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

Implement more test cases based on public and user contributed video and image data of elderly falls #4

Open
ivelin opened this issue Jan 20, 2021 · 3 comments
Assignees

Comments

@ivelin
Copy link

ivelin commented Jan 20, 2021

Is your feature request related to a problem? Please describe.
We continuously receive images from users with examples of false positives or missed positives. This is expected iterative process of improvement.

Describe the solution you'd like
We should add to the testsuite examples from publicly available elderly fall videos in order to improve the performance of our fall detection algorithm.

Here is one such dataset.

Additional context
Attached are additional images reported from ambianic users with false positives.
Screen Shot 2021-01-12 at 2 10 10 PM
Screen Shot 2021-01-12 at 2 10 23 PM
Screen Shot 2021-01-19 at 4 22 48 PM

@ivelin ivelin changed the title Implement more test cases based on public video and image data of elderly falls Implement more test cases based on public and user contributed video and image data of elderly falls Jan 26, 2021
@ivelin
Copy link
Author

ivelin commented Jan 26, 2021

@bhavikapanara here is again the link to the data samples I extracted for our test suite. These are sequences of image falls of elderly from public video sources.

@ivelin ivelin transferred this issue from ambianic/ambianic-edge Feb 1, 2021
@ivelin
Copy link
Author

ivelin commented Feb 25, 2021

@bhavikapanara more user contributed test images. These show the challenges that the MobileNet PoseNet model has detecting people poses from a camera mounted on a ceiling corner looking down towards the door and floor.

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