COS 429 - Computer Vision
Proposals due Thursday, Dec. 15
Presentations on Thursday, Jan. 12
Written reports due Tuesday, Jan. 17
No late presentations or reports allowed.
The final assignment for this semester is to do an in-depth project
implementing a nontrivial vision system. You will be expected to
design a complete pipeline, read up on the relevant literature,
implement the system, and evaluate it on real-world data. You will
work in small groups (2-3 people), and must deliver
- A short (2 paragraph) proposal on December 15
- A 10-15 minute group presentation describing your system, and
- A report on your system. This should be in the style of
a research paper, and should include sections on previous work,
design and implementation, results, and a discussion of the strengths
and weaknesses of your system. The report should be in HTML format,
and we expect lots of pretty pictures!
- Set up a webcam in a public space and perform tracking, counting, and/or
classification of people, cars, etc.
- Image mosaicing, including automatic image alignment and multiresolution
- Foliage/tourist removal from several photos of a building. An important
question to answer is whether you want to attempt 3D reconstruction as part
of the process, or whether you want to consider it as a purely 2D problem.
- Video textures - see the SIGGRAPH paper linked from the
textures web page.
- OCR or handwriting recongition. This can be based on templates
or on (some simplified version of) the "shape context" approach of
Belongie, Malik, and Puzicha. See the ICCV paper on
their web page.
Project ideas for those with graphics experience:
- Inserting computer-generated objects into a video sequence taken with a
moving camera. Use a calibration or structure from motion method to
recover the camera pose.
- Some variant of Facade (human-assisted architectural modeling
from a small number of photographs). See the the SIGGRAPH 96 paper
linked from the Facade
- Vision-based automatic image morphing (e.g., of faces). That is, you
use an optical flow or other correspondence method to generate
matches between images, then use a morphing algorithm to generate
- Image-based visual hull (shape from silhouettes) for moving scenes.
See the SIGGRAPH 2000 paper, linked from their
smr at princeton edu