Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change Optical Flow computation #2

Open
4 tasks
TanguyJeanneau opened this issue Sep 24, 2019 · 0 comments
Open
4 tasks

Change Optical Flow computation #2

TanguyJeanneau opened this issue Sep 24, 2019 · 0 comments
Assignees
Labels
improvement Implementation of non-existing, needed features

Comments

@TanguyJeanneau
Copy link
Owner

TanguyJeanneau commented Sep 24, 2019

[Before trying anything, train 1 model with current state to be able to compare]
[After this comes issue #1]
So far, optical flow is calculated thanks to OpenCV's function cv2.calcOpticalFlowFarneback. In the original paper, DeepFlow is used. This difference might be the source of the poor quality of the Temporal Loss.

  • Clone DeepFlow github repo
  • Add it to the requirements
  • Test DeepFlow on some images and compare it with the current solution
  • If the results are coherent and better than the current, switch it.

/!\ For better training performances, It might be necessary to compute all dataset's optical flow once and store it (changing the current dataset organisation). This will allow us not to compute optical flow on each example of the training set.

@TanguyJeanneau TanguyJeanneau added the improvement Implementation of non-existing, needed features label Sep 24, 2019
TanguyJeanneau added a commit that referenced this issue Sep 24, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
improvement Implementation of non-existing, needed features
Projects
None yet
Development

No branches or pull requests

2 participants