very poor tracking performance
Closed this issue · 5 comments
I tried tracking simple objects I was holding in my hand using the macbook pro's isight camera, and performance seemed to be very poor. Objects would be completely lost within a few seconds even if I don't move or change the orientation much (including when orientation changes are enabled). Perhaps I'm using it wrong or only a certain type of use case is supported?
That sounds puzzling as the tracker, from my experience is the best tracker I have tested. Maybe lighting or other issues may be responsible. Have had situations when using it for FPV, the tracking cut out instanting because, I believe from loss of frame because of the radio transmission noise. Try other cameras.
if your computer is not powerful, it maybe lost a lots of video frame. That
may affect the tracking performance
On Fri, Jan 29, 2016 at 1:56 PM, cinspired notifications@github.com wrote:
That sounds puzzling as the tracker, from my experience is the best
tracker I have tested. Maybe lighting or other issues may be responsible.
Have had situations when using it for FPV, the tracking cut out instanting
because, I believe from loss of frame because of the radio transmission
noise. Try other cameras.—
Reply to this email directly or view it on GitHub
#36 (comment).
Zheng Lu
Jilin University.
2699 Qianjin St
Changchun,Jilin,R.P.China,130012
Email: polaris.varlin@gmail.com
ph: +86-15643110346
The information contained in this e-mail, including any attachment (s), is
intended solely for use by the named addressee (s). If you are not the
intended recipient, or a person designated as responsible for delivering
such messages to the intended recipient, you are not authorized to
disclose, copy, distribute or retain this message, in whole or in part,
without written authorization from Jilin University. This e-mail may
contain proprietary, confidential or privileged information. If you have
received this message in error, please notify the sender immediately. This
notice is included in all e-mail messages leaving Jilin university. Thank
you for your cooperation.
My computer is a 2014 15" MacBook Pro with an Intel Core i7, so I don't believe the issue is my computer being slow.
I made sure to pull the latest version and compile in release mode. I don't know what changed but things seem substantially better.
Which OpenCV and compiler version are you using?
On Monday, January 11, 2016, Andrew Hundt notifications@github.com wrote:
I tried tracking simple objects I was holding in my hand using the macbook
pro's isight camera, and performance seemed to be very poor. Objects would
be completely lost within a few seconds even if I don't move or change the
orientation much (including when orientation changes are enabled). Perhaps
I'm using it wrong or only a certain type of use case is supported?—
Reply to this email directly or view it on GitHub
#36.
homebrew/science/opencv: stable 2.4.12 (bottled), HEAD
Open source computer vision library
http://opencv.org/
/usr/local/Cellar/opencv/2.4.12_2 (231 files, 35.8M) *
Built from source with: --with-qt --with-tbb --without-numpy
From: https://github.com/Homebrew/homebrew-science/blob/master/opencv.rb
==> Dependencies
Build: cmake ✘, pkg-config ✔
Required: jpeg ✔, libpng ✘, libtiff ✔
Recommended: eigen ✔, openexr ✔, homebrew/python/numpy ✔
Optional: gstreamer ✔, jasper ✘, libdc1394 ✔, openni ✔, qt ✔, tbb ✔, vtk ✔, ffmpeg ✔
± c++ --version
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.2.0
Thread model: posix
Note this still isn't 100% ideal performance, just acceptable.