KITTI数据集介绍
KITTI数据集：
7481 training images (and point clouds) and 7518 test images (and point clouds).
采集平台：
1惯性导航系统（GPS / IMU）：OXTS RT 3003
1台激光雷达：Velodyne HDL-64E
2台灰度相机，1.4百万像素：Point Grey Flea 2（FL2-14S3M-C）
2个彩色摄像头，1.4百万像素：Point Grey Flea 2（FL2-14S3C-C）
4个变焦镜头，4-8毫米：Edmund Optics NT59-917
文件结构：
├── data
│ ├── kitti
│ │ ├── ImageSets
│ │ ├── testing
│ │ │ ├── calib
│ │ │ ├── image_2
│ │ │ ├── velodyne
│ │ ├── training
│ │ │ ├── calib
│ │ │ ├── image_2
│ │ │ ├── label_2
│ │ │ ├── velodyne
ImageSets: xxx.txt，x为train，test，valid，数据集划分
calib：xx.txt，参数校准文件
image_2：图像数据
velodyne：点云数据
label_2：3D检测的标签文件
label_2标注格式：
Values Name Description
----------------------------------------------------------------------------
1 type Describes the type of object: 'Car', 'Van', 'Truck',
'Pedestrian', 'Person_sitting', 'Cyclist', 'Tram',
'Misc' or 'DontCare'
object类别
1 truncated Float from 0 (non-truncated) to 1 (truncated), where
truncated refers to the object leaving image boundaries
物体是否超出图像边界
1 occluded Integer (0,1,2,3) indicating occlusion state:
0 = fully visible, 1 = partly occluded
2 = largely occluded, 3 = unknown
遮挡程度
1 alpha Observation angle of object, ranging [-pi..pi]
4 bbox 2D bounding box of object in the image (0-based index):
contains left, top, right, bottom pixel coordinates
3 dimensions 3D object dimensions: height, width, length (in meters)
3 location 3D object location x,y,z in camera coordinates (in meters)
1 rotation_y Rotation ry around Y-axis in camera coordinates [-pi..pi]
1 score Only for results: Float, indicating confidence in
detection, needed for p/r curves, higher is better.
举例说明：Car 0.00 0 1.85 387.63 181.54 423.81 203.12 1.67 1.87 3.69 -16.53 2.39 58.49 1.57Car: 类别； 0.00：truncated；0：occluded；1.85：alpha；387.63 181.54 423.81 203.12： bbox；1.67 1.87 3.69：dimensions；-16.53 2.39 58.49： location；1.57 :rotation_y
NOTE: 1. DontCare类别指的是没有被标记的物体，例如：激光雷达无法扫描到的（距离太远的）物体。
2. alpha和rotation_y：一辆在相机坐标系中正向x轴的的汽车对应rotation_y=0，无论它位于X/Z平面(鸟瞰图)的哪个位置，而alpha值只有当该对象位于相机坐标系的Z轴时才为0。
calib参数校准文件的介绍：
P0: 7.215377000000e+02 0.000000000000e+00 6.095593000000e+02 0.000000000000e+00 0.000000000000e+00 7.215377000000e+02 1.728540000000e+02 0.000000000000e+00 0.000000000000e+00 0.000000000000e+00 1.000000000000e+00 0.000000000000e+00
P1: 7.215377000000e+02 0.000000000000e+00 6.095593000000e+02 -3.875744000000e+02 0.000000000000e+00 7.215377000000e+02 1.728540000000e+02 0.000000000000e+00 0.000000000000e+00 0.000000000000e+00 1.000000000000e+00 0.000000000000e+00
P2: 7.070493000000e+02 0.000000000000e+00 6.040814000000e+02 4.575831000000e+01 0.000000000000e+00 7.070493000000e+02 1.805066000000e+02 -3.454157000000e-01 0.000000000000e+00 0.000000000000e+00 1.000000000000e+00 4.981016000000e-03
P3: 7.215377000000e+02 0.000000000000e+00 6.095593000000e+02 -3.395242000000e+02 0.000000000000e+00 7.215377000000e+02 1.728540000000e+02 2.199936000000e+00 0.000000000000e+00 0.000000000000e+00 1.000000000000e+00 2.729905000000e-03
R0_rect: 9.999128000000e-01 1.009263000000e-02 -8.511932000000e-03 -1.012729000000e-02 9.999406000000e-01 -4.037671000000e-03 8.470675000000e-03 4.123522000000e-03 9.999556000000e-01
Tr_velo_to_cam: 6.927964000000e-03 -9.999722000000e-01 -2.757829000000e-03 -2.457729000000e-02 -1.162982000000e-03 2.749836000000e-03 -9.999955000000e-01 -6.127237000000e-02 9.999753000000e-01 6.931141000000e-03 -1.143899000000e-03 -3.321029000000e-01
Tr_imu_to_velo: 9.999976000000e-01 7.553071000000e-04 -2.035826000000e-03 -8.086759000000e-01 -7.854027000000e-04 9.998898000000e-01 -1.482298000000e-02 3.195559000000e-01 2.024406000000e-03 1.482454000000e-02 9.998881000000e-01 -7.997231000000e-01
解释：
P0，P1，P2，P3分别代表左边灰度相机，右边灰度相机，左边彩色相机，右边彩色相机。
后面的数字代表相机的内参矩阵，大小为3×4：
Prect (i)=(fu(i)0cui−fu(i)bxi0fv(i)cvi00010)P_{\text {rect }}^{(i)}=\left(\begin{array}{cccc} f_{u}^{(i)} & 0 & c_{u}^{i} & -f_{u}^{(i)} b_{x}^{i} \\ 0 & f_{v}^{(i)} & c_{v}^{i} & 0 \\ 0 & 0 & 1 & 0 \end{array}\right)Prect (i)=⎝⎜⎛fu(i)000fv(i)0cuicvi1−fu(i)bxi00⎠⎟⎞fu和fv指的是相机的焦距cu和cv是指主点偏移bi指的是第i个相机到0号摄像头的距离偏移（x方向）R0_rect指的是0号相机的修正矩阵Tr_velo_to_cam指的是velodyne到camera的矩阵 大小为3x4，包含了旋转矩阵 R 和 平移向量 tTr_imu_to_veloIMU到camera的矩阵 大小为3x4，包含了旋转矩阵 R 和 平移向量 t
例如：要将Velodyne坐标中的一个点投影到左边的彩色图像中：x = P2 * R0_rect * Tr_velo_to_cam * y
其中：Tr_velo_to_cam * x是将Velodyne坐标中的点x投影到编号为0的相机（参考相机）坐标系中R0_rect *Tr_velo_to_cam * x 是将Velodyne坐标中的点x投影到编号为0的相机（参考相机）坐标系中，再修正P2 * R0_rect *Tr_velo_to_cam * x是将Velodyne坐标中的点x投影到编号为0的相机（参考相机）坐标系中，再修正，而后投影到编号为2的相机（左边彩色相机）
投影到右边彩色图像：x = P3 * R0_rect * Tr_velo_to_cam * y
参考：
- kitti数据集介绍(采集平台+标定文件+标注文件解释) https://blog.csdn.net/QFJIZHI/article/details/103682310
- http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d
- kitti 数据集解析 http://www.javashuo.com/article/p-diursvxm-vc.html