感谢大佬的文章:基于深度相机 RealSense D435i 的 ORB SLAM 2 - 简书
之前一直使用Kinect进行尝试,但是一直点云都出不来
Ubuntu安装、重装_echo_gou的博客-CSDN博客
wget https://gitlab.com/libeigen/eigen/-/archive/3.2.10/eigen-3.2.10.tar.gz
tar -xvzf eigen-3.2.10.tar.gz
mkdir build
cd build
cmake ..
sudo make install
在 ORB SLAM 2 中那些很炫酷的实时建图画面是通过 Pangolin 实现的。
Pangolin 是一个轻量级的开发库,控制 OpenGL 的显示、交互等。
Pangolin 的核心依赖是 OpenGL 和 GLEW。
# OpenGL
sudo apt install libgl1-mesa-dev
# Glew
sudo apt install libglew-dev
# CMake
sudo apt install cmake
# python
sudo apt install libpython2.7-dev
sudo python -mpip install numpy pyopengl Pillow pybind11
# Wayland
sudo apt install pkg-config
sudo apt install libegl1-mesa-dev libwayland-dev libxkbcommon-dev wayland-protocols
# FFMPEG (For video decoding and image rescaling)
sudo apt install ffmpeg libavcodec-dev libavutil-dev libavformat-dev libswscale-dev libavdevice-dev
# DC1394 (For firewire input)
sudo apt install libdc1394-22-dev libraw1394-dev
# libjpeg, libpng, libtiff, libopenexr (For reading still-image sequences)
sudo apt install libjpeg-dev libpng-dev libtiff5-dev libopenexr-dev
# build Pangolin
git clone https://github.com/stevenlovegrove/Pangolin.git
cd Pangolin
mkdir build
cd build
cmake ..
cmake --build . # 注意最后那个点
测试:
cd ~/Pangolin/build/examples/HelloPangolin
./HelloPangolin
sudo apt install libpcl-dev
git clone https://github.com/gaoxiang12/ORBSLAM2_with_pointcloud_map.git
其中是一个压缩包和文件夹,我们只需要其中的子文件夹 ORB_SLAM2_modified。
把原本 ORB SLAM2 repo 中的 Vocabulary 文件夹和它里面的
ORBvoc.txt.tar.gz
文件拷贝过来,放到ORB_SLAM2_modified
路径下。把
~/ORB_SLAM2_modified/build
,~/ORB_SLAM2_modified/Thirdparty/DBoW2/build
和~/ORB_SLAM2_modified/Thirdparty/g2o/build
~/ORB_SLAM2_modified/Examples/ROS/ORB_SLAM2/build
这四个 build 文件夹删掉
在/opt/ros/melodic/setup.bash中的最后加入对应的路径,即:
export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:xxx/xxx/catkin_ws/src/ORB_SLAM2_modified/Examples/ROS
记得每次运行的时候要source一下/opt/ros/melodic/setup.bash,或者在.bashrc中加上上面的export,但是在多个orbslam代码的时候容易出错,所以需要时刻用下面的语句检查路径是否export成功。
查看自己的rospath:
echo $ROS_PACKAGE_PATH
输出里面需要有刚刚加入的ROS路径,即xxx/xxx/catkin_ws/src/ORB_SLAM2_modified/Examples/ROS,才可以在ROS下执行。
修改
~/ORB_SLAM2_modified/Examples/ROS/ORB_SLAM2/CMakeLists.txt
文件,加入pcl... find_package(Eigen3 3.1.0 REQUIRED) find_package(Pangolin REQUIRED) find_package( PCL 1.7 REQUIRED ) ####### 1 include_directories( ${PROJECT_SOURCE_DIR} ${PROJECT_SOURCE_DIR}/../../../ ${PROJECT_SOURCE_DIR}/../../../include ${Pangolin_INCLUDE_DIRS} ${PCL_INCLUDE_DIRS} ####### 2 ) add_definitions( ${PCL_DEFINITIONS} ) ####### 3 link_directories( ${PCL_LIBRARY_DIRS} ) ####### 4 set(LIBS ${OpenCV_LIBS} ${EIGEN3_LIBS} ${Pangolin_LIBRARIES} ${PROJECT_SOURCE_DIR}/../../../Thirdparty/DBoW2/lib/libDBoW2.so ${PROJECT_SOURCE_DIR}/../../../Thirdparty/g2o/lib/libg2o.so ${PROJECT_SOURCE_DIR}/../../../lib/libORB_SLAM2.so ${PCL_LIBRARIES} ####### 5 ) ...
这里因为作者除了这个代码还有其他的orbslam代码,所以ROS空间下的文件夹的名字要作区分,这里我将 ORB_SLAM2_modified/Examples/ROS/下的文件夹改成了ORB_SLAM2-2,同时需要在build_ros.sh中进行相应的路径修改。
然后运行
ORB_SLAM2_modified
中的./build.sh ./build_ros.sh
下载数据集:
rgbd_dataset_freiburg1_xyz
下面网址下载好以后拷贝associate.py至ORB_SLAM2主文件夹内。在associate.py所在的目录执行:(将RGB信息和深度信息链接到一起)
cvpr-ros-pkg - Revision 232: /trunk/rgbd_benchmark/rgbd_benchmark_tools/src/rgbd_benchmark_tools
python associate.py data/rgbd_dataset_freiburg1_xyz/rgb.txt data/rgbd_dataset_freiburg1_xyz/depth.txt > data/rgbd_dataset_freiburg1_xyz/associations.txt
运行:
./bin/rgbd_tum Vocabulary/ORBvoc.txt Examples/RGB-D/TUM1.yaml data/rgbd_dataset_freiburg1_xyz data/rgbd_dataset_freiburg1_xyz/associations.txt
修改为彩色: