GitHub/quartz
1
0
Fork 2
mirror of https://github.com/jackyzha0/quartz.git synced 2026-03-24 23:15:46 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

vault backup: 2023-04-03 13:39:22

Browse Source
This commit is contained in:
Jet Hughes 2023-04-03 13:39:22 +12:00
parent 0d020e9c4e
commit ed49bffb2e
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
content/notes/342-assignment-01.md
View File

@ -35,6 +35,7 @@ Procedure
_control for other factors: lighting, camera settings (exposure, iso, etc), resolution?__ _control for other factors: lighting, camera settings (exposure, iso, etc), resolution?__
RESULTS RESULTS
![](https://i.imgur.com/cxVO8up.png)
DISCUSSION DISCUSSION
@ -58,6 +59,7 @@ Procedure
5. Plot the time taken as a function of the RANSAC threshold. 5. Plot the time taken as a function of the RANSAC threshold.
RESULTS RESULTS
![](https://i.imgur.com/uAWQ2W3.png)
DISCUSSION DISCUSSION
@ -103,4 +105,13 @@ part 3 needs to be worded better... think about it like you are writing a recipe
- looks like error has very little correlation with the number of features using a flann based matcher - looks like error has very little correlation with the number of features using a flann based matcher
- re ran experiement with bf matcher and redid analysis still very little correlation - re ran experiement with bf matcher and redid analysis still very little correlation
- change experiment 1 to run BFMatcher and FlannBasedMatcher on same keypoints. - change experiment 1 to run BFMatcher and FlannBasedMatcher on same keypoints.
-
- wrote experiment 2 which went quite smoothly
- ran tests for ransac values {1.0, 2.0, 3.0}, very similar resutls
- used scatter plot to graph results
- ran tests for ransac values {0.1, 1, 3, 10, 100}, there was some variation which suggested an exponential set of values was a good idea
- used box plot to graph results
- ran tests for threshold values { 0.05, 0.1, 0.5, 1.0,3.0, 10.0, 50.0, 100.0 }.
- clear trends