Kinect V2相机的定义 [英] Definitions of Kinect V2 camera
问题描述
我想知道以下定义,因为我不太清楚: -
1。 Matrix4 - 相机的X,Y,Z位置?
2。 WorldToCamera转换
3。 WorldToVolume转换。
4。相机的内在和外在参数。
这大部分与现实世界中相机的TRS(平移,旋转,缩放)矩阵有关。 0,0,0始终是相机启动时的第一个帧方向。可以假设身份,但如果您移动传感器,您需要
知道它移动到哪里。 WorldToCamera是对摄像机的翻译,世界到体积是摄像机如何与Fusion的世界体积重建对齐。
摄像机的内在属性由CoordinateMapper api提供。
I want to know the following definitions as it is not very clear to me:-
1. Matrix4 - Is it X,Y,Z position of camera ?
2. WorldToCamera Transform
3. WorldToVolume transform.
4. Intrinsic and extrinsic parameters of camera.
Most of this has to do with the TRS(translation, rotation, scale) matrix of the camera in real world space. 0,0,0 is always the first frame orientation of the camera when starting. Can be assumed identity but if you move the sensor you need to know where it moved to. WorldToCamera, is the translation to the camera, world to volume is how the camera aligns to the reconstruction of Fusion's world volume.
Intrinsic properties of the camera are provided from the CoordinateMapper api.
这篇关于Kinect V2相机的定义的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!