Research Areas Real-time Detection # 3-D Object Detection using Randomized Trees and Ferns # Augmenting Deformable Surfaces 3-D Surface Modeling # Deformable 3D Surfaces from Single Videos # Local Descriptor for Dense Wide-Baseline Stereo Matching Face and Body Modeling # Faces from Single Video Sequences # Temporal Models for Body Tracking # Spatio-Temporal Pose Detection # Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture # Tracking Multiple People in a Multi-Camera Environment
http://cvlab.epfl.ch/research/index.php
AVT Stingray FireWire Cameras * Excellent Price/Performance Ratio * High bit-depth (14-bit or 8-bit output, user-selectable) * VGA(640x480) – 5MP Resolutions Available The AVT Stingray camera family offers high-performance cameras that utilize a high-speed IEEE-1394-b interface at an economical price. Using Sony CCD sensors, 14-bit depth output, and on-board SmartFeatures allows for greater flexibility in demanding image applications. Every member of the Stingray family has high-sensitivity and is available in color or monochrome versions. The Stingray is compatible with PC (including WMD) or Linux environments. Each camera includes a FireWire cable, driver and SDK CD. Optional 1/4-20 mounting adapter #59-157, 12-pin trigger I/O cable, and laptop FireWire card are available.
http://www.edmundoptics.com/onlinecatalog/displayproduct.cfm?productid=2942
The goal of the CMUcam project is to provide simple vision capabilities to small embedded systems in the form of an intelligent sensor. The CMUcam3 extends upon this idea by providing a flexible and easy to use open source development environment that complements a low cost hardware platform. The CMUcam3 is an ARM7TDMI based fully programmable embedded computer vision sensor. The main processor is the NXP LPC2106 connected to an Omnivision CMOS camera sensor module. Custom C code can be developed for the CMUcam3 using a port of the GNU toolchain along with a set of open source libraries and example programs. Executables can be flashed onto the board using the serial port with no external downloading hardware required.
http://www.cmucam.org
Computer Vision for Artists and Designers: Pedagogic Tools and Techniques for Novice Programmers This article also appears in the following publications ABSTRACT "Computer vision" refers to a broad class of algorithms that allow computers to make intelligent assertions about digital images and video. Historically, the creation of computer vision systems has been regarded as the exclusive domain of expert researchers and engineers in the fields of signal processing and artificial intelligence. Likewise, the scope of application development for computer vision technologies, perhaps constrained by conventional structures for research funding, has generally been limited to military and law-enforcement purposes.
http://www.flong.com/texts/essays/essay_cvad
Daito has just posted this amazing video of smart laser tracking (see below). Laser is projected onto paper and at the same time can read constraints as well as obstacles in physical world. Examples include being able to contain the laser using hands, laser behaviour on drawn paper and more. Some note from this laser research: The piece is based upon a 3d tracking technology developped in our lab in 2003, using a laser diode, a pair of steering mirrors, and a single non-imaging photodetector called the “smart laser scanner” (for details, see here).
http://www.creativeapplications.net/e.../sticky-light-smart-laser-environment
OpenCV Swiki This swiki is a collaborative tool for the OpenCV Community. Note on how to contribute Documents, papers and links of interest.
OpenCV : list archive and comments. Samples using OpenCV. Projects and Essays using OpenCV. Failures and BUG report page. OpenCV Resource files * Haar Cascades
OpenCV : list archive and comments. Samples using OpenCV. Projects and Essays using OpenCV. Failures and BUG report page. OpenCV Resource files * Haar Cascades
http://alereimondo.no-ip.org/OpenCV/16
Description d'un procédé de stabilisation numérique sur une vidéo.
http://pages.cs.wisc.edu/~fliu/project/3dstab.htm
Masquage automatique de visages dans les vidéos avec openCV.
http://jilt.indivia.net/docu/doKu/doku.php?id=projects:web_tool
Librairie C++ pour la reconnaissance de marqueurs et la réalisation d'interfaces physiques. Exemple : une application de boite à rythmes. Permet de fabriquer ses marqueurs.
http://www.d-touch.org
Logiciel de vision pour machines / robots : capture de l'image, analyse, traitement par modules (filtres, détection de contours, de blobs, etc.). Peut communiquer par OSC / série / USB HID. Serveur web intégré pour diffusion MJPEG. Serveur d'API pour modification à distance. Controle d'action sur systèmes robotiques
http://www.roborealm.com/help/index.php
