BazAR is an augmented reality library based on efficient computer vision techniques. It contains an easy to use geometric and photometric camera calibration system. It works in real-time with one or more cameras. A simple OpenGL GLSL shader augments the video stream by inserting artificial 3D objects, shaded with the calibrated lightmap, on a real surface. BazAR is based on a very fast textured planar object detector and features point classification trees.
reacTIVision is a computer vision framework for the fast and robust tracking of fiducial markers attached to physical objects, as well as for multi-touch finger tracking. It was mainly designed as a toolkit for the rapid development of table-based tangible user interfaces and interactive multi-touch surfaces such as the reacTable. Client application examples are available for various programming environments such as C++, Java, C#, Processing, PureData, Max/MSP, and Quartz Composer.
CellProfiler is a system for analyzing cell images. It is designed for biologists without training in computer vision or programming to make quantitative measurements of cells in thousands of images automatically. It is implemented using Matlab, but compiled standalone versions are available.
Waveblend is a focus enhancing tool. It implements an image fusion algorithm to combine many images to one, using the images most in focus at each point; the resulting image is in focus everywhere. It uses the complex dual-tree two dimensional discrete wavelet transform algorithm, with a number of pre- and post-processing steps.
Brook for GPUs is a compiler and runtime implementation of the Brook stream programming language for modern graphics hardware. The goals for this project are to demonstrate general purpose programing on GPUs, to provide a useful tool for developers who want to run applications on GPUs, and to research the stream language programming model, streaming applications, and system implementations.