Skip to content

Conversation

@noctrog
Copy link
Collaborator

@noctrog noctrog commented Dec 21, 2021

This implementation works with the formulation described in exercise 9.
In my laptop it takes a couple of seconds to solve the BA problem for 4
poses.

I didn't write any tests because this code gives roughly the same results as seen in the exercise9.pdf. But I am planning on testing it when we are done debugging the current pipeline.

noctrog and others added 4 commits December 22, 2021 00:43
This implementation works with the formulation described in exercise 9.
In my laptop it takes a couple of seconds to solve the BA problem for 4
poses.
Plots in (more or less) same format as example GUI from project PDF. imshow() will probably need to be replaced with something else once we know how we'd like to integrate the keypoints to the current frame; additionally, the top view will need a new data structure, since it should only be holding the points from the previous 20 frames, and Im not sure how to do that efficiently off the top of my head
Big ol commit which adds images with point annotation, two sets of points for the top view plot (since it needs vehicle position and 3D landmark location), titles (mostly, see TODO in createFigure.m), and rebuids testPlotting.m to test all this
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants