Google Summer of Code (GSOC) 2010 for OpenCV
GSoC 2011 page is here
March 18, 2010: OpenCV has been accepted as one as a mentoring organization in GSoC 2010!
See the timeline.
Short time line now:
- August 16th They are supposed to then document the code and stop work by August 16th
Melange site to manage students etc http://socghop.appspot.com/gsoc/program/home/google/gsoc2010
- August 20th: We then submit the student's evaluations by Aug 20th UTC 1900.
August 30th-Sept 10. Students upload their code to http://code.google.com/p/google-summer-of-code-2010-OpenCV (will be created on Aug 30th).
- October 23-24. Participant's meet up at Google subsidized by same.
Open source Computer Vision Library (OpenCV)
The Open Source Computer Vision Library (OpenCV) contains a comprehensive set of both classic and state of the art computer vision and machine learning algorithms. OpenCV is open source and free for commercial or research use under a BSD license. Computer vision algorithms in OpenCV can be used, for example, to detect and recognize faces, identify objects, classify human actions in videos, track camera movements, track moving objects, extract 3D models of objects, produce 3D point clouds from stereo cameras, stitch images together to produce a high resolution image of an entire scene, find similar images from an image database, remove red eye from images taken using flash, follow eye movements, recognize scenes and establish markers to overlay the scenes with augmented reality to name but a few applications. OpenCV has well over 2 million downloads, has an active user group with over 41 thousand registered members. The O'Reilly coding book on OpenCV, "Learning OpenCV" has been the best selling computer vision or machine vision book for a year and a half now.
OpenCV is used extensively in companies, research groups and by governmental bodies. Some well known companies that use OpenCV are Google, Yahoo, Microsoft, Intel, IBM, Sony, Honda, Toyota. Many startups such as Applied Minds, VideoSurf, and Zeitera make extensive use of OpenCV. OpenCV's deployed uses span the range from stitching streetview images together, detecting intrusions in surveillance video in Israel, monitoring mine equipment in China (or, more controversially, OpenCV is used in China's "Green Dam" internet filter), helping robots navigate and pick up objects at Willow Garage, detection of swimming pool drowning events in Europe, running interactive art in Spain and New York, checking runways for derbies, inspecting labels on products in factories around the world on to rapid face detection in Japan.
OpenCV leans mostly towards real time vision applications and takes advantage of MMX and SSE instructions when available. A CUDA interface is being developed right now. There are over 500 algorithms and about 10 times as many functions that compose or support those algorithms. OpenCV is written natively in C++ and has a templated interface that works seamlessly with std containers. Its native data type is a general matrix class that reference counts and leverages LAPACK and (in April) EIGEN matrix libraries. OpenCV also has a full custom Python interface and, using SWIG, OpenCV has interfaces to Matlab and Octave. OpenCV was built to provide a common infrastructure for vision applications and to accelerate the use of machine perception in the commercial products. To enable this, OpenCV has a BSD license to make it easy for businesses to use and modify the code.
Applying for OpenCV GSOC 2010
Student application deadline April 9th
Apply to Google first by going here.
- See Google's summer of code 2010 page.
Read the GSOC FAQ
Other links for mentor and Student Google Summer of Code 2010 Instructions and Links
- Student application starts March 29th, 2010.
Interested students need to start out by applying to Google.
Who are we looking for
- Students who
- have a background in computer vision (especially geometric vision and features) and/or signal processing
- or at least a good understanding of mathematical programming
- Linear algebra
- Numerical optimization
- or at least a good understanding of mathematical programming
In general, you must already know (not want to learn on the job) C++ with STL and Boost
- Especially interested in people who can write optimized C code together with SSE.
- But some projects below require Python
- This year we can also make use of:
- A web programmer who has experience dealing with massive amounts of data (for example, a back end to streetview using cell phone data)
- Android programmers (front end image capture, image stitching etc).
- have a background in computer vision (especially geometric vision and features) and/or signal processing
To Apply
To apply:
- Read the project ideas and make sure your experience is appropriate to the project.
You MUST apply by going through Google. Apply here
- You may contact the mentor beforehand to discuss the project.
Use "OpenCV GSOC2010" somewhere in the subject line of the email.
Fill out the application form OpenCV_GSOC2010_Application
Send in an application, with subject "OpenCV GSOC2010 Application" to (remove the "-delete-"s)
Project Ideas
- Please choose from one of the projects below.
Students may suggest their own, well thought out and documented ideas which should also have project timeline for completion. These will only be accepted if one of the mentors likes it. The project should use a substantial, proven technology and be of general interest. This is not the place to finish a class project or incomplete.
- Each project will have short, medium and an ultimate goal. The ultimate goal is not expected to be finished in one summer but we hope that the student will continue as a contributor and see if finished.
- Each project will end with a demo that will be posted on youtube.
Mark Asbach
Image Features, OpenCV on 64bit Mac OS X (2 projects)
- We want to add a new and powerful feature type to OpenCV
- We want OpenCV to work well on 64 bit Mac OS X.
Gary Bradski
OpenCV on Android: (three projects that are related)
- Streetview Stitching
- Augmented Reality
Open Collage:
- Open source project to make nice image collages
Victor Eruhimov
Object Recognition:
- Assess and improve OpenCV machine learning algorithms
Vadim Pisarevski
OpenCV GUI and Performance: (2 projects)
- Enhance the GUI for vision algorithms
- Parallelize some important algorithms
Nicolas Saunier
Motion Magic: (3 related projects)
- Background modeling for foreground segmentation. Improve the API.
- Tracking a textured object with point features.
- Motion trajectory analysis.
Projects Mentors
In the below, get rid of the -delete- to make the emails work.
Mark Asbach Fraunhofer IAIS Schloss Birlinghoven Sankt Augustin, Germany http://mmprec.iais.fraunhofer.de/asbach.html -delete-mark.asbach@-delete-iais.fraunhofer.de
Gary Bradski Senior Scientist, Willow Garage Consulting Prof. Stanford U. OpenCV Founder, Technical Content Owner http://www.willowgarage.com/pages/people/gary-bradski-senior-researcher -delete-bradski@-delete-willowgarage.com
Victor Eruhimov OpenCV founding team/Senior Researcher Argus/Itseez founder NNU Lecturer -delete-relrotciv@-delete-googlemail.com
Vadim Pisarevsky OpenCV founding team/Czar -delete-Vadim.-delete-Pisarevsky@-delete-gmail.com
Nicolas Saunier, Ph.D. Assistant Professor Civil, Geological and Mining Department (CGM) École Polytechnique de Montréal http://nicolas.saunier.confins.net -delete-nicolas.saunier@-delete-polymtl.ca
Our Application to GSOC
