyth & Ponce textbook. Another possible reference is:
M. Pollefeys, L. Van Gool, M. Vergauwen, F. Verbiest, K. Cornelis, J. Tops, R. Koch, Visual modeling with a hand-held camera, International Journal of Computer Vision 59(3), 207-232, 2004.

Resources: 3D Photography dataset, MATLAB functions for multiple view geometry, multi-view datasets from Oxford

Recognition Using Local Features

S. Lazebnik, C. Schmid, and J. Ponce, A Sparse Texture Representation Using Local Affine Regions, IEEE Transactions on Pattern Analysis and Machine Intelligence, August 2005, vol. 27, no. 8, pp. 1265-1278.
Data: UIUC Texture dataset
S. Lazebnik, C. Schmid, and J. Ponce, Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, June 2006, vol. II, pp. 2169-2178. Data: scene category dataset, Caltech-101 dataset
David G. Lowe, Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2 (2004), pp. 91-110.
Josef Sivic, Bryan Russell, Alexei A. Efros, Andrew Zisserman, Bill Freeman, Discovering Objects and their Location in Images, ICCV 2005.

Resources: ICCV/CVPR short course on recognition (including pointers to data and code)

Misc. Image Classification

Y. Ke, X. Tang, and F. Jing. The Design of High-Level Features for Photo Quality Assessment. Computer Vision and Pattern Recognition, 2006.
Florin Cutzu, Riad Hammoud, and Alex Leykin. Estimating the photorealism of images: Distinguishing paintings from photographs. Computer Vision and Pattern Recognition (CVPR) 2003.
M.J. Jones and J.M. Rehg, Statistical color models with application to skin detection. IJCV, 2002.
Ryan White, Ashley Eden, Michael Maire, Automatic Prediction of Human Attractiveness, CS 280 class report, December 2003. Data

Object Detection

P. Viola and M. Jones, Robust Real-Time Object Detection, IJCV 2002.
Navneet Dalal, Bill Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005. Code

Resources: Face detection resources (including data)

Image Segmentation

Jianbo Shi and Jitendra Malik, Normalized Cuts and Image Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI) 2000.
Pedro F. Felzenszwalb and Daniel P. Huttenlocher, Efficient Graph-Based Image Segmentation, International Journal of Computer Vision, Volume 59, Number 2, September 2004. Project page
D. Comaniciu, P. Meer, Mean shift: A robust approach toward feature space analysis, IEEE Trans. Pattern Anal. Machine Intell., 24, 603-619, May 2002.

Video

Action recognition: Juan Carlos Niebles, Hongcheng Wang and Li Fei-Fei, Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words, British Machine Vision Conference (BMVC), Edinburgh, 2006.
Motion detection and gesture recognition: see ideas from Gary Bishop.
People tracking: Ramanan, D., Forsyth, D. A., Zisserman, A., Tracking People by Learning their Appearance, IEEE Pattern Analysis and Machine Intelligence, Jan 2007. Code

Resources: action recognition datasets, CVPR 2006 Human Motion tutorial

Other

Feel free to propose your own project idea! If you do this, please contact me in advance of submitting your project proposal.