this is for holding javascript data
Volker Strobel edited subsection_Optical_Flow_label_sec__.tex
almost 8 years ago
Commit id: 3534d0883da80ef5e525b474985c5f72fc31718a
deletions | additions
diff --git a/subsection_Optical_Flow_label_sec__.tex b/subsection_Optical_Flow_label_sec__.tex
index d060c08..f325f6e 100644
--- a/subsection_Optical_Flow_label_sec__.tex
+++ b/subsection_Optical_Flow_label_sec__.tex
...
\label{sec:opticalflow}
Optical flow estimates the motion based on successive images: the shift of corresponding image keypoints in $x,y$-direction.
The approach is computationally rather complex. It is a relative localization method: without an initial reference point, it can only estimate the distance to an initial reference point but not its absolute position in space. The approach suffers from drift: since the distance travelled is based on comparing successive images, errors are accumulating over time. The approach alone does not have the the possibility to correct these errors.
\citet{} McGuire introduces a lightweight optical flow algorithm that is able to run on-board of an MAV. The algorithm uses compressed representations of images in the form of edge histogram to calculate the flow.