ORB-SLAM3 but for underwater environments.
Currently only implemented with monocular setups.
Implement depth readings with mono setupAdd CLAHE image preprocessing- Implement depth readings with mono-inertial setup
- Add underwater ORB vocabulary
- Add prerequisites used in installing ROS + standard packages
Uses the ROS implementation written by tien94. The implementation can be found here.
The instructions are copied from the same repo.
This package uses catkin build. Tested on Ubuntu 20.04.
sudo apt install libeigen3-dev
cd ~
git clone https://github.com/stevenlovegrove/Pangolin.git
cd Pangolin
mkdir build && cd build
cmake ..
make
sudo make install
Check the OpenCV version on your computer (required at least 3.0):
python3 -c "import cv2; print(cv2.__version__)"
On a freshly installed Ubuntu 20.04.4 LTS with desktop image, OpenCV 4.2.0 is already included. If a newer version is required (>= 3.0), follow installation instruction and change the corresponding OpenCV version in CMakeLists.txt
Technically this package is optional, but is used by default within the project. TODO: Make this optional.
Install hector-trajectory-server to visualize the real-time trajectory of the camera/imu. Note that this real-time trajectory might not be the same as the keyframes' trajectory.
sudo apt install ros-[DISTRO]-hector-trajectory-server
cd ~/catkin_ws/src
git clone https://github.com/einatomter/orb_u
cd ../
catkin build