-
Notifications
You must be signed in to change notification settings - Fork 299
Open
Description
Hello author,
Thanks for your sharing.
I notice in mainSift.cpp, we can find the two images transform by FindHomography() and ImproveHomography() functions. I have 2 trival questions to seek your confirmation.
-
- Does variable
homographyrepresents SE(2), namely, [R, t; 0, 1]= [H[0], H[1], H[2]; H[3], H[4], H[5]; H[6], H[7], H[8]]?
- Does variable
-
- If it is correct, the translation part t = [H[2], H[5] ] unit is pixel, or m? The rotaion part unit is rad.
Lines 72 to 78 in 5bc874a
| // Match Sift features and find a homography | |
| for (int i=0;i<1;i++) | |
| MatchSiftData(siftData1, siftData2); | |
| float homography[9]; | |
| int numMatches; | |
| FindHomography(siftData1, homography, &numMatches, 10000, 0.00f, 0.80f, 5.0); | |
| int numFit = ImproveHomography(siftData1, homography, 5, 0.00f, 0.80f, 3.0); |
Best regards
narutojxl
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels