A. 问题答案转自https://stackoverflow.com/questions/2764238/image-processing-what-are-occlusions，如有侵权请联系本人，本人会第一时间处理。
B. 图像遮蔽意味着，在图像处理中，由于探测器或者其它因素的影响，使得你想要看到的东西看不到了。关于图像遮蔽的定义需要根据你面临的具体问题进行分析。
举几个例子：
1、假设你正在开展目标追踪（人物追踪、车辆追踪等等），遮蔽问题将是你正在追踪的目标物体被另一个物体隐藏了或遮住了。例如两个相对行走的人，或者车辆穿过桥洞。这时的问题是当目标物体重新出现的时候你该怎么做？
2、If you are using a range camera, then occlusion is areas where you do not have any information. Some laser range cameras works by transmitting a laser beam onto the surface you are examining and then having a camera setup which identifies the point of impact of that laser in the resulting image. That gives the 3D-coordinates of that point. However, since the camera and laser is not necessarily aligned there can be points on the examined surface which the camera can see but the laser can not hit (occlusion). The problem here is more a matter of sensor setup.
3、3维成像中也会出现遮蔽现象，如果场景的部分信息只能被两个相机中的其中一个探测到，range data 不能从这些点收集到。
C. 图像配准时，遮蔽如何被发现了？
在“SimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithm ”论文中，作者给出了这样的方法：
“to detect occlusions, we compare the forward flow (uf, vf) from t to t + 1, and the backward flow (ub,vb) from t + 1 to t. Ideally, one should be the opposite of the other. One can either test the equality to get a binary detector or compute the difference ||(uf, vf) − (−ub,−vb)|| for a continuous estimator. When the computed difference is high, we mark the pixel as occluded between the frames.”