VINS-Fusion, VINS-Fisheye, OpenVINS, EnVIO, ROVIO, S-MSCKF, ORB-SLAM2, NVIDIA Elbrus application of different sets of cameras and imu on different board including desktop and Jetson boards
VINS-Fusion
, VINS-Fusion-GPU
, VINS-Fisheye
, OpenVINS
, EnVIO
, ROVIO
, S-MSCKF
, ORB-SLAM2
, DM-VIO
NVIDIA Isaac Elbrus
VINS-Fusion
for PX4 with Masking: hereworld
to map
Ceres-solver
, OpenCV
and Eigen
and performance of VINS is strongly proportional to CPU performance and some parameters
camera_models
and CUDA
acceleration
OpenCV 3.4.1
and Jetson TX2
(I guess, I failed on i9-10900k + RTX3080)Ubuntu 20.04
: CUDA
11.4, 11.5 (not 11.6), NVIDIA-graphic driver
from 470.103.01Jetpack
: 4.6.1 on Jetson Xavier AGX
, Jetson Xavier NX
Trouble shooting
for VINS-Fusion
$ wget -O eigen.zip https://gitlab.com/libeigen/eigen/-/archive/3.3.7/eigen-3.3.7.zip #check version
$ unzip eigen.zip
$ cd eigen-3.3.7
& mkdir build && cd build
$ cmake .. && sudo make install
$ git clone https://gitlab.com/libeigen/eigen.git
$ cd eigen
$ mkdir build && cd build
$ cmake .. && sudo make install
$ sudo apt-get install -y cmake libgoogle-glog-dev libatlas-base-dev libsuitesparse-dev
$ wget http://ceres-solver.org/ceres-solver-1.14.0.tar.gz
$ tar zxf ceres-solver-1.14.0.tar.gz
$ mkdir ceres-bin
$ mkdir solver && cd ceres-bin
$ cmake ../ceres-solver-1.14.0 -DEXPORT_BUILD_DIR=ON -DCMAKE_INSTALL_PREFIX="../solver" #good for build without being root privileged and at wanted directory
$ make -j8 # 8 : number of cores
$ make test
$ make install
$ sudo apt install gcc make
get the right version of CUDA(with graphic driver) .deb file at https://developer.nvidia.com/cuda-downloads
follow the installation instructions there!
# .run file can be used as nvidia graphic driver. But, .deb file is recommended to install tensorRT further.
# if want to install only graphic driver, get graphic driver install script at https://www.nvidia.com/Download/index.aspx?lang=en-us
# sudo ./NVIDIA_<graphic_driver_installer>.run --dkms
# --dkms option is recommended when you also install NVIDIA driver, to register it along with kernel
# otherwise, NVIDIA graphic driver will be gone after kernel upgrade via $ sudo apt upgrade
$ sudo reboot
$ gedit ~/.bashrc
# type and save
export PATH=<CUDA_PATH>/bin:$PATH #ex: /usr/local/cuda-11.1
export LD_LIBRARY_PATH=<CUDA_PATH>/lib64:$LD_LIBRARY_PATH #ex : /usr/local/cuda-11.1
$ . ~/.bashrc
# check if installed well
$ dpkg-query -W | grep cuda
# check installed cuda version
$ nvcc --version
# if nvcc --version does not print out CUDA,
$ gedit ~/.profile
# type below and save
export PATH=<CUDA_PATH>/bin:$PATH #ex: /usr/local/cuda-11.1
export LD_LIBRARY_PATH=<CUDA_PATH>/lib64:$LD_LIBRARY_PATH #ex : /usr/local/cuda-11.1
$ source ~/.profile
X server
is being used.
X server
and install.# if you are using lightdm
$ sudo service lightdm stop
# or if you are using gdm3
$ sudo service gdm3
# then press Ctrl+Alt+F3 -> login with your ID/password
$ sudo sh cuda_<version>_linux.run
Secure Boot
as below reference
Secure Boot
and then turn off X server
(as above) both.$ sudo tar zxf cudnn.tgz
$ sudo cp extracted_cuda/include/* <CUDA_PATH>/include/ #ex /usr/local/cuda-11.1/include/
$ sudo cp -P extracted_cuda/lib64/* <CUDA_PATH>/lib64/ #ex /usr/local/cuda-11.1/lib64/
$ sudo chmod a+r <CUDA_PATH>/lib64/libcudnn* #ex /usr/local/cuda-11.1/lib64/libcudnn*
OpenCV 4.X
opencv4.pc
file to /usr/local/lib/pkgconfig
or /usr/lib/aarch64-linux-gnu/pkgconfig
for jetson boards$ sudo apt-get purge libopencv* python-opencv
$ sudo apt-get update
$ sudo apt-get install -y build-essential pkg-config
$ sudo apt-get install -y cmake libavcodec-dev libavformat-dev libavutil-dev \
libglew-dev libgtk2.0-dev libgtk-3-dev libjpeg-dev libpng-dev libpostproc-dev \
libswscale-dev libtbb-dev libtiff5-dev libv4l-dev libxvidcore-dev \
libx264-dev qt5-default zlib1g-dev libgl1 libglvnd-dev pkg-config \
libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev mesa-utils #libeigen3-dev # recommend to build from source : http://eigen.tuxfamily.org/index.php?title=Main_Page
$ sudo apt-get install python2.7-dev python3-dev python-numpy python3-numpy
$ mkdir <opencv_source_directory> && cd <opencv_source_directory>
# check version
$ wget -O opencv.zip https://github.com/opencv/opencv/archive/3.4.1.zip # check version
$ unzip opencv.zip
$ cd <opencv_source_directory>/opencv
$ wget -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/3.4.1.zip # check version
$ unzip opencv_contrib.zip
$ mkdir build && cd build
# check your BIN version : http://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/
# 8.6 for RTX3080 7.2 for Xavier, 5.2 for GTX TITAN X, 6.1 for GTX TITAN X(pascal), 6.2 for TX2
# -D BUILD_opencv_cudacodec=OFF #for cuda10-opencv3.4
$ cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_C_COMPILER=gcc-6 \
-D CMAKE_CXX_COMPILER=g++-6 \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D OPENCV_GENERATE_PKGCONFIG=YES \
-D WITH_CUDA=ON \
-D OPENCV_DNN_CUDA=ON \
-D WITH_CUDNN=ON \
-D CUDA_ARCH_BIN=8.6 \
-D CUDA_ARCH_PTX=8.6 \
-D ENABLE_FAST_MATH=ON \
-D CUDA_FAST_MATH=ON \
-D WITH_CUBLAS=ON \
-D WITH_LIBV4L=ON \
-D WITH_GSTREAMER=ON \
-D WITH_GSTREAMER_0_10=OFF \
-D WITH_CUFFT=ON \
-D WITH_NVCUVID=ON \
-D WITH_QT=ON \
-D WITH_OPENGL=ON \
-D WITH_IPP=OFF \
-D WITH_V4L=ON \
-D WITH_1394=OFF \
-D WITH_GTK=ON \
-D WITH_EIGEN=ON \
-D WITH_FFMPEG=ON \
-D WITH_TBB=ON \
-D BUILD_opencv_cudacodec=OFF \
-D CUDA_NVCC_FLAGS="--expt-relaxed-constexpr" \
-D OPENCV_EXTRA_MODULES_PATH=../opencv_contrib-3.4.1/modules \
../
$ time make -j8 # 8 : numbers of core
$ sudo make install
$ sudo rm -r <opencv_source_directory> #optional for saving disk, but leave this folder to uninstall later, if you need.
...
...
if(CUDA_FOUND)
set(HAVE_CUDA 1)
ocv_list_filterout(CUDA_nppi_LIBRARY "nppicom") #this line is added
ocv_list_filterout(CUDA_npp_LIBRARY "nppicom") #this line is added
if(WITH_CUFFT)
set(HAVE_CUFFT 1)
endif()
...
...
No module name cv2
when import cv2
in Python3
## optional, I just leave default OpenCV from ROS2, since I can set proper PATHS for desired OpenCV versions
## If you cannot, just do below:
$ sudo apt-get purge libopencv*
## (But you will have to sudo apt install ros-foxy-desktop again, when you need other packages related to this)
$ sudo apt-get purge python-opencv python3-opencv
$ pip uninstall opencv-python
$ sudo apt-get update
$ sudo apt-get install -y build-essential pkg-config
$ sudo apt-get install -y cmake libavcodec-dev libavformat-dev libavutil-dev \
libglew-dev libgtk2.0-dev libgtk-3-dev libjpeg-dev libpng-dev libpostproc-dev \
libswscale-dev libtbb-dev libtiff5-dev libv4l-dev libxvidcore-dev \
libx264-dev qt5-default zlib1g-dev libgl1 libglvnd-dev pkg-config \
libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev mesa-utils #libeigen3-dev # recommend to build from source : http://eigen.tuxfamily.org/index.php?title=Main_Page
$ sudo apt-get install python3-dev python3-numpy
$ mkdir <opencv_source_directory> && cd <opencv_source_directory>
# check version
$ wget -O opencv.zip https://github.com/opencv/opencv/archive/4.5.5.zip # check version
$ unzip opencv.zip
$ cd <opencv_source_directory>/opencv
$ wget -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/4.5.5.zip # check version
$ unzip opencv_contrib.zip
$ mkdir build && cd build
# check your CUDA_ARCH_BIN and CUDA_ARCH_PTX version : http://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/
# 8.6 for RTX3080 7.2 for Xavier, 5.2 for GTX TITAN X, 6.1 for GTX TITAN X(pascal), 6.2 for TX2
# -D BUILD_opencv_cudacodec=OFF #for cuda10-opencv3.4
$ cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_C_COMPILER=gcc-9 \
-D CMAKE_CXX_COMPILER=g++-9 \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D OPENCV_GENERATE_PKGCONFIG=YES \
-D PYTHON_EXECUTABLE=/usr/bin/python3.8 \
-D PYTHON2_EXECUTABLE="" \
-D BUILD_opencv_python3=ON \
-D BUILD_opencv_python2=OFF \
-D PYTHON3_PACKAGES_PATH=/usr/local/lib/python3.8/dist-packages \
-D BUILD_NEW_PYTHON_SUPPORT=ON \
-D OPENCV_SKIP_PYTHON_LOADER=ON \
-D WITH_CUDA=ON \
-D OPENCV_DNN_CUDA=ON \
-D WITH_CUDNN=ON \
-D CUDA_ARCH_BIN=8.6 \
-D CUDA_ARCH_PTX=8.6 \
-D ENABLE_FAST_MATH=ON \
-D CUDA_FAST_MATH=ON \
-D WITH_CUBLAS=ON \
-D WITH_LIBV4L=ON \
-D WITH_GSTREAMER=ON \
-D WITH_GSTREAMER_0_10=OFF \
-D WITH_CUFFT=ON \
-D WITH_NVCUVID=ON \
-D WITH_QT=ON \
-D WITH_OPENGL=ON \
-D WITH_IPP=OFF \
-D WITH_V4L=ON \
-D WITH_1394=OFF \
-D WITH_GTK=ON \
-D WITH_EIGEN=ON \
-D WITH_FFMPEG=ON \
-D WITH_TBB=ON \
-D BUILD_opencv_cudacodec=OFF \
-D CUDA_NVCC_FLAGS="--expt-relaxed-constexpr" \
-D OPENCV_EXTRA_MODULES_PATH=../opencv_contrib-4.5.5/modules \
../
$ time make -j20 # 20 : numbers of core
$ sudo make install
$ sudo rm -r <opencv_source_directory> #optional for saving disk, but leave this folder to uninstall later, if you need.
$ cd ~/catkin_ws/src && git clone https://github.com/ros-perception/vision_opencv
# since ROS Noetic is added, we have to checkout to melodic tree
$ cd vision_opencv && git checkout origin/melodic
$ gedit vision_opencv/cv_bridge/CMakeLists.txt
#when error, try both lines
find_package(OpenCV 3 REQUIRED PATHS /usr/local/share/OpenCV NO_DEFAULT_PATH
#find_package(OpenCV 3 HINTS /usr/local/share/OpenCV NO_DEFAULT_PATH
COMPONENTS
opencv_core
opencv_imgproc
opencv_imgcodecs
CONFIG
)
include(/usr/local/share/OpenCV/OpenCVConfig.cmake) #under catkin_python_setup()
$ cd .. && catkin build cv_bridge
$ cd ~/catkin_ws/src && git clone https://github.com/ros-perception/vision_opencv
# since ROS Noetic is added, we have to checkout to melodic tree
$ cd vision_opencv && git checkout origin/melodic
$ gedit vision_opencv/cv_bridge/CMakeLists.txt
# add right after project()
set(CMAKE_CXX_STANDARD 11)
# edit find_package(OpenCV)
#find_package(OpenCV 4 REQUIRED PATHS /usr/local/share/opencv4 NO_DEFAULT_PATH
find_package(OpenCV 4 REQUIRED
COMPONENTS
opencv_core
opencv_imgproc
opencv_imgcodecs
CONFIG
)
include(/usr/local/lib/cmake/opencv4/OpenCVConfig.cmake)
cv_bridge/src/CMakeLists.txt
# line number 35, Edit 3 -> 4
if (OpenCV_VERSION_MAJOR VERSION_EQUAL 4)
cv_bridge/src/module_opencv3.cpp
// line number 110
// UMatData* allocate(int dims0, const int* sizes, int type, void* data, size_t* step, int flags, UMatUsageFlags usageFlags) const
UMatData* allocate(int dims0, const int* sizes, int type, void* data, size_t* step, AccessFlag flags, UMatUsageFlags usageFlags) const
// line number 140
// bool allocate(UMatData* u, int accessFlags, UMatUsageFlags usageFlags) const
bool allocate(UMatData* u, AccessFlag accessFlags, UMatUsageFlags usageFlags) const
$ cd .. && catkin build cv_bridge
$ cd ~/colcon_ws/src && git clone https://github.com/ros-perception/vision_opencv
$ cd vision_opencv
$ git checkout origin/ros2
$ cd ~/colcon_ws
$ colcon build --symlink-install --packages-select cv_bridge image_geometry --allow-overriding cv_bridge image_geometry
$ source install/setup.bash
$ sudo ./flash.sh -k kernel -C "usbcore.usbfs_memory_mb=1000" -k kernel-dtb jetson-xavier mmcblk0p1
$ gedit kalibr/aslam_offline_calibration/kalibr/python/kalibr_camera_calibration/MulticamGraph.py
#import Image
from PIL import Image
$ gedit kalibr/aslam_cv/aslam_cameras/include/aslam/cameras/implementation/PinholeProjection.hpp
# edit if sentence in line 781
# comment from line 782 to 795
f_guesses.push_back(2000.0) #initial guess of focal length!!!!
$ gedit kalibr/aslam_offline_calibration/kalibr/python/kalibr_calibrate_cameras
# comment from line 201 to 205
$ cd ~/catkin_ws/src
$ git clone https://github.com/HKUST-Aerial-Robotics/VINS-Fusion #CPU
or
$ git clone https://github.com/pjrambo/VINS-Fusion-gpu #GPU
$ cd .. && catkin build camera_models # camera models first
$ catkin build
Before build VINS-Fusion, process below could be required.
GPU
version, Edit CMakeLists.txt
for loop_fusion
and vins_estimator
$ cd ~/catkin_ws/src/VINS-Fusion-gpu/loop_fusion && gedit CMakeLists.txt
or
$ cd ~/catkin_ws/src/VINS-Fusion-gpu/vins_estimator && gedit CMakeLists.txt
##For loop_fusion : line 19
#find_package(OpenCV)
include(/usr/local/share/OpenCV/OpenCVConfig.cmake)
##For vins_estimator : line 20
#find_package(OpenCV REQUIRED)
include(/usr/local/share/OpenCV/OpenCVConfig.cmake)
cv
codes are changed from original repo.$ cd ~/catkin_ws/src
$ git clone https://github.com/engcang/vins-application #Only CPU version yet
$ cd vins-application
$ mv vins_estimator ..
$ mv camera_models ..
$ cd ..
$ rm -r vins-application
$ cd ..
$ catkin build
$ echo "export MALLOC_CHECK_=0" >> ~/.bashrc
$ source ~/.bashrc
OpenCV 3.4.1
and Jetson TX2
(I guess yet, I failed on i9-10900k + RTX3080)libSGM
and install with OpenCV
option as below:$ git clone https://github.com/fixstars/libSGM
$ cd libSGM
$ git submodule update --init
check and edit CMakeLists.txt
$ gedit CMakeLists.txt
Edit
BUILD_OPENCV_WRAPPER=ON and ENABLE_TESTS=ON
$ mkdir build && cd build
$ cmake .. -DBUILD_OPENCV_WRAPPER=ON -DENABLE_TESTS=ON
$ make -j6
$ sudo make install
do test
$ cd libSGM/build/test && ./sgm-test
VINS-Fisheye
and install$ cd ~/catkin_ws/src
$ git clone https://github.com/xuhao1/VINS-Fisheye
$ cd ..
build camera_models first
$ catkin build camera_models
$ gedit src/VINS-Fisheye/vins_estimator/CMakeLists.txt
edit as below:
set(ENABLE_BACKWARD false)
or
$ sudo apt install libdw-dev
$ catkin build
$ cd ~/catkin_ws/src
$ git clone https://github.com/rpng/open_vins/
$ cd ..
$ catkin build
EnVIO
and install: refer official git
$ cd ~/catkin_ws/src
$ git clone https://github.com/lastflowers/envio.git
$ cd ..
$ catkin_make
or, if you want to use it with catkin build,
then
$ gedit src/envio/CMakeLists.txt
comment two lines, line 4 and 5
#set(CMAKE_CXX_COMPILER "/usr/bin/g++-5")
#set(CMAKE_C_COMPILER "/usr/bin/gcc-5")
$ catkin build
$ sudo apt-get install libsuitesparse-dev
$ cd ~/catkin_ws/src && https://github.com/KumarRobotics/msckf_vio
$ cd ~/catkin_ws && catkin build msckf_vio -DCMAKE_BUILD_TYPE=Release
ROVIO
receives input image as gray scale image
- convert the RGB image as this file
Kalibr
results:$ rosrun kalibr kalibr_rovio_config --cam <cam-chain.yaml filename>
Camera1
and Camera2
into Camera0
and Camera1
in .info
fileVelocity Updates
block in .info
file$ cd ~/catkin_ws/src && git clone https://github.com/ANYbotics/kindr
$ cd .. && catkin build -j8
ROVIO
$ cd ~/catkin_ws/src && git clone https://github.com/ethz-asl/rovio
$ cd rovio && git submodule update --init --recursive
$ cd ..
$ catkin build rovio --cmake-args -DCMAKE_BUILD_TYPE=Release
# With with opengl scene (optional)
$ sudo apt-get install freeglut3-dev libglew-dev
$ catkin build rovio --cmake-args -DCMAKE_BUILD_TYPE=Release -DMAKE_SCENE=ON
$ cd ~/catkin_ws/src && git clone https://github.com/appliedAI-Initiative/orb_slam_2_ros
$ cd .. && rosdep install --from-paths src --ignore-src -r -y
$ catkin build
$ sudo apt-get install cmake libsuitesparse-dev libeigen3-dev libboost-all-dev libyaml-cpp-dev libtbb-dev libgl1-mesa-dev libglew-dev pkg-config libegl1-mesa-dev libwayland-dev libxkbcommon-dev wayland-protocols -y
$ cd ~/your_workspace
$ git clone https://github.com/borglab/gtsam.git
$ cd gtsam
$ git checkout 4.2a6 # not strictly necessary but this is the version tested with.
$ mkdir build && cd build
$ cmake -DGTSAM_POSE3_EXPMAP=ON -DGTSAM_ROT3_EXPMAP=ON -DGTSAM_USE_SYSTEM_EIGEN=ON -DGTSAM_BUILD_WITH_MARCH_NATIVE=OFF ..
$ make -j
$ sudo make install
$ cd ~/your_workspace
$ git clone https://github.com/stevenlovegrove/Pangolin.git
$ cd Pangolin
$ git checkout v0.6
$ mkdir build && cd build
$ cmake ..
$ cmake --build .
$ sudo make install
DM-VIO
and DM-VIO-ROS
$ cd ~/your_workspace
$ git clone https://github.com/lukasvst/dm-vio.git
$ cd dm-vio
$ mkdir build && cd build
$ cmake ..
$ make -j10
$ echo "export DMVIO_BUILD=`pwd`" >> ~/.bashrc && . ~/.bashrc
$ cd ~/your_workspace/src
$ git clone https://github.com/lukasvst/dm-vio-ros.git
$ cd ~/your_workspace
$ catkin build
$ . devel/setup.bash
$ sudo ldconfig
KAIST-VIO-Dataset
, refer this config files
$ rosrun dmvio_ros node calib=camera_kaistvio.txt imuCalib=camchain_kaistvio.yaml settingsFile=setting_kaistvio.yaml mode=3 nogui=0 preset=1 quiet=1 useimu=1
CUDA
: 11.4-11.5 (11.6 cannot install VPI 1.1.11)
NVIDIA Graphic driver
>= 470.103.01NVIDIA VPI
1.1.11 (Only this version) - install with this files after CUDA installationRaw stereo image
+ camera info topics
+ (Important!) /tf_static
(including base_frame (e.g., camera_link) to left and right camera frame)$ sudo apt install git-lfs
$ cd ~/colcon_ws/src
$ git clone https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_visual_slam &&
git clone https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_image_pipeline &&
git clone https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_common
$ cd ..
$ rosdep install -i -r --from-paths src --rosdistro foxy -y
$ colcon build --symlink-install && source install/setup.bash
# Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
...
import launch
from launch_ros.actions import ComposableNodeContainer, Node
from launch_ros.descriptions import ComposableNode
...
remappings=[('stereo_camera/left/image', '/camera/infra1/image_rect_raw'),
('stereo_camera/left/camera_info', '/camera/infra1/camera_info'),
('stereo_camera/right/image', '/camera/infra2/image_rect_raw'),
('stereo_camera/right/camera_info', '/camera/infra2/camera_info')]
)
...
bag
file, then use or refer this launch file
/tf_static
cannot be recorded in bag
file, static_transform_publisher
should be added in the launch file as these lines
VINS-Mono
on FlightGoggles
: youtube, with CPU youtube
ROVIO
on FlightGoggles
: youtube
ORB-SLAM2
on FlightGoggles
: youtube
VINS with Loop fusion
vs VINS
on FlightGoggles
: youtube
VINS-Mono
vs ROVIO
: youtube
VINS-Mono
vs ROVIO
vs ORB-SLAM2
: youtube
VINS-Fusion
(Stereo) vs S-MSCKF
on FlightGoggles
: youtube
VINS-Fusion
(Stereo) based autonomous flight and 3D mapping using RGB-D camera: youtube
Hand-held - VINS-Mono
with pointgrey cam, myAHRS+ imu on Jetson Xavier AGX: youtube, moved faster : youtube
Hand-held - ROVIO
with Intel D435i on Jetson Xavier AGX: youtube
Hand-held - ORB-SLAM2
with Intel D435i on Jetson Xavier AGX: youtube
Hand-held - VINS(GPU version)
with pointgrey, myAHRS at Intel i7-8700k, TITAN RTX: youtube
Hand-held - VINS(GPU version, Stereo)
with Intel D435i, on Xavier AGX, max CPU clocked: youtube and youtube2 : screen
Hand-held - VINS-Fusion (Stereo)
with Intel D435i and Pixhawk4 mini fused with T265 camera: here
Hand-held - VINS-Fusion (stereo)
with Intel D435i and Pixhawk4 mini on 1km long underground tunnel: here
Hand-held - VINS-Fusion GPU version
test using T265: here
Hand-held - VINS-Fusion (stereo)
test using OAK-D: here
Hand-held - VINS-Fusion (stereo)
test using OAK-D PRO: here
Real-Drone - VINS-Fusion
with Intel D435i and Pixahwk4 mini on Real Hexarotor: here
Real-Drone - VINS-Fusion
with Intel D435i and Pixahwk4 mini on Real Quadrotor: here
OpenVINS
on KAIST VIO dataset: result youtube
EnVIO
vs VINS-Fusion
on KAIST VIO dataset: result youtube
DM-VIO
vs VINS-Mono
on KAIST VIO dataset: result youtube
NVIDIA Isaac Elbrus
in real-world: result youtube
Qualcomm RB5
vs Khadas VIM3 Pro
- Video