Two demonstration applications using the Intel Open Computer Vision Library (OpenCV) have been uploaded in the CVS repository.
The CAMSHIFT demonstration (CVS module CamshiftDemo) illustrates a now classical face tracking method based on color.
Haar detection demo (CVS module: HaarDetectionDemo) illustrates the use of boosted classifiers for object detection (very successful with faces).
Both demonstrations introduce new modules that will be contributed to the MFSM web site shortly.... read more
A demonstration application illustrating statistical adaptive color background model-based change detection has been uploaded in the CVS repository (module name: ChangeDetection). The principles of the system are described in several publications, see e.g.:
Alexandre R.J. Franois, "Software Architecture for Computer Vision," Emerging Topics in Computer Vision, G.Medioni and S.B. Kang Eds., Prentice Hall, 2004, pp. 585-654.... read more
The webcam computer vision (WCCV) project focuses on computer vision algorithms and systems that follow the web cam paradigm: cheap, robust and efficient. It will comprise designs, patterns, cross-platform code, tutorials and examples.
The project leverages the Software Architecture for Immersipresence (SAI) framework for the design of modular systems that perform asynchronous parallel processing of generic data streams.... read more