1. 程式人生 > >SLAM中“camera類中座標轉換"方法解讀

SLAM中“camera類中座標轉換"方法解讀

/*
p_p : position_pexil  ;  p_c:position_camera  ; p_w : position_world ; T_c_w : 歐式矩陣(包含R,t資訊) from camera to world 

cpp功能:實現關於pexil,camera,world的任意兩者間的座標轉換。

pixel2world的實現是能過兩步實現的: pixel -> camera ,進而 camera -> world ,反之, world2pixel 也一樣。
*/
#include "myslam/camera.h"

namespace myslam
{

Camera:
:Camera() { } Vector3d Camera::world2camera ( const Vector3d& p_w, const SE3& T_c_w ) { return T_c_w*p_w; // T_c_w即歐式矩陣,包含R,t的資訊,公式為 T * P_world } Vector3d Camera::camera2world ( const Vector3d& p_c, const SE3& T_c_w ) { return T_c_w.inverse() *p_c; } //為什麼p_c用兩個值來索引,它不是一維向量嗎?
//the convenience Vector3f is a (column) vector of 3 floats. It is defined as follows by Eigen: Matrix<float, 3, 1> Vector3f; //We also offer convenience typedefs for row-vectors, for example: Matrix<int, 1, 2> RowVector2i; //so Vector3d is a column vector ,they have 3 rows; Vector2d Camera:
:camera2pixel ( const Vector3d& p_c ) { return Vector2d ( //參照書本5.5的公式 fx_ * p_c ( 0,0 ) / p_c ( 2,0 ) + cx_, fy_ * p_c ( 1,0 ) / p_c ( 2,0 ) + cy_ ); } Vector3d Camera::pixel2camera ( const Vector2d& p_p, double depth ) { return Vector3d ( //參照書本5.5的公式,depth 即為公式的Z。 ( p_p ( 0,0 )-cx_ ) *depth/fx_, ( p_p ( 1,0 )-cy_ ) *depth/fy_, depth ); } Vector2d Camera::world2pixel ( const Vector3d& p_w, const SE3& T_c_w ) { return camera2pixel ( world2camera ( p_w, T_c_w ) ); } Vector3d Camera::pixel2world ( const Vector2d& p_p, const SE3& T_c_w, double depth ) { return camera2world ( pixel2camera ( p_p, depth ), T_c_w ); } }