Open Source Computer Vision Library (OpenCV)

Web Page: http://opencv.willowgarage.com/wiki/GSOC_OpenCV2011

Mailing List: http://opencv.willowgarage.com/wiki/

The Open Source Computer Vision Library (OpenCV) is a comprehensive computer vision library and machine learning (over 2000 functions) written in C++ and C with additional Python and Java interfaces. It officially supports Linux, Mac OS, Windows, Android (with several iOS ports, one of which we will canonize). OpenCV has specific optimizations for SSE instructions, CUDA and especially Tegra. There is an active user group of nearly 45 thousand members and download are approaching 3.5M. The book that the Admin wrote on using OpenCV out by O'Reilly press: Learning OpenCV: Computer Vision with the OpenCV Library has been the top selling book in computer vision and machine learning for 3 years now. OpenCV is already far along in the application process for joining Khronos (http://www.khronos.org/), a consortium of 100 companies setting agreed standards interfaces for a number of open source libraries including OpenCL and OpenGL.

Projects

• Body Tracking with Kinect I would like to use depth Data and combine it with the image data along with some other heuristics to do body tracking, preferably dense.I have previously worked a lot Images while writing a paper and recently submitted it in the ICCV on structure from motion,so i also have been on the generating end of depth data. The primary task of my Project in Computer Vision Course was to do body tracking on humans. We used multiple camera's and our own flavour of Tomasi Kanade. Kinect should shed new ligh
• High quality structure from motion for rigid models. I started my thesis on the extraction of 3D information from uncalibrated videos (i.e. type of cameras unknown) two years ago and I had not found an efficient API to easily try some classical "structure from motion" methods. I propose to build an API with various methods to be used by any new users in the field and expandable enough to allow integration of new methods. I will focus my efforts on rigid 3D models but add the possibility to easily add methods for non-rigid models.
• Improved Object Tracking in OpenCv I am interested in the object tracking project. My main motivation for working on this project is that I am interested in Augmented Reality. Hence, alongwith the proposed approach I would also like to propose an addition that the algorithm can take a prior model.
• Object Tracking Algorithms for OpenCV In this project we will contribute some newer, state-of-the-art object tracking algorithms to OpenCV.
• OpenCV on iOS/iPhone/iPad I'm a gradudate students in Dartmouth College Computer Science, I started to work in the field of mobile sensing from last summer, with focus on phone camera. I've been working with OpenCV on iPhone for a while, I successfully implemented and ported 3D head pose tracking, eye gaze tracking, AMM fitting algorithms on an iPhone. Prior to this, I worked on several computer vision and machine learning projects. I'm experienced in developing vision project in C with OpenCV, familiar with iOS and Android.
• OpenCV on iOS/iPhone/iPad The goal of the project is to bring iOS port into official build-test system. The official support of OpenCV on iOS will not only promote the OpenCV library as the standard in the field of Computer Vision, but also will make development of Computer Vision applications faster and easier, contribute to intelligence of other applications and can even facilitate in conducting large-scale research projects.
• OpenCV samples in Python The aim of this project is extending OpenCV Python examples with a comprehensive set of new nontrivial samples. Also I want to improve the Python interface. Project is based on extensive personal OpenCV Python experience.
• Tutorials and Examples My goal for this project is to give OpenCV users a single resource of information that fills all their programming needs and answers all their questions. Either if you are a first-time user or a intermediate-level one, we should provide you with interesting, easy-to-understand and enticing material that makes you feel curious and motivated about Computer Vision (and also, we should convince you that OpenCV is the way to go)
• Tutorials and examples for the OpenCV Library The success of any open source project depends mainly on two factors. First, it is just how well it is written and here I refer to the fact just how fast and usable it is. The second factor is how easy it is to use it. It is pointless to create a state of art solution to something if no one else understands it how and when to use it. Through my project I intend to improve this later on of the OpenCV by writing multiple quality source code examples accompanied by in-depth tutorials for them.