Skip to content

Commit

Permalink
paper link in README
Browse files Browse the repository at this point in the history
  • Loading branch information
themattinthehatt committed Jun 26, 2024
1 parent 395916d commit 493a75b
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 5 deletions.
6 changes: 2 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,14 +1,12 @@
# EKS
This repo contains code to run an Ensemble Kalman Smoother (EKS) for improving pose estimation outputs.

The EKS uses a Kalman filter to ensemble and smooth pose estimation outputs as a post-processing
The EKS uses a Kalman smoother to ensemble and smooth pose estimation outputs as a post-processing
step after multiple model predictions have been generated, resulting in a more robust output:

![](assets/crim13_singlecam.gif)

In this gif, there are five models (in red) on which EKS is run to generate the EKS
output (in green). As can be seen, the EKS output improves tracking by ensembling and smoothing the
individual model outputs, which can often diverge considerably for difficult frames.
For more details see [Biderman, Whiteway et al. 2024, Nature Methods](https://rdcu.be/dLP3z).

---

Expand Down
2 changes: 1 addition & 1 deletion eks/__init__.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
from eks import *

__version__ = '1.1.0'
__version__ = '2.0.0'

0 comments on commit 493a75b

Please sign in to comment.