ORB-SLAM3 双目惯性联合下的TUM-VI yaml数据集的解析

前言

这个yaml数据集包括了左右目相机和IMU数据（需要进行标定）、ORB参数以及可视化器的参数三部分。

解读：

1.左右目相机和IMU参数：包括了左右目相机的内参、去畸变的系数、右目到左目的变换矩阵、左右目图像的像素重叠区域、相机分辨率、相机帧率、图像的形式（RGB、BGR、灰色）、深度阈值、IMU坐标系到左目相机坐标系的变换矩阵、IMU的噪声数据、IMU的频率。

2.ORB参数：每张图应提取的特征点参数、金字塔的缩放因子、金字塔层数、FAST算法提取角点的阈值。 

3.可视化参数 

%YAML:1.0

#--------------------------------------------------------------------------------------------
# Camera Parameters. Adjust them!
#--------------------------------------------------------------------------------------------
File.version: "1.0"

Camera.type: "KannalaBrandt8"

# Left Camera calibration and distortion parameters (OpenCV)
//左侧相机的内参
//水平垂直方向的焦距
Camera1.fx: 190.97847715128717
Camera1.fy: 190.9733070521226
//相机的主点坐标
//光心和主点不是一回事儿。
Camera1.cx: 254.93170605935475
Camera1.cy: 256.8974428996504

# Kannala-Brandt distortion parameters
//相机的去畸变参数
Camera1.k1: 0.0034823894022493434
Camera1.k2: 0.0007150348452162257
Camera1.k3: -0.0020532361418706202
Camera1.k4: 0.00020293673591811182

# Right Camera calibration and distortion parameters (OpenCV)
//右侧相机的参数
Camera2.fx: 190.44236969414825
Camera2.fy: 190.4344384721956
Camera2.cx: 252.59949716835982
Camera2.cy: 254.91723064636983

# Kannala-Brandt distortion parameters
Camera2.k1: 0.0034003170790442797
Camera2.k2: 0.001766278153469831
Camera2.k3: -0.00266312569781606
Camera2.k4: 0.0003299517423931039
    
# Transformation matrix from right camera to left camera
//双目相机的右侧相加到左侧相机的变换矩阵
Stereo.T_c1_c2: !!opencv-matrix
  rows: 4
  cols: 4
  dt: f
  data: [ 0.999999445773493,   0.000791687752817,   0.000694034010224,   0.101063427414194,
            -0.000823363992158,   0.998899461915674,   0.046895490788700,   0.001946204678584,
            -0.000656143613644,  -0.046896036240590,   0.998899560146304,   0.001015350132563,
          0.0,0.0,0.0,1.0]

# Lapping area between images
//图像的重叠区域
Camera1.overlappingBegin: 0
Camera1.overlappingEnd: 511

Camera2.overlappingBegin: 0
Camera2.overlappingEnd: 511

# Camera resolution
//相机的分辨率512*512
Camera.width: 512
Camera.height: 512

# Camera frames per second
//相机的帧率
Camera.fps: 20

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

# Close/Far threshold. Baseline times.
Stereo.ThDepth: 40.0//深度阈值：近距离物体和远距离物体的深度值的界限

# Transformation from body-frame (imu) to left camera
//IMU坐标系到左目相机坐标系的变换矩阵
IMU.T_b_c1: !!opencv-matrix
   rows: 4
   cols: 4
   dt: f//矩阵中的数据类型为浮点型。
   data: [-0.9995250378696743, 0.0075019185074052044, -0.02989013031643309, 0.045574835649698026, 
          0.029615343885863205, -0.03439736061393144, -0.998969345370175, -0.071161801837997044,
         -0.008522328211654736, -0.9993800792498829, 0.03415885127385616, -0.044681254117144367,
          0.0, 0.0, 0.0, 1.0]

# IMU noise (Use those from VINS-mono)
//噪声数据
IMU.NoiseGyro: 0.00016 # 0.004 (VINS) # 0.00016 (TUM) # 0.00016    # rad/s^0.5 
IMU.NoiseAcc: 0.0028 # 0.04 (VINS) # 0.0028 (TUM) # 0.0028     # m/s^1.5
IMU.GyroWalk: 0.000022 # 0.000022 (VINS and TUM) rad/s^1.5
IMU.AccWalk: 0.00086 # 0.0004 (VINS) # 0.00086 # 0.00086    # m/s^2.5
//频率：一秒采集200次数据
IMU.Frequency: 200.0

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

# ORB Extractor: Number of features per image
ORBextractor.nFeatures: 1000 # Tested with 1250
//每张图片要提取的特征点，可根据图片的复杂度作适当的调整。

# ORB Extractor: Scale factor between levels in the scale pyramid 	
ORBextractor.scaleFactor: 1.2//金字塔层之间的缩放因子。

# ORB Extractor: Number of levels in the scale pyramid	
ORBextractor.nLevels: 8//金字塔的层数。

# 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
//FAST算法提取角点的阈值。
//先采用高阈值提取，当特征点不足时则采用更低的阈值。
ORBextractor.iniThFAST: 20
ORBextractor.minThFAST: 7

#--------------------------------------------------------------------------------------------
# Viewer Parameters
#--------------------------------------------------------------------------------------------
Viewer.KeyFrameSize: 0.05
Viewer.KeyFrameLineWidth: 1.0
Viewer.GraphLineWidth: 0.9
Viewer.PointSize: 2.0
Viewer.CameraSize: 0.08
Viewer.CameraLineWidth: 3.0
Viewer.ViewpointX: 0.0
Viewer.ViewpointY: -0.7
Viewer.ViewpointZ: -3.5
Viewer.ViewpointF: 500.0

结束语

以上就是我学习到的内容，如果对您有帮助请多多支持我，如果哪里有问题欢迎大家在评论区积极讨论，我看到会及时回复。