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

Person / face detection with tensorflow lite #437

Open
wtip opened this issue Jan 7, 2021 · 3 comments
Open

Person / face detection with tensorflow lite #437

wtip opened this issue Jan 7, 2021 · 3 comments

Comments

@wtip
Copy link

wtip commented Jan 7, 2021

Adding person or face detection with something like tensorflow lite instead of simple motion detection would be a useful feature.

@lukeswitz
Copy link
Collaborator

I like this idea; motion detection needs an overhaul. Granular options, I can get behind that for sure.

Pinging @archie94 for input on which camera framework/API to move forward with (first or third party). Thanks all

@archie94
Copy link
Collaborator

archie94 commented Jan 9, 2021

Yes this can be a valuable add on.

We can use Framework's Camera2 apis or any wrapper over the same (Like CameraX). I believe the current camera library we have in the project can also work. Since analysis of frame are costly we can maybe analysis only certain frames at regular intervals.

We need to go with on device TFLite models like Pose estimation model or similar face detection models.

@wtip
Copy link
Author

wtip commented Jan 9, 2021

An app called tinyCam pro https://play.google.com/store/apps/details?id=com.alexvas.dvr.pro has an option to only do object detection on frames that contain motion. This helps reduce the CPU usage for environments where there isn't constant movement.

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

3 participants