Clean up script for pose estimation slides
This commit is contained in:
parent
b266f35529
commit
3dd11655a9
1 changed files with 6 additions and 8 deletions
|
@ -140,18 +140,16 @@
|
|||
<section data-background-image="https://docs.opencv.org/4.x/singlemarkersaxes.jpg">
|
||||
<h2 class="r-fit-text text-shadow">7. Pose Estimation</h2>
|
||||
<aside class="notes" data-markdown>
|
||||
- Now we know where there's a marker
|
||||
- Now we know _where_ there's a marker
|
||||
- Which way is it facing?
|
||||
- We know where the corners are
|
||||
- We can get the angle from that
|
||||
- Much like when we removed distortion
|
||||
- If we know the size of the marker, we can calculate its distance
|
||||
- Some calibration per camera model is required
|
||||
- Done once upfront
|
||||
- Out the end, we get rotation and translations from the camera
|
||||
- Find out translation and rotation
|
||||
- _complicated maths_
|
||||
- `solvePnP` in OpenCV (entertaining name)
|
||||
- "Perspective 'n' Point"
|
||||
- If we know the size of the marker, we can calculate its distance
|
||||
- Some calibration per camera model is required
|
||||
- Done once up-front
|
||||
- With simpler maths, can be turned into angles, distances etc
|
||||
</aside>
|
||||
</section>
|
||||
|
|
Loading…
Reference in a new issue