5,710
edits
Changes
→Visual SFM Workflow
Use Visual Structure From Motion (SFM) software to ascertain camera parameters and locations
*http://ccwu.me/vsfm/
==imagesImages==
point cloud and cameras:
*generating contact sheet / composite of all frames in single texture
==homographiesHomographies==cvFindHomograpyfrom mpalign.py (using SIFT features, cv2.findHomography):
<pre>
Closest Image for frame0020.jpg: frame0000.jpg 0.151351351351
[ -2.70420863e-05 2.11710811e-05 1.00000000e+00]]
</pre>
trying to create H (homography) for pespective transform based on VisSFM camera positions. ??
=References=