Hi - I liked the Wee thing:-) Very clever. The Actor Machine has an idea that I would like to include to motion capture - learning from previous movements. I'd like the character to compare earlier attemps or exercises and learn from them. (Kind of intellectual environment - for learning golf this would mean that character would be comparing earlier swings to it's own swing. This is good because we all have a different swing - body build etc.)
Here are some more links: EyeCon - a free motion capture from video http://www.frieder-weiss.de/eyecon/index.html wireless Sensor-to-midi (Maybe a solution???) http://www.infomus.dist.unige.it/eywindex.html Body Tracking from Single-Camera Video http://www.merl.com/projects/body/ Hannu > Hi Guys, > > Slightly off beam in relation to Mo Cap and animation. > > Could this app have any impact on the way > animations are done in the future - could we even say revolutionary :) > > http://www.actormachine.com/index.html > > Note the Team page - Ken Perlin, Chief Technology > Advisor - he of Perlin Noise fame and Tron. > > Cheers > Aidan > > > > At 15:08 04/02/2008, you wrote: >>Here's some research I found on the subject: >> >>Design of a Body-Driven Multiplayer Game System >>(Sami Laakso and Mikko Laakso) >> >>"So far camera-based user interfaces have been used in various >>entertainment or education applications, ranging from interactive dance >>space [Sparacino 2001] to martial arts training [Hämäläinen et al. 2005]. >>Today there are also several commercial camerabased body-driven game >>systems available, both complete game systems such as Mandala GX System >> by >>Vivid Group [http://www.vividgroup.com/] and home-sized devices such as >>Eyetoy for Sony PlayStation 2 [http://www.fmod.org/]."; >> >>"The software was coded in C++ on a Windows platform. The computer vision >>component was developed on top of the video-processing platform, EyesWeb >>Design of a Body-Driven Multiplayer Online Game System ● 7 >>ACM Computers in Entertainment, Vol. 4, No. 4, October 2006. >>[http://www.eyesweb.org/], using Intel Integrated erformance Primitives >>(Intel IPP) [http://www.intel.com/software/products/ipp/], and the Open >>Source Computer Vision Library >>http://www.intel.com/technology/computing/opencv/] for additional image >>processing. The 3D graphics output was obtained by using OpenGL, and >> audio >>effects obtained with an F-Mod audio engine [http://www.fmod.org/] and >> the >>Simple Direct Media Layer [http://www.libsdl.org/]."; >> >>(This is an old project :-) http://www.kickasskungfu.net/en/) >> >> >>Other articles tha might interest you: >>(Not public so I cannot share with the list. If anyone is interested, >> I'll >>email them to your personal email.) >> >>Markerless 4 gestures 6 DOF real-time visual tracking of the >>human hand with automatic initialization >>Markus Schlattmann, Ferenc Kahlesz, Ralf Sarlette and Reinhard Klein >> >>Automatic Detection and Tracking of Human Motion >>with a View-Based Representation >>Ronan Fablet and Michael J. Black >> >>A Fast and Handy Method for Skeleton-Driven Body Deformation >>WANG ZHAOQI, MAO TIANLU, AND XIA SHIHONG >> >>Software and Methods for Motion Capture and Tracking in Animation >>J Condell and G Moore, J Moore >> >>A posture optimization algorithm for model-based >>motion capture of movement sequences >>Jure Zakotnik a,∗, Tom Matheson b, Volker Dürr a >> >>Maximizing Validity in 2D Motion Analysis >>Martin Eriksson Stefan Carlsson >> >>A Novel Framework for Athlete Training Based >>on Interactive Motion Editing and Silhouette Analysis >>Shihong Xia, Xianjie Qiu, Zhaoqi Wang >> >> >>Interesting stuff - but not very much applications - or I have not found >>them... >> >>br. Hannu >> >> >> >> >> > I think it's somewhat doable already, it's just a matter of combining >> > different technologies. >> > The biggest drawbacks of a single camera setup are occlusion and >> > missing depth information. Depth information can already be derived >> > from a single camera video rather well, but occlusion is still a hard >> > problem. There's no 'clean' way to get around it, all you can do is >> > quesstimate. >> > A similar problem I've been thinking of is tracking a (computer) >> > player's head (or eyes) to get the same functionality that TrackIR >> > has. It's a fairly controlled subset of the >> > single-camera-motion-tracking problem and would be an excellent start: >> > It would enable tracking with a single webcam, no additional HW >> > needed. >> > >> > On 04/02/2008, [EMAIL PROTECTED] <[EMAIL PROTECTED]> wrote: >> >> Look at http://www.motion-capture.de/ >> >> >> >> Videotrack is a motion capture software for movements. >> >> >> >> I'd like to see a software that captures movements from video and >> >> compines >> >> it to a character. Like "Shadow-Chaser", but the software would >> compere >> >> the movements - as well as the person. >> >> link -> >> >> >> http://www.5star-shareware.com/Windows/Hobby/Sport/shadow-chaser-screenshot.html >> >> >> >> I read some research papers and it might be possible in near future, >> but >> >> at the moment there are a lot of difficulties. (Problems in >> model-based >> >> approaches that use single video, but with extra information it might >> be >> >> done - also low cost. High end mocap solutions are working ofcourse.) >> >> >> >> Hannu >> >> >> >> >> >> >> >> >> > > > >
