-
Notifications
You must be signed in to change notification settings - Fork 67
Troubleshooting tips: KB
[KB] Rough notes for errors that have been run into
//I am going to clean this all up
- reinstall the Kinect:
- go inside your ROS workspace (i.e. usually /home/$USER/workspace/ros/catkin/src)
git clone https://github.com/OpenPTrack/libfreenect2.git;
cd libfreenect2 git checkout iai_kinect2
cd depends/
- sudo apt-get install -y git cmake cmake-curses-gui libXmu-dev libXi-dev libgl1-mesa-dev dos2unix xorg-dev libglu1-mesa-dev libtool automake libudev-dev libgtk2.0-dev pkg-config libjpeg-turbo8-dev libturbojpeg libglewmx-dev --reinstall
./install_ubuntu.sh sudo ln -s /usr/lib/x86_64-linux-gnu/libturbojpeg.so.0.0.0 /usr/lib/x86_64-linux-gnu/libturbojpeg.so
cd ../examples/protonect/ cmake . make -j4 sudo make install
< go inside your ROS workspace (i.e. usually /home/$USER/workspace/ros/catkin/src) >
git clone https://github.com/OpenPTrack/iai_kinect2.git cd iai_kinect2
git checkout development
echo '# ATTR{product}=="Kinect2"
SUBSYSTEM=="usb", ATTR{idVendor}=="045e", ATTR{idProduct}=="02c4", MODE="0666" SUBSYSTEM=="usb", ATTR{idVendor}=="045e", ATTR{idProduct}=="02d8", MODE="0666" SUBSYSTEM=="usb", ATTR{idVendor}=="045e", ATTR{idProduct}=="02d9", MODE="0666"' > ~/90-kinect2.rules sudo mv ~/90-kinect2.rules /etc/udev/rules.d/90-kinect2.rules
< go inside your ROS workspace before src (i.e. usually /home/$USER/workspace/ros/catkin) > catkin_make < reboot > < disconnect and reconnect the Kienct v2 to the USB3.0 port of the computer > < wait a couple of seconds >
sudo apt-get install -y ocl-icd-opencl-dev --reinstall
- try resetting power strip
- Likely to be due to the Nvidia driver crashing
- sudo service light dm restart
- sudo service ntp restart
//the following are when we try to run detection
- background subtraction enabled - this is ok
- Unplug USB and replug to that respective machine
Error message: No valid frame. Move the camera to a better position. OR [ERROR'[longnumber.longnumber]:CV_bridge exception: Unrecognized image encoding
- not enough points on the floor //make sure to add the notes about the issue that came up from the Gnocchi email thread
- System Requirements
- Supported Hardware
- Initial Network Configuration
- Example Hardware List for UCLA Setup
- Making the Checkerboard
- Time Synchronization
- Pre-Tracking Configuration
- Camera Network Configuration
- Single Camera
- Setting Parameters
- Multi-Sensor Person Tracking
- HOG vs YOLO Detectors
- World Coordinate Settings
- Single Camera
- Pose Initialization
- Multi Sensor Pose Annotation
- Pose Best Practices
- Setting Parameters
- Single Camera
- Setting Parameters
- Multi Sensor Object Tracking
- YOLO Custom Training & Testing
- Yolo Trainer
- Single Camera
- Setting Parameters
- Multi Sensor Face Detection and Recognition
- Face Detection and Recognition Data Format
How to receive tracking data in: