ORB_SLAM安裝

源文件目錄https://github.com/raulmur/ORB_SLAM2

安裝orb_slam首先需要安裝依賴庫

1. 安裝Pangolin

• sudo apt-get install libglew-dev
• sudo apt-get install cmake
• sudo apt-get install libpython2.7-dev
• sudo apt-get install ffmpeg libavcodec-dev libavutil-dev libavformat-dev libswscale-dev
• git clone https://github.com/stevenlovegrove/Pangolin.git

cd Pangolin
mkdir build
cd build
cmake ..
make -j

2. 安裝OpenCV
   ros中自帶

3. 安裝Eigen3
   后續(xù)安裝

4. 安裝BLAS and LAPACK

sudo apt-get install libblas-dev
sudo apt-get install liblapack-dev

5. 安裝DBoW2 和 g2o
   包含在orb_slam的第三方庫中乾戏，后續(xù)一起安裝

安裝orb_slam

1. 下載軟件包

cd catkin_ws/src
git clone https://github.com/raulmur/ORB_SLAM2.git

2. 編譯第三方庫

cd ORB_SLAM2
chmod +x build.sh
./build.sh

ORB_SLAM測試

安裝USB_CAM 驅(qū)動(dòng)

cd catkin_ws/src
git clone https://github.com/bosch-ros-pkg/usb_cam.git
cd ../
catkin_make

運(yùn)行usb_cam 輸出topic為/usb_cam/image_raw

roslaunch usb_cam usb_cam-test.launch

攝像頭標(biāo)定

參考ROS單目標(biāo)定wiki

1. 準(zhǔn)備標(biāo)準(zhǔn)黑白棋格盤
   • 下載黑白棋盤

• 打印棋盤（可以A4紙打印，粘貼在硬紙板上）
• 測量棋盤單元邊長（A4紙的在0.025 m 左右）

2. 安裝測試程序（ros）

$ rosdep install camera_calibration
$ rosmake camera_calibration

3. 啟動(dòng)usb_cam程序

sudo apt-get install ros-indigo-usb-cam (如果沒有安裝usb_cam)
roslaunch usb_cam usb-cam-test.launch

4. 啟動(dòng)camera_calibration

rosrun camera_calibration cameracalibrator.py --size 8x6 --square 0.025 image:=/usb_cam/image_raw camera:=/usb_cam
其中 size是黑白格的橫縱點(diǎn)數(shù)夺荒，square是黑白格邊長崎坊，image是圖像節(jié)點(diǎn)名稱灌旧，camera是相機(jī)名稱。

5. 實(shí)際標(biāo)定

   
   
   標(biāo)定界面
   
   

   標(biāo)定界面出現(xiàn)后，按照x（左右）瘟滨、y（上下）坎藐、size（前后）为牍、skew（傾斜）等方式移動(dòng)棋盤哼绑，知道x,y,size,skew的進(jìn)度條都變成綠色位置，此時(shí)可以按下CALIBRATE按鈕碉咆，等一段時(shí)間就可以完成標(biāo)定抖韩。

   
   
   標(biāo)定就緒
   
   標(biāo)定完成后，點(diǎn)擊COMMIT按鈕疫铜，最終的標(biāo)定結(jié)果會(huì)在終端出現(xiàn)茂浮，在usb_cam的終端上會(huì)有yaml文件保存地址。
   
   標(biāo)定結(jié)果
6. 結(jié)果轉(zhuǎn)換
   轉(zhuǎn)換結(jié)果如下所示：
   image_width: 640
   image_height: 480
   camera_name: usb_cam
   camera_matrix:
   rows: 3
   cols: 3
   data: [914.5937398762499, 0, 313.2995046937195, 0, 906.4439566149695, 299.4151672923101, 0, 0, 1]
   distortion_model: plumb_bob
   distortion_coefficients:
   rows: 1
   cols: 5
   data: [0.09838481350767736, 0.1181389276375996, 0.01127830741538815, 0.006633733461628469, 0]
   rectification_matrix:
   rows: 3
   cols: 3
   data: [1, 0, 0, 0, 1, 0, 0, 0, 1]
   projection_matrix:
   rows: 3
   cols: 4
   data: [933.7507934570312, 0, 315.2716618576233, 0, 0, 926.8785400390625, 300.85249210037, 0, 0, 0, 1, 0]

而在orb_slam中的格式如下壳咕，需要將上面的
camera_matrix：

camera_matrix

distortion_coefficients：

distortion_coefficients

src/ORB_SLAM2/Examples/Monocular/mycam.yaml

    %YAML:1.0
    #--------------------------------------------------------------------------------------------
    # Camera Parameters. Adjust them!
    #--------------------------------------------------------------------------------------------

    # Camera calibration and distortion parameters (OpenCV) 
    Camera.fx: 914.5937398762499
    Camera.fy: 906.4439566149695
    Camera.cx: 313.2995046937195
    Camera.cy: 299.4151672923101

    Camera.k1: 0.09838481350767736
    Camera.k2: 0.1181389276375996
    Camera.p1: 0.01127830741538815
    Camera.p2: 0.006633733461628469
    Camera.k3: 0

    Camera.width: 640
    Camera.height: 480

    # Camera frames per second 
    Camera.fps: 30.0

    # Color order of the images (0: BGR, 1: RGB. It is ignored if images are grayscale)
    Camera.RGB: 1

    #--------------------------------------------------------------------------------------------
    # ORB Parameters
    #--------------------------------------------------------------------------------------------

    # ORB Extractor: Number of features per image
    ORBextractor.nFeatures: 1000

    # ORB Extractor: Scale factor between levels in the scale pyramid   
    ORBextractor.scaleFactor: 1.2

    # ORB Extractor: Number of levels in the scale pyramid  
    ORBextractor.nLevels: 8

    # ORB Extractor: Fast threshold
    # Image is divided in a grid. At each cell FAST are extracted imposing a minimum response.
    # Firstly we impose iniThFAST. If no corners are detected we impose a lower value minThFAST
    # You can lower these values if your images have low contrast           
    ORBextractor.iniThFAST: 20
    ORBextractor.minThFAST: 7

    #--------------------------------------------------------------------------------------------
    # Viewer Parameters
    #--------------------------------------------------------------------------------------------
    Viewer.KeyFrameSize: 0.05
    Viewer.KeyFrameLineWidth: 1
    Viewer.GraphLineWidth: 0.9
    Viewer.PointSize:2
    Viewer.CameraSize: 0.08
    Viewer.CameraLineWidth: 3
    Viewer.ViewpointX: 0
    Viewer.ViewpointY: -0.7
    Viewer.ViewpointZ: -1.8
    Viewer.ViewpointF: 500

運(yùn)行demo

1. 環(huán)境配置

export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:PATH/ORB_SLAM2/Examples/ROS

2. 編譯

cd src/ORB_SLAM2/Examples/ROS/ORB_SLAM2
mkdir build
cd build
cmake .. -DROS_BUILD_TYPE=Release
make -j

3. 啟動(dòng)demo

rosrun ORB_SLAM2 Mono /home/your_path/catkin_ws/src/ORB_SLAM2/Vocabulary/ORBvoc.txt /home/your_path/catkin_ws/src/ORB_SLAM2/Examples/Monocular/mycam.yaml

其中有兩個(gè)參數(shù)谓厘，第一個(gè)參數(shù)為加載的字典幌羞，第二個(gè)參數(shù)為相機(jī)參數(shù)，更改為自身的相機(jī)參數(shù)即可竟稳。