deletions | additions       diff --git a/subsection_Homography_Determination_Keypoint_Matching__.tex b/subsection_Homography_Determination_Keypoint_Matching__.tex  index a1698cc..55e24e8 100644  --- a/subsection_Homography_Determination_Keypoint_Matching__.tex  +++ b/subsection_Homography_Determination_Keypoint_Matching__.tex 
...
\label{sec:keypointmatching}  A standard approach for estimating camera pose is detecting and  describing keypoints of the current view and a reference image, image~\cite{se2002global},  using algorithms such as \textsc{Sift}~\cite{lowe1999object}, followed by finding a homography between both keypoint sets. A  keypoint is a salient image location---described by a feature vector---that is invariant to different  viewing angles and scaling . scaling.  By finding a homography, that is a perspective transformation between the keypoints of the current view and a reference image, the current view can be located in the reference image. %The $3 \times 3$  %homography matrix ($H$) is based on at least four keypoint matches