Video processing source code for algorithms and tools used in software media pipelines. The currently available source code is written in C++ with their associated libraries and DirectShow Filters. Filters include an H.264 encoder, H.264 decoder, H.264 source filter, RTSP sink and source filters, YUV source, RGB to YUV color conversion, croppers, scalers, video mixing/picture in picture filters, rotate filter, virtual mic, and many more. Code is released under BSD license with exception of H.264 codec related classes which are released under LGPL.
Track & log x & y displacement, in realtime, of object in webcam
Track, in realtime, horizontal and vertical displacement of object in webcam. Log timestamp, x and y to comma-separated value (.csv) file importable to spreadsheet. Uses Lukas-Kanade algorithm and based on lkdemo.cpp in OpenCV, stripped down to track single point in high contrast against a uniform background. Based on the BSD licensed OpenCV, TrackXY also has BSD-style license. I am a bit embarrassed to be posting this here, because it's such a rudimentary program, but I couldn't find any other ready-made program that would track an object in real-time from webcam, other than an $80 special-purpose program used in the original (torsion balance) experiment we were replicating. I released TrackXY to reduce barriers to entry to science. Planned features include versions for each platform, a GUI, comprehensive data management, and data analysis tools. To analyze motion in /recorded/ video (not real-time), you may prefer something like PhysMo, also a SourceForge project.
Fully automated segmentation of moving objects from a stationary scene using pre-stored scene images. Needs no external parameters or settings; all parameters are derived internally from the pre-stored images. Implemented using OpenCV framework.
QC Player Plus is a simple Quartz Composer composition player. It takes the Apple-supplied "QC Player" example project, improves the rendering pipeline and adds the features you need for it to be useful in a live context.
Video Recorder/Reader for Virtual Reality Experiments
The tools in this project are used by the Virtual Reality lab at University of Texas at Austin to record the stream of rendered images (OpenGL) and combine them with eye tracking data (if eyes are being tracked) and user defined metadata. The project is split into two parts. DVR is used to record the data stream as a QuickTime movie. The RVD is used to read the movie recorded by the DVR. Acknowledgements: John Stone - created most of the code base Gabriel Diaz and Joseph Cooper - QA Dmitry Kit - Maintainer/QA Dr. Mary Hayhoe and Dr. Dana Ballard Virtual Reality Laboratory at University of Texas in Austin