tailieunhanh - O’Reilly Learning OpenCV phần 8

Trong video, một đối tượng nền trước (đó là, trên thực tế, một bàn tay) đi qua mặt trước của máy ảnh. Đối tượng tiền cảnh là gần như không tươi sáng như bầu trời và cây trong nền. Độ sáng của bàn tay cũng được hiển thị trong hình. | the imager of our camera is an example of planar homography. It is possible to express this mapping in terms of matrix multiplication if we use homogeneous coordinates to express both the viewed point Q and the point q on the imager to which Q is mapped. If we define Q x v i 1 T T v a 1 T then wecan express the action of the homography simply as q sHQ Here we have introduced the param He wh ich is an arbitrary scale factor intended to make explicit that the homography is defined only up to that factor . It is conventionally factoredou if ve and we ll otic withlOat conventioT here. With a little geometry and some matrix aIgebra we can solve for this transformation matrix. The most important observation is that H has two parts the physical transfor-mctioe which so r tially locvQee the objeet plana we are viewine and or e fc ention which ifhroducae tlae camera mVaiwsicn Figora 11 -in. Figure 11-11. View of a planar object as described by homography a mapping from the object plane to the image plane that simultaneously comprehends the relative locations of those two planes as well as the camera projection matrix Calibration I 385 The physical transformation part is the sum of the effects of some rotation R and some translation t that relate the plane we are viewing to the image plane. Because we are working in homogeneous coordinates we can combine these within a single matrix as follows W a t Then the a c t ion o f theeame ra mat rixM wliicti we already knowhow toeepress in p ro-jectivecoordinates as multieliod Wy SVQ -hit wields q sMWQ where M 0 r 0 w It would seem that we ate done. However .ttums out that 1 n our .merest Is not the coordinate Q which is defined for all of space but rather a coordinate Q which is defined only on the plane we are lo kn ị od Ibis al tows for a s light simplification. Without loss of generality we can choose to define the object plane so that z 0. We do this because if we also break up the rotation matrix into three