dannyxyz22 / ehci Goto Github PK
View Code? Open in Web Editor NEWAutomatically exported from code.google.com/p/ehci
Automatically exported from code.google.com/p/ehci
Would it be possible to add eye-tracking as well?
After all, you have a pretty good idea about where the eye is at any
moment. You would then have to add a separate set of tracking points to
detect the direction of gaze? Tracking one eye should be enough.
It would be awesome to have an idea about where on the screen the user is
looking. :-) Think about the panda3d/pygame possibilities (targeting your
air to air missiles by looking at the enemy) as well as new assistive
technologies.
Original issue reported on code.google.com by [email protected]
on 20 Feb 2010 at 9:11
What steps will reproduce the problem?
1. Execute the boxView3d sample
What is the expected output? What do you see instead?
It is expected that when the user moves to the right, the boxes will "move"
to the left. In version 0.4 the boxes are moving to the right.
It is just because the camera is now showing the mirror of what it is seeing.
Original issue reported on code.google.com by [email protected]
on 14 Aug 2008 at 4:09
What steps will reproduce the problem?
1. Use the trunk version of EHCI 0.7
2. Compile it and try to run with Logitech webcam Pro9000 in Ubuntu
Do you have any advice on what may be occurring? I am compiling everything out
of the box and it's producing a.out just fine. When I try running after using
my Makefile it responds with
"Could not initialize capturing..."
Segmentation fault
Is this an issue that is possibly due to my camera version? I used the
config.ini recommended in one of the other issue threads, and everything is
setup to compile correctly.
Thanks!
Original issue reported on code.google.com by [email protected]
on 18 Jan 2011 at 5:16
Hi!
I wanna do something like this:
http://www.youtube.com/watch?v=aE0F4F5WIuI&feature=channel_page
I wrote a code but it doesn't work :)
I don't know why but I think it should work! Take a look at this:
http://rapidshare.de/files/47764349/bg.tar.bz2.html
it is the full source based on "background.tar.gz-code" ( the author is:
http://www.youtube.com/
user/dannyxyz22 )
First I take a cam shot where I'm gone from the cam view. Then I try to find a
difference between
two IplImages: canvas (current video frame) and bgWithoutFace (fixed frame
without me in it).
But it doesn't work. I have no ideas why it happens.. It's just not work :)
Does anyone have any suggestions?
I use Gentoo Linux. C++, SDL + OpenCV.
Original issue reported on code.google.com by [email protected]
on 5 Jul 2009 at 7:18
Attachments:
What steps will reproduce the problem?
1.
2. a
3.
What is the expected output? What do you see instead?
Please use labels and text to provide additional information.
Original issue reported on code.google.com by [email protected]
on 27 Jul 2008 at 7:19
I have been trying to port your program to compile for mac os x under a xcode
project.
For this I had to change some of your code.
I am not an expert in C/C++ so if you find I am wrong at some point please
correct me.
Steps I have made:
1st: I changed most of your includes to a more dynamic style such as
<OpenCV/OpenCV.h>, <OpenCV/highgui.h>.
2nd: I opted to remove the support for freeglut for the time being and changed
the writing code to use standard glut library that is included
with mac os x.
3rd: I had problems while linking files due to some declarations on ehtc.h. To
solve this I moved some declarations to the .cpp files and
flaged others as extern.
I have a prototype working version at the moment and including a zip with all
the files attached fr your consideration.
Issues:
I am having issues while running the code.
The program runs properly for a bit (10-20 seconds) some times just a couple of
seconds and breaks with the following error:
...
Old size 188 new size 187
ehci: Deleted 67
Ransac in action: updating modelPoints tp 186 mp 187
Erasing 67
Old size 187 new size 186
ehci: Deleted 114
Ransac in action: updating modelPoints tp 185 mp 186
Erasing 114
Old size 186 new size 185
ehci: Deleted 60
Ransac in action: updating modelPoints tp 184 mp 185
Erasing 60
Old size 185 new size 184
ehci: Deleted 13
ehci: Deleted 16
ehci: Deleted 54
ehci: Deleted 68
ehci: Deleted 136
Ransac in action: updating modelPoints tp 179 mp 184
Erasing 13
Erasing 16
Erasing 54
Erasing 68
Erasing 136
Old size 184 new size 179
ehci: Deleted 127
Ransac in action: updating modelPoints tp 178 mp 179
Erasing 127
Old size 179 new size 178
ehci: Deleted 159
Ransac in action: updating modelPoints tp 177 mp 178
Erasing 159
Old size 178 new size 177
ehci: Deleted 110
Ransac in action: updating modelPoints tp 176 mp 177
Erasing 110
Old size 177 new size 176
ehci: Deleted 20
Ransac in action: updating modelPoints tp 175 mp 176
Erasing 20
Old size 176 new size 175
ehci: Deleted 3
Ransac in action: updating modelPoints tp 174 mp 175
Erasing 3
Old size 175 new size 174
/usr/include/c++/4.2.1/debug/vector:198:error: attempt to subscript
container with out-of-bounds index 173, but container only holds 173
elements.
Objects involved in the operation:
sequence "this" @ 0x0xbfffeed4 {
type = NSt7__debug6vectorI12CvPoint2D32fSaIS1_EEE;
}
Any Idea of what would be causing this problem?
Have you faced with the same problem before?
Original issue reported on code.google.com by [email protected]
on 31 May 2010 at 4:25
Attachments:
What steps will reproduce the problem?
1. svn checkout http://ehci.googlecode.com/svn/trunk/ ehci-read-only
2. edit CMakeCache.txt to enable //Build OpenGL Samples
BUILD_OPENGL_EXAMPLES:BOOL=ON
3. cmake .
What is the expected output? What do you see instead?
diediaga@diediaga-laptop:~/ehci-read-only$ cmake .
-- Looking for GLUT
-- Looking for GLUT - found : /usr/include
CMake Error: The following variables are used in this project, but they are set
to NOTFOUND.
Please set them or make sure they are set and tested correctly in the CMake
files:
GLUT_Xmu_LIBRARY (ADVANCED)
linked by target "6dofhand" in directory /home/diediaga/ehci-read-only/samples
linked by target "6dofhead" in directory /home/diediaga/ehci-read-only/samples
linked by target "boxView3d" in directory /home/diediaga/ehci-read-only/samples
linked by target "zoomHand" in directory /home/diediaga/ehci-read-only/samples
-- Configuring incomplete, errors occurred!
What version of the product are you using? On what operating system?
version 237 of the snv
my cumputer is running ubuntu 10.04
2.6.32-24-generic
opencv 2.1
Please provide any additional information below.
Original issue reported on code.google.com by [email protected]
on 24 Nov 2010 at 10:19
- Made ehci a lib
- Changed some code so that it compiles.
- Still some serious changes to made it work flawlessly (config.ini is not
- crlf just cr, therefore config.ini read fails.)
- Didn't do anything about python scripts.
Original issue reported on code.google.com by [email protected]
on 2 Apr 2009 at 2:03
Attachments:
What steps will reproduce the problem?
1. run the 6dofhead
2. produce abrupt head motion
3. head angles will accumulate errors
What version of the product are you using? 0.7
On what operating system? Win7
Any plans on implementing re-initialization to deal with error accumulation as
you outlined in "next step" in wiki?
Any other ideas on dealing with this? I'm using it with Kinect now, and while
it's beyond the scope of this project maybe the depth-map there can be used as
an additional input modality?
http://www.youtube.com/watch?v=MinkGUl2WnA
Original issue reported on code.google.com by alexleykin
on 8 Mar 2011 at 4:58
What steps will reproduce the problem?
1. I've got an IVTV capture card as /dev/video0 and my web cam on /dev/video1
and I don't find any way to get ehci to get the stream from the cam...
When I run the 6dofhand sample I recieve:
/
libv4l2: error setting pixformat: Périphérique ou ressource occupé
HIGHGUI ERROR: libv4l unable to ioctl S_FMT
HIGHGUI ERROR: libv4l unable to ioctl VIDIOCSPICT
Could not initialize capturing...
Erreur de segmentation
/
What version of the product are you using? On what operating system?
ehci-0.6 on opensuse 11.4 64
[email protected]
Original issue reported on code.google.com by [email protected]
on 17 Apr 2011 at 9:12
What steps will reproduce the problem?
1. while running samples m getting the error cannot initialize the capturing
2.
3.
What is the expected output? What do you see instead?
to capture the human present in front of the webcam
What version of the product are you using? On what operating system?
i m workin on ehci-0.6 in fedora 13 installed using vmware(virtual machine) n i
m using webcam for capturing
Please provide any additional information below.
i m a final year BE student working on a project based on ehci-0.6.i am able to
compile the ehci code but unable to run the samples present.
error i m getting is cannot initialise capturing.
can you plz suggest me to get the capture done.
Original issue reported on code.google.com by [email protected]
on 13 Mar 2011 at 6:52
What steps will reproduce the problem?
1. ./configure
2. make
3.
What is the expected output? What do you see instead?
What version of the product are you using? On what operating system?
ehci-0.4
Ubuntu-12.04 LTS
opencv-2.4.9
Please provide any additional information below.
Fails to locate share opencv libraries
Original issue reported on code.google.com by [email protected]
on 3 Sep 2014 at 10:02
Attachments:
What steps will reproduce the problem?
1. Using Eclipse in Windows Vista with OpenCV 2.0 since the codes didn't run in
OpenCV 2.4.3 (which is the latest version)
2. Gave all the relevant links to ehci files,and project gets built. Solved the
detection problem using issue no. 21 where [email protected] pointed out that
debug value needed to be 1.
3. Specified values in the config.ini file too
What is the expected output? What do you see instead?
The expected output of the program as per Daniel is that using the face
detection the perspective of the cubes should change. The problem is that when
I run the executable file,it detects the head in one frame, the cubes are
displayed in the background and then the executable stops responding. To check
how many frames are being captured, wrote a printf line("frame grabbed") after:
frame = cvQueryFrame( capture );
and in the command line,"frame grabbed" appears only twice.
In all likelihood,the frame capturing gets stuck after the first frame.
Hence I would like to know how to establish a continuous detection through the
frames,since I can see my face being detected before the executable stops
responding. The code for the program is pretty huge and I couldn't figure out
the problem. Any help would be beneficial. Its an exciting project.
What version of the product are you using? On what operating system?
Eclipse Helios for Windows Vista with OpenCV 2.0 and MinGW 4.6!
Please provide any additional information below.
Original issue reported on code.google.com by [email protected]
on 3 Mar 2013 at 2:23
Hi,
Im new to this and am looking for codes that can give me the head pose
information from videos. I came across your code and found that I could use
this. It is great work!!
I copied and pasted your "6dofhead.cpp" file into my "headposegoogle.cpp" file
and added the "echi.h", "echi.cpp" and "boxView3d.cpp" files, as directed in
the "Compiling on Windows" page. On building this, I am getting the following
errors.
"Error 23 error C3861: 'isEhciTextureCreated': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 602 headposegoogle
Error 24 error C3861: 'getEhciGlTexture': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 614 headposegoogle
Error 25 error C3861: 'getGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 632 headposegoogle
Error 26 error C3861: 'setGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 633 headposegoogle
Error 27 error C2227: left of '->imageData' must point to
class/struct/union/generic type d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 641 headposegoogle
Error 28 error C2227: left of '->widthStep' must point to
class/struct/union/generic type d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 642 headposegoogle
Error 29 error C3861: 'getGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 641 headposegoogle
Error 30 error C3861: 'getGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 641 headposegoogle
Error 31 error C2227: left of '->width' must point to
class/struct/union/generic type d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 643 headposegoogle
Error 32 error C3861: 'getGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 643 headposegoogle
Error 33 error C3861: 'getGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 662 headposegoogle
Error 34 error C3861: 'getGeneratedImage': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 663 headposegoogle
Error 35 error C3861: 'getEhciModelScale': identifier not found d:\demo
project\headposegoogle\headposegoogle\headposegoogle.cpp 745 headposegoogle
"
On googling this, I found some solutions. But I did not really understand how
to solve this. Is there any advice from you regarding this?
Also, just letting you know, I am intending to use this code for extracting
head pose information from recorded videos and use that information for further
work in my research. I want to be able to get the head pose information in the
form of numbers into a file. Thanks in advance for any help.
Cheers,
Jinesh
Original issue reported on code.google.com by [email protected]
on 3 Oct 2010 at 5:28
Hi there,
First off, it seems as if your program is the answer to what I've been looking
for! I have been looking for a program which can track and then output as
virtual control.
But the biggest problem I'm encountering right now is that I cannot run the 0.7
pack at all. Each of the executables will crop up a could not initialize
capturing error.
Seeing as I hit that wall, I gave the older builds a try and to my surprise,
0.6 works just fine. The 1.0 background windows program runs without hitch too.
Any ideas?
I've already tried running the 0.7 build on Windows 7 64-bit, XP SP3 and all
the compability modes, to no avail..
Original issue reported on code.google.com by [email protected]
on 20 Sep 2010 at 6:30
What version of the product are you using? On what operating system?
ehci 0.7 open cv2.2 windows 7 32 bit visual studios 2010
Please provide any additional information below.
Probably a stupid question, but after I built everything correctly with cmake
the debug files did not extract or don't exist. How do I get the files like
BUILD_ALL to run? I tried redoing the cmake process 4 or 5 times and none of
the times they extracted. I think the samples work and they have the debug
files, but are there debug files for the BUILD_ALL and INSTALL? Those files?
Thanks!
Original issue reported on code.google.com by [email protected]
on 16 Jun 2011 at 2:11
What steps will reproduce the problem?
1. . i am able to compile the code but couldnot run the sample programs.i am
facing the same program as posted by u.The error s as follows
After I compile the program
cd ehci-0.6
./configure
make
I am able to do the above with out any errors. Later when try running samples
I am getting the below errors
cd samples
make
./simple2d
(<unknown>:5940): GStreamer-CRITICAL **:
Trying to dispose element appsink1, but it is in READY instead of the NULL
state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
(<unknown>:5940): GStreamer-CRITICAL **:
Trying to dispose element ffmpegcsp1, but it is in READY instead of the NULL
state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
OpenCV Error: Unspecified error (unicap: failed to get info for device
) in CvCapture_Unicap::initDevice, file
/builddir/build/BUILD/OpenCV-2.0.0/src/highgui/cvcap_unicap.cpp, line 139
terminate called after throwing an instance of 'cv::Exception'
Aborted (core dumped)
2. but ven tried using
./samples/simple2d
the error i am facing is "couldnot initialise tha capturing"
blank window opens and goes on showing the error mentioned above and ends ven
given ctrl + c.
3.
What is the expected output? What do you see instead?
the expected output to open a window and display the capture the person present
in front of the webcam
What version of the product are you using? On what operating system?
. i am working on the ehci-0.6 library for tracking the the face in fedora 13
in vmware.
Please provide any additional information below.
Original issue reported on code.google.com by [email protected]
on 17 Mar 2011 at 11:06
What steps will reproduce the problem?
1. after ./configure run successfully make is showing errors
2. errors
3.
What is the expected output? What do you see instead?
I GET THIS ERROR AFTER MAKE WHILE INSTALLING EHCI 0.6
saurabh@saurabh-Aspire-5740:~/Desktop/ehci-0.6$ make
make all-recursive
make[1]: Entering directory `/home/saurabh/Desktop/ehci-0.6'
Making all in lib
make[2]: Entering directory `/home/saurabh/Desktop/ehci-0.6/lib'
make[2]: Nothing to be done for `all'.
make[2]: Leaving directory `/home/saurabh/Desktop/ehci-0.6/lib'
Making all in samples
make[2]: Entering directory `/home/saurabh/Desktop/ehci-0.6/samples'
Making all in data
make[3]: Entering directory `/home/saurabh/Desktop/ehci-0.6/samples/data'
make[3]: Nothing to be done for `all'.
make[3]: Leaving directory `/home/saurabh/Desktop/ehci-0.6/samples/data'
make[3]: Entering directory `/home/saurabh/Desktop/ehci-0.6/samples'
/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -lGL -lm
-L/usr/local/lib -lcv -lhighgui -lcvaux -lml -lcxcore -lglut -o 6dofhand
6dofhand.o ../lib/libehci.la
g++ -g -O2 -o .libs/6dofhand 6dofhand.o -lGL -lm -L/usr/local/lib
/usr/local/lib/libhighgui.so /usr/lib/libgtk-x11-2.0.so
/usr/lib/libgdk-x11-2.0.so /usr/lib/libatk-1.0.so /usr/lib/libgio-2.0.so
/usr/lib/libpangoft2-1.0.so /usr/lib/libpangocairo-1.0.so /usr/lib/libcairo.so
/usr/lib/libpango-1.0.so /usr/lib/libfreetype.so -lfontconfig -lgdk_pixbuf-2.0
/usr/lib/libgobject-2.0.so /usr/lib/libgmodule-2.0.so
/usr/lib/libgthread-2.0.so /usr/lib/libglib-2.0.so -lpng12
/usr/local/lib/libcvaux.so /usr/local/lib/libcv.so /usr/local/lib/libml.so
/usr/local/lib/libcxcore.so -lrt -lz -lpthread -ldl -lglut
../lib/.libs/libehci.so
6dofhand.o: In function `InitGL(int, int)':
/home/saurabh/Desktop/ehci-0.6/samples/6dofhand.cpp:578: undefined reference to
`gluPerspective'
6dofhand.o: In function `ReSizeGLScene(int, int)':
/home/saurabh/Desktop/ehci-0.6/samples/6dofhand.cpp:482: undefined reference to
`gluPerspective'
6dofhand.o: In function `DrawGLScene()':
/home/saurabh/Desktop/ehci-0.6/samples/6dofhand.cpp:436: undefined reference to
`gluLookAt'
collect2: ld returned 1 exit status
make[3]: *** [6dofhand] Error 1
make[3]: Leaving directory `/home/saurabh/Desktop/ehci-0.6/samples'
make[2]: *** [all-recursive] Error 1
make[2]: Leaving directory `/home/saurabh/Desktop/ehci-0.6/samples'
make[1]: *** [all-recursive] Error 1
What version of the product are you using? On what operating system?
UBUNTU 10.1
Please provide any additional information below.
I have tried other Opengl programs with gluperspective and they are running
fine.
I didnt have a problem with ./configure.
Please help me
Original issue reported on code.google.com by [email protected]
on 23 Mar 2011 at 8:23
Hi,
I am making project on "motion detection using VS 6.0 MFC and open CV"
Please guide me that
Should i apply motion detection on HSV model. if so then why
and How can morphology help me in this project ? Should i apply this in my
project if so then why ?
Plese guide me
thanks
Original issue reported on code.google.com by [email protected]
on 10 Jun 2011 at 6:25
The ehci-0.7 windows binary samples seem to be more updated than the source
code given. Is it possible to release the source code for these binary samples?
What version of the product are you using? On what operating system?
ehci 0.7
Windows 7
Visual Studio 2010
Original issue reported on code.google.com by [email protected]
on 14 Nov 2010 at 2:53
What steps will reproduce the problem?
1. svn checkout http://ehci.googlecode.com/svn/trunk/ ehci-read-only
2.
3.
What is the expected output? What do you see instead?
The downloaded code does not include configure and friends.
What version of the product are you using? On what operating system?
svn trunk on Fedora 12 x86_64
Please provide any additional information below.
I have compiled 0.6 successfully, and wanted to look at the latest version.
Original issue reported on code.google.com by [email protected]
on 20 Feb 2010 at 9:05
Hello,
Ehci was compiled from the SVN using CMake without errors. The simple2d demo is
working fine but simple3d can not determine the coordinates.
Here is an example output :
Reading values from data/config.ini
USE_RANSAC: 1
RANSAC_SAMPLES: 6
RANSAC_DISTANCE_THRESHOLD: 0
RANSAC_ITERATIONS: 20
CAMERA_INDEX: 0
Opening movie file: NO.80608
Disabling
Head Coordinates X: +0.000 Y: +0.000 Z: +0.000 [initializing] (Press Ctrl+C
to finish)
Disabling
Error: no posit: number of points 1
The last 3 lines are repeated 30 times, then the output changes to :
Head Coordinates X: +0.000 Y: +0.000 Z: +0.000 (Press Ctrl+C to finish)
until the end of the execution.
I don't understand where it comes from.
Original issue reported on code.google.com by [email protected]
on 10 Feb 2011 at 4:01
I have used the background.tar code and done a RGB to YUV conversion
double Y=0.299 * cvGetAt(display,i,j).val[0] + 0.587 + 0.114;
double U=0.492 * cvGetAt(display,i,j).val[1] + 0.114 - 1.000;
double V=0.877 * cvGetAt(display,i,j).val[2] + 0.299 - 1.000;
if(( Y > Value1 ) &&
( U > Value2 ) &&
( V < Value3 )){
putpixel(person, j, i, 0x00FF00FF);
}
this keys out blue color perfectly ... but i dont seem to understand how ur
code works ? how does the code in background.tar know which color to remove ?
Thank You
Original issue reported on code.google.com by [email protected]
on 5 Dec 2010 at 11:04
What steps will reproduce the problem?
1. Windows Vista
2. Using the following software
MINGW 5.1.6
gcc-g++3.4.5
gcc-core-3.4.5
binutils-2.20.51-1-mingw32
gcc-build-3.4.5
mingw-runtime-3.14
w32api-3.14-mingw32-dev
glut-3.7.6
ehci-0.6
3. Eclipse with no include or library problems to my knowledge, at least there
is nothing in the problems list.
What is the expected output? What do you see instead?
Whatever the simple2d is supposed to do.
This is what I get from the console report
**** Build of configuration Debug for project GetBounds ****
**** Internal Builder is used for build ****
g++ -LC:\OpenCV2.1\lib -LC:\MinGW\ehci -oGetBounds.exe Headbounds.o -lcv210
-lml210 -lcvaux210 -lcxcore210 -lhighgui210
Headbounds.o:在函数‘main’ä¸ï¼š
C:/Users/Bluefrared/workspace/GetBounds/Debug/../Headbounds.cpp:23:对â
€˜ehciLoop(int, int)’未定义的引用
C:/Users/Bluefrared/workspace/GetBounds/Debug/../Headbounds.cpp:24:对â
€˜getHeadBounds(int*, int*, int*,
int*)’未定义的引用
collect2: ld returned 1 exit status
Build error occurred, build is stopped
Time consumed: 536 ms.
What version of the product are you using? On what operating system?
Windows Vista, EHCI 0.6
Please provide any additional information below.
I originally was working in Mac OS X snow leopard but was running into
significant OpenGL and GLUT issues so I tried in Windows Vista--the issues from
before cleared, but this new one appeared and I am at a loss as to what the
cause is because I am not an experienced programmer.
I did not follow the INSTALL file that came with ehci because I did not know
how to perform the instructions in the windows terminal. I simply extracted
the files into my MinGW folder in the folder ehci and included them, and did
not include any ehci library or direction path because I did not see any ehci
lib files.
OpenCV worked with some sample code such as a contour identification program.
I assume, because it is a rather large and complex OpenCV program, that OpenCV
is being correctly referenced and was properly installed.
Original issue reported on code.google.com by [email protected]
on 14 Jun 2010 at 10:31
I am using panda3D game engine and i have to combine opencv, augmented reality
and panda3d.
and the webcam output either plays opencv or panda and not both of them
together.
Original issue reported on code.google.com by [email protected]
on 23 Aug 2012 at 7:51
Hey there,
thanks for the nice software. I wonder if there's any possibility to use videos
for headtracking instead of live-recognition from camera.
Thanks for your help..
Original issue reported on code.google.com by [email protected]
on 4 Mar 2011 at 12:26
hello, i want to use ehci python bindings but i don't know how to compile
it on windows, i use windows XP and i have visual studio 2005, i found it
is difficult to set, because i knows little about makefile. please give
some instruction to compile on windows, thank you.
Original issue reported on code.google.com by [email protected]
on 20 Oct 2008 at 1:35
I tried to find contact information for the project, but this form is the
only thing I've found.
I just tried out your project, and I'm very excited to see it! after
experimenting with the face detection part, and your samples, I had the
following experiences / thoughs:
- if one moves his had too fast, because the web camera blurs the image,
face tracking is confused for the duration of the movement. after one stops
the head movement, it re-captures the face.
I wonder - one might be able to predict the vector of movement for the
uncertain period, and use that info in the meantime?
- if one moves his head out of the camera's view, basically the face
detection is gone forever. even if one moves back his head, the reference
points are gone
in such cases, auto re-initialization might help, basically entering a
state of actively looking for a face?
- looking the application working, basically I found that the number of
reference points is always decreasing - some are lost with time, but no new
ones are picked up.
maybe looking for new reference points while running would be of help?
- if one turns his head left or right (not facing the camera, but looking
to the side), head recognition is lost. maybe a prediction could be used in
these cases as well? or maybe adaptive tracking could be used - basically
re-calibrating the features for the same region, and sort of 'accepting the
fact' that the visuals of the face have changed?
basically I'm trying to think of improving the tracking nature of the solution.
(I'm doing all this with a Linux laptop and a Logitech webcam using the UVC
driver)
Original issue reported on code.google.com by [email protected]
on 18 Jan 2009 at 8:54
I have a problem with the cvGet2D in opencv.
I captured video from webcam, and it work.
There is a code part, and i see the video in the opencv window, but the s
Scalar always get 0 value. But there is an image in the "gray" iplimage.
What i missed in the code?
....
IplImage *frame;
IplImage *gray;
CvCapture* capture = cvCaptureFromCAM(2);
CvScalar s;
.....
frame = cvQueryFrame( capture );
gray = cvCreateImage( cvGetSize(frame), IPL_DEPTH_8U,1 );
cvCvtColor(frame, gray, CV_RGB2GRAY);
s=cvGet2D(frame,100,100);
....
cvShowImage( "Cam", gray );
Please help me somebody! Thank you!
Original issue reported on code.google.com by [email protected]
on 7 Dec 2009 at 2:30
Hello, I am getting similar errors when Im using Ehci. I am trying to use ehci
along with Kinect XBOX visual camera. I am running it on linux. I have openNI,
ehci and opencv installed. When I try to compile using the following line:
g++ main.cpp -I/usr/include/nite -I/usr/include/ni -I/usr/local/include
-I/usr/local/include -lOpenNI -lGL -lGLU -lglut -lehci `pkg-config --libs
--cflags opencv` -lEGL SceneDrawer.cpp HeadTracker.cpp opengles.cpp -o trial
I get the following errors:
HeadTracker.cpp: In function ‘void keyframeRelated()’:
HeadTracker.cpp:29:26: error: ‘isEhciTextureCreated’ was not declared in
this scope
HeadTracker.cpp:41:41: error: ‘getEhciGlTexture’ was not declared in this
scope
HeadTracker.cpp: In function ‘void drawHeadModel(IplImage*, float,
XnPoint3D)’:
HeadTracker.cpp:96:25: error: ‘setGeneratedImage’ was not declared in this
scope
HeadTracker.cpp:98:23: error: ‘getGeneratedImage’ was not declared in this
scope
HeadTracker.cpp:99:59: error: invalid conversion from ‘int’ to
‘IplImage*’
HeadTracker.cpp:99:59: error: initializing argument 3 of ‘int ehciLoop(int,
int, IplImage*)’
HeadTracker.cpp:102:59: error: invalid conversion from ‘int’ to
‘IplImage*’
HeadTracker.cpp:102:59: error: initializing argument 3 of ‘int
ehciLoop(int, int, IplImage*)’
Can you please help?
Thank you,
Charan
Original issue reported on code.google.com by [email protected]
on 8 Jul 2011 at 2:03
Hi Daniel,
I just wonder if you have any suggestion about automatic reinitialize when
needed. I try to make the program remember the initial frame, or initialize
when too few points are detected, but they did not work desirably. I notice you
are using the lkdemo.c example from opencv. When I swipe my hand over my face
the tracking points goes away with my hand. Is there a way to avoid it?
Original issue reported on code.google.com by [email protected]
on 8 Sep 2010 at 8:44
What steps will reproduce the problem?
1. When I build the echi-0.7 in visual studio 2010 I get an error
MSVCRTD.lib(crtexe.obj) : error LNK2019: unresolved external symbol _main
referenced in function ___tmainCRTStartup. Since I am completely new I tested
change the System to Console and Entry point to main etc. But nothing has
changed.
Thank you very much
Original issue reported on code.google.com by [email protected]
on 25 Jun 2013 at 12:43
i have installed ehci 0.6 on my linux ubuntu, 11.04.
I copied the source code of ehci.cpp and ehci.h and placed it in my code
folder. I get the following errors.
/tmp/ccvmS1gO.o: In function `DrawHead(unsigned int)':
SceneDrawer.cpp:(.text+0x15d2): undefined reference to `g_ImageGenerator'
/tmp/ccLok2ua.o: In function `keyframeRelated()':
HeadTracker.cpp:(.text+0x73): undefined reference to `isEhciTextureCreated()'
HeadTracker.cpp:(.text+0x11a): undefined reference to `getEhciGlTexture()'
/tmp/ccLok2ua.o: In function `drawHeadModel(_IplImage*, float, XnVector3D)':
HeadTracker.cpp:(.text+0x47d): undefined reference to
`setGeneratedImage(_IplImage*)'
HeadTracker.cpp:(.text+0x489): undefined reference to `getGeneratedImage()'
HeadTracker.cpp:(.text+0x4ab): undefined reference to `ehciLoop'
HeadTracker.cpp:(.text+0x4c8): undefined reference to `ehciLoop'
HeadTracker.cpp:(.text+0x4f8): undefined reference to `getGlPositMatrix'
collect2: ld returned 1 exit status
The command Im using to compile is
g++ main.cpp -I/usr/include/nite -I/usr/include/ni -I/usr/local/include
-lOpenNI -lGL -lGLU -lglut -lehci `pkg-config --libs --cflags opencv`
`pkg-config --libs --cflags ehci` -lEGL SceneDrawer.cpp HeadTracker.cpp
opengles.cpp -o abc
Do i need to place them in some specific folder? do I need to link any other
library..
Please help me out!! I am new to Linux and Im struggling!!
Original issue reported on code.google.com by [email protected]
on 12 Jul 2011 at 10:39
What steps will reproduce the problem?
1. hand movements(finger based)
2.
3.
What is the expected output? What do you see instead?
use finger as a mouse pointer in windows.and execute commands depending on
type of gesutre of hands and fingers.
What version of the product are you using? On what operating system?
ehci 6 on windows
Please provide any additional information below.
Original issue reported on code.google.com by [email protected]
on 8 Jan 2010 at 1:52
What steps will reproduce the problem?
1. Running Windows XP SP3
2. Running the precompiled binaries
What is the expected output? What do you see instead?
It just crashes, for every single program
What version of the product are you using? On what operating system?
EHCI 0.7 with OpenCV2.2 installed
Please provide any additional information below.
The webcamera is a logitech quickcam pro 9000 with the drivers installed. Not
sure what else would be of help to say.
Original issue reported on code.google.com by [email protected]
on 21 Feb 2011 at 11:06
What steps will reproduce the problem?
1. I want to test the issue interface
What is the expected output? What do you see instead?
Please use labels and text to provide additional information.
Original issue reported on code.google.com by [email protected]
on 27 Jul 2008 at 7:15
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.