ORB-SLAM3 yaml文件介绍

水深无声 2022-12-20 12:53 139阅读 0赞

# 一个yaml文件例子 #

%YAML:1.0
    
    #--------------------------------------------------------------------------------------------
    # Camera Parameters. Adjust them!
    #--------------------------------------------------------------------------------------------
    Camera.type: "PinHole"
    
    # Camera calibration and distortion parameters (OpenCV)
    
    Camera.fx: 718.856
    Camera.fy: 718.856
    Camera.cx: 607.1928
    Camera.cy: 185.2157
    
    Camera.k1: -0.3691481 # D_02: -3.691481e-01 1.968681e-01 1.353473e-03 5.677587e-04 -6.770705e-02
    Camera.k2: 0.1968681
    Camera.p1: 0.0005677587
    Camera.p2: -0.06770705
    Camera.k3: 0.001353473
    
    Camera.width: 1241
    Camera.height: 376
    
    # Camera frames per second 
    Camera.fps: 10.0
    
    # IR projector baseline times fx (aprox.)
    Camera.bf: 40.0  #待确定
    
    # Color order of the images (0: BGR, 1: RGB. It is ignored if images are grayscale)
    Camera.RGB: 1
    
    # Close/Far threshold. Baseline times.
    ThDepth: 80.0   #TUM1.YAML=40,待确定
    
    # Deptmap values factor 
    DepthMapFactor: 2560
    #--------------------------------------------------------------------------------------------
    # ORB Parameters
    #--------------------------------------------------------------------------------------------
    
    # ORB Extractor: Number of features per image
    ORBextractor.nFeatures: 2000
    
    # 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: -10
    Viewer.ViewpointZ: -0.1
    Viewer.ViewpointF: 2000

## Camera.bf ##

中的b指基线baseline（单位：米），f是焦距fx（x轴和y轴差距不大），bf=b\*f，和ThDepth一起决定了深度点的范围：bf \* ThDepth / fx即大致为b \* ThDepth。 基线在双目视觉中出现的比较多，如ORB-SLAM中的双目示例中的EuRoC.yaml中的bf为47.9，ThDepth为35，fx为435.2，则有效深度为47.9\*35/435.3=3.85米；KITTI.yaml中的bf为387.57，ThDepth为40，fx为721.54，则有效深度为387.57\*40/721.54=21.5米。这里的xtion的IR基线（其实也可以不这么叫）bf为40，ThDepth为50，fx为558.34，则有效深度为3.58米（官方为3.5米）。

ORB-SLAM3中使用:

//Tracking::Tracking(System *pSys, ...构造函数中:
    if(sensor==System::STEREO || sensor==System::RGBD || sensor==System::IMU_STEREO)
        {
            mThDepth = mbf*(float)fSettings["ThDepth"]/fx;
            cout << endl << "Depth Threshold (Close/Far Points): " << mThDepth << endl;
        }

## DepthMapFactor ##

DepthMapFactor: 1000.0这个很好理解，depth深度图的值为真实3d点深度\*1000. 例如depth值为2683，则真是世界尺度的这点的深度为2.683米。 这个值是可以人为转换的（如opencv中的convert函数，可以设置缩放因子），如TUM中的深度图的DepthMapFactor为5000，就代表深度图中的5000个单位为1米。