yes pix_opencv, thx for that by the way!
of course, if you want you can link the video, i can share the patch too, but it's really a clone of your example (also the patch have network stuff for the voice recognition). it works well for 2d positioning, but for 3d i didn't found an open source solution, so i am using facetracker -> pd -> blender: http://www.vimeo.com/5699993
if anyone know an open source solution...
also sorry for everyone who likes mel gibson :)
pat
patrick wrote:
yes pix_opencv, thx for that by the way!
of course, if you want you can link the video, i can share the patch too, but it's really a clone of your example (also the patch have network stuff for the voice recognition). it works well for 2d positioning, but for 3d i didn't found an open source solution, so i am using facetracker -> pd -> blender: http://www.vimeo.com/5699993 u
wow!
what do you mean ? facetracker is a closed source program that gives you the orientation and movemvyent of the eyes?
what information is lacking from pix_opencv??
saludos, sevy
if anyone know an open source solution...
also sorry for everyone who likes mel gibson :)
pat
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
yes, faceapi by seeing machines is closed source (there's a non-commercial license with limitations) and guess what yves, only for windows :)
basically what is missing from opencv is an 6 DOF Head Tracking.
à + pat
patrick wrote:
yes, faceapi by seeing machines is closed source (there's a non-commercial license with limitations) and guess what yves, only for windows :)
grrrr.... of course, no windows machine here.
basically what is missing from opencv is an 6 DOF Head Tracking.
and the 6 point are : eyes, nose, mouth, ears ? is it??
something could be done maybe with SURF algorithm.
salaam, sevy
à + pat
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
On Tue, 2010-08-17 at 13:58 +0200, ydegoyon@gmail.com wrote:
patrick wrote:
yes, faceapi by seeing machines is closed source (there's a non-commercial license with limitations) and guess what yves, only for windows :)
grrrr.... of course, no windows machine here.
basically what is missing from opencv is an 6 DOF Head Tracking.
and the 6 point are : eyes, nose, mouth, ears ? is it??
I guess "6 DOF" refers to "6 Degrees of freedom", which means, tracking both the position (X, Y, Z) and the orientation (pitch, roll, yaw).
Roman
Roman Haefeli wrote:
On Tue, 2010-08-17 at 13:58 +0200, ydegoyon@gmail.com wrote:
patrick wrote:
yes, faceapi by seeing machines is closed source (there's a non-commercial license with limitations) and guess what yves, only for windows :)
grrrr.... of course, no windows machine here.
basically what is missing from opencv is an 6 DOF Head Tracking.
and the 6 point are : eyes, nose, mouth, ears ? is it??
I guess "6 DOF" refers to "6 Degrees of freedom", which means, tracking both the position (X, Y, Z) and the orientation (pitch, roll, yaw).
yes of course... don't know why i was thinking of points tracking.. it could also be done this way cos you can calculate vectors from the points
sevy
Roman
While I was checking out a Canon EOS 5D automatic face detection and focus, I wondered why this camera can do so effortless and the OpenCV on a Mac 8 core machine uses one Processor with 250% for that. When changing to greyscale colorspace and reducing the resolution to a quarter of PAL one get under 100% but it still still seems like a lot. Any Ideas why that could be?
m.
Am 19.08.2010 um 13:34 schrieb ydegoyon@gmail.com:
ola,
basically what is missing from opencv is an 6 DOF Head Tracking.
do you have an idea on which algorithm it is based? i googled a bit but couldn't find really valuable information on this...
saludos, sevy
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
On Thu, 19 Aug 2010, Max wrote:
While I was checking out a Canon EOS 5D automatic face detection and focus, I wondered why this camera can do so effortless and the OpenCV on a Mac 8 core machine uses one Processor with 250% for that. When changing to greyscale colorspace and reducing the resolution to a quarter of PAL one get under 100% but it still still seems like a lot. Any Ideas why that could be?
There are several reasons, one of which being that specialised processors can still be much faster than general processors (just look at what video cards can do...) but it's also very possible that they downscale the image by a factor of 2*2 (4 times faster) or 4*4 (16 times faster) before starting to apply the face detection.
Note also that converting from GEM's YUV to RGB upscales the U and V channel by a factor of 2 horizontally (no vertical scaling), which means that the RGB data is a bit redundant. That's the "422" mode. For cameras in YUV "420" mode, there's also vertical scaling, therefore, in my camera code, I have added an option to convert directly from YUV420 to a twice narrower, twice shorter RGB picture, for the case where the chroma resolution is absolutely essential. It reduces a lot of waste.
_ _ __ ___ _____ ________ _____________ _____________________ ... | Mathieu Bouchard, Montréal, Québec. téléphone: +1.514.383.3801
ola,
i dunno, is the source of the sofware coming with your cam available?
second, you don't need to convert to grayscale, it's already made internally
saludos, sevy
Max wrote:
While I was checking out a Canon EOS 5D automatic face detection and focus, I wondered why this camera can do so effortless and the OpenCV on a Mac 8 core machine uses one Processor with 250% for that. When changing to greyscale colorspace and reducing the resolution to a quarter of PAL one get under 100% but it still still seems like a lot. Any Ideas why that could be?
m.
Am 19.08.2010 um 13:34 schrieb ydegoyon@gmail.com:
ola,
basically what is missing from opencv is an 6 DOF Head Tracking.
do you have an idea on which algorithm it is based? i googled a bit but couldn't find really valuable information on this...
saludos, sevy
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
On 08/16/2010 11:40 AM, patrick wrote:
yes pix_opencv, thx for that by the way!
of course, if you want you can link the video, i can share the patch too, but it's really a clone of your example (also the patch have network stuff for the voice recognition). it works well for 2d positioning, but for 3d i didn't found an open source solution, so i am using facetracker -> pd -> blender: http://www.vimeo.com/5699993
if anyone know an open source solution...
also sorry for everyone who likes mel gibson :)
I would have used Tom Cruise for stupid, but cool program.
pat
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
-
Johnny Ferguson -
Mathieu Bouchard -
Max -
patrick -
Roman Haefeli -
ydegoyon＠gmail.com