在自己的聯想YOGA筆記本上成功編譯運行ORBSLAM2,並在TUM數據集上驗證運行效果,記錄安裝編譯過程。
1.安裝git、cmake
sudo apt-get install git(用於從github上clone項目到本地)
sudo apt-get cmake(用於編譯項目)
sudo apt-get update(用於更新軟件列表)
2.安裝Pangolin用於可視化和用戶界面
sudo apt-get install libglew-dev libpython2.7-dev (安裝依賴項)
git clone https://github.com/stevenlovegrove/Pangolin.git(將項目下載到本地)
3.編譯運行Pangolin:
cd Pangolin
mkdir build
cd build
cmake ..
make(注:如果只是筆記本安裝,CPU性能一般不建議使用make -j,本人親試使用make -j死機)
sudo make install
4.安裝Opencv用於處理圖像,ORBSLAM2支持Opencv 2和Opencv 3,本實驗使用的是Opencv 2.4.11
前往官網https://opencv.org/releases/page/4/下載Opencv 2.4.11 sources版本
首先安裝依賴項:
sudo apt-get install build-essential libgtk2.0-dev pkg-config vcodec-dev libavformat-dev libswscale-dev
選擇性安裝:
sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev
將下載的Opencv 2.4.11 解壓縮到本地並編譯安裝
cd ~/opencv 2.4.11
mkdir build
cd build
cmake -D CMAKE_BUILD_TYPE=Release –D CMAKE_INSTALL_PREFIX=/usr/local ..
make
sudo make install
5.安裝Eigen
sudo apt-get install libeigen3-dev
6.下載ORBSLAM2項目並且編譯:
git clone https://github.com/raulmur/ORB_SLAM2.git ORB_SLAM2
cd ORB_SLAM2
chmod +x build.sh
./build.sh
7.編譯成功以後,下載TUM、KITTI、EuRoC數據集,本實驗使用了TUM數據集,數據集下載地址:
./Examples/Monocular/mono_tum Vocabulary/ORBvoc.txt Examples/Monocular/TUMX.yaml PATH_TO_SEQUENCE_FOLDER
其中PATH_TO_SEQUENCE_FOLDER表示數據集存儲路徑,例如本實驗進行了單目和RGBD的實驗,現在了數據集fr2_desk
Monocular運行指令爲:
./Examples/Monocular/mono_tum Vocabulary/ORBvoc.txt Examples/Monocular/TUM1.yaml ./fr2_desk
運行結果截圖:
RGB-D運行指令爲:
./Examples/RGB-D/rgbd_tum Vocabulary/ORBvoc.txt Examples/RGB-D/TUM1.yaml ./fr2_desk ./Examples/RGB-D/associations/fr2_desk.txt