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

gen_flow.py #25

Open
Amitharitan25 opened this issue May 7, 2022 · 1 comment
Open

gen_flow.py #25

Amitharitan25 opened this issue May 7, 2022 · 1 comment

Comments

@Amitharitan25
Copy link

Hi there :)
I am trying to replicate your results and am currently on the data prepare steps.
In the Generate flow data from rgb and depth videos section you mention that I must run the docker image.
Is there a way for me to do it without that image? (I am running in an environment which is really strict about loading foreign images).
Thanks in advance,
Amit

@DavidMosoarca
Copy link

DavidMosoarca commented May 9, 2022

I recommend you to use this repo to extract the optical flow: https://github.com/open-mmlab/denseflow
But make sure to run the denseflow command with these flags:
denseflow <input_video> -a=tvl1 -b=20 -s=1 -st=jpg -nw=512 -nh=512 -o=<output_folder>
This code is able to make the extraction on a single video at the time. Although in the documentation it appears to be able to extract the flows of all the videos from a directory, that didn't work for me. Instead I made it extract the flow on each video at a time. Make sure to do a for loop on the directory in which you have the data stored and call the denswflow command for each one of them.

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

No branches or pull requests

2 participants