Name: iai_kinect2
Owner: pr2-debs
Description: Tools for using the Kinect One (Kinect v2) in ROS
Created: 2015-11-16 23:17:31.0
Updated: 2015-11-16 23:17:32.0
Pushed: 2015-11-13 14:00:15.0
Homepage: null
Size: 997
Language: C++
GitHub Committers
| User | Most Recent Commit | # Commits |
|---|
Other Committers
| User | Most Recent Commit | # Commits |
|---|
This is a collection of tools and libraries for a ROS Interface to the Kinect One (Kinect v2).
It contains:
First you should look at this FAQ and the FAQ from libfreenect2. Secondly, look at issue page from libfreenect2 and the issue page of iai_kinect2 for similar issues and solutions.
Right now it will not work with OpenCV 3.0. The default version in Ubuntu and ROS and therefore also for the iai_kinect2 package is OpenCV 2.4.x.
There are many reasons why kinect2_bridge might not working. The first thing to find out whether the problem is related to kinect2_bridge or libfreenect2. A good tool for testing is Protonect, it is a binary located in libfreenect2/build/bin/Protonect. It uses libfreenect directly with a minimal dependency on other libraries, so it is a good tool for the first tests.
Execute:
./Protonect gl to test OpenGL support../Protonect cl to test OpenCL support../Protonect cpu to test CPU support.Before running kinect2_bridge please make sure Protonect is working and showing color, depth and ir images. If some of them are black, than there is a problem not related to kinect2_bridge and you should look at the issues from the libfreenect2 GitHub page for help.
If one of them works, try out the one that worked with kinect2_bridge: rosrun kinect2_bridge kinect2_bridge depth_method:=<opengl|opencl|cpu>. You can also change the registration method with reg_method:=<cpu|opencl>.
If that is the case, you have to make sure that Protonect uses the same version of libfreenect2 as kinect2_bridge does. To do so, run make and sudo make install in the build folder again. And try out kinect2_bridge again.
ibfreenect2/build
& sudo make install
This is the normal behavior. 'kinect2_bridge' will only process data when clients are connected (ROS nodes listening to at least one of the topics). This saves CPU and GPU resources. As soon as you start the kinect_viewer or rostopic hz on one of the topics, processing should start.
rosdep will output errors on not being able to locate [kinect2_bridge] and [kinect2_registration]. That is fine because they are all part of the iai_kinect2 package and rosdep does not know these packages.
This indicates problems with the USB connection.
First of all, check the issue pages on GitHub for similar issues, as they might contain solutions for them. By default you will only see the open issues, but if you click on closed you will the the ones solved. There is also a search field which helps to find similar issues.
If you found no solution in the issues, feel free to open a new issue for your problem. Please describe your problem in detail and provide error messages and log output.
Install the ROS. Instructions for Ubuntu 14.04
Install libfreenect2:
Follow the instructions and enable C++11 by using cmake .. -DENABLE_CXX11=ON instead of cmake ..
Copy the udev rule file sudo cp libfreenect2/rules/90-kinect2.rules /etc/udev/rules.d/ and reconnect the sensor
Clone this repository into your catkin workspace, install the dependencies and build it:
/catkin_ws/src/
clone https://github.com/code-iai/iai_kinect2.git
ai_kinect2
ep install -r --from-paths .
/catkin_ws
in_make -DCMAKE_BUILD_TYPE="Release"
Note: rosdep will output errors on not being able to locate [kinect2_bridge] and [depth_registration]. That is fine because they are all part of the iai_kinect2 package and rosdep does not know these packages.
Connect your sensor and run kinect2_bridge:
un kinect2_bridge kinect2_bridge
Calibrate your sensor using the kinect2_calibration. Further details
Add the calibration files to the kinect2_bridge/data/<serialnumber> folder. Further details
Restart kinect2_bridge and view the results using rosrun kinect2_viewer kinect2_viewer kinect2 sd cloud.
Install the latest version of the AMD Catalyst drivers from https://support.amd.com and opencl-headers.
Install the latest version of the Nvidia drivers, for example nvidia-355 and nvidia-modprobe from ppa:graphics-drivers/ppa and opencl-headers.
You can either install a binary package from a PPA like ppa:pmjdebruijn/beignet-testing, or build beignet yourself. It's recommended to use the binary from the PPA.
Download and compile the newest Beignet release from source.
For Beignet the following depencies have to be installed manually:
Error “clang: not found”:
ln -s /usr/lib/llvm-3.5/bin/clang /usr/bin/clang
Known Beignet issue with Kernel 3.15/3.16 (see Beignet readme); fix is to disable cmd_parser:
su
0 > /sys/module/i915/parameters/enable_cmd_parser
To get 100% pass rate on the Beignet unit tests you may have to:
Execute directly on hw: ssh-session might not work
Execute as root
Note: Both previous points have to to with the fact that no x-server was installed. Apparently this will be fixed in a future release of Beignet.
~100 fps on the OpenCLDepthPacketProcessor (compared to < 5 fps on same hardware using CPU-based depth registration!)
nCLDepthPacketProcessor] avg. time: 10.1716ms -> ~98.3129Hz
boJpegRgbPacketProcessor] avg. time: 16.0787ms -> ~62.194Hz
If you used iai_kinect2 for your work, please cite it.
c{iai_kinect2,
thor = {Wiedemeyer, Thiemo},
tle = {{IAI Kinect2}},
ganization = {Institute for Artificial Intelligence},
dress = {University Bremen},
ar = {2014 -- 2015},
wpublished = {\url{https://github.com/code-iai/iai\_kinect2}},
te = {Accessed June 12, 2015}
The result should look something similar to this (may depend on the bibliography style used):
iedemeyer, ?IAI Kinect2,? https://github.com/code-iai/iai_kinect2,
itute for Artificial Intelligence, University Bremen, 2014 ? 2015,
ssed June 12, 2015.
Here are some screenshots from our toolkit:
