-
-
Notifications
You must be signed in to change notification settings - Fork 17
Issues: ambianic/fall-detection
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Jupyter Notebook on Fall Detection data
enhancement
New feature or request
#25
opened Sep 10, 2021 by
ivelin
Switch to MoveNet as a default ML model
enhancement
New feature or request
#24
opened Sep 10, 2021 by
ivelin
Publish pose-detection as a standalone repo and pypi package
enhancement
New feature or request
#21
opened Aug 17, 2021 by
ivelin
Align our PoseDetector API with the TFJS version from Google
enhancement
New feature or request
#20
opened Aug 17, 2021 by
ivelin
User labeling and model training of fall detection model
enhancement
New feature or request
#18
opened Jul 3, 2021 by
ivelin
Image pre-processing for improved PoseNet inference results
enhancement
New feature or request
#11
opened Feb 7, 2021 by
ivelin
feat: reduce false positives when there are multiple persons in view
enhancement
New feature or request
#10
opened Feb 6, 2021 by
ivelin
Optimize CPU usage - rotate image only if there is a standing up pose in the frame buffer
enhancement
New feature or request
#7
opened Feb 4, 2021 by
ivelin
False positive - people bending over intentionally, not falling
#2
opened Jan 31, 2021 by
mchapman67
Implement more test cases based on public and user contributed video and image data of elderly falls
#4
opened Jan 20, 2021 by
ivelin
move fall detection library out of ambianic-edge into independent pypi package
#1
opened Dec 31, 2020 by
ivelin
Upgrade pose detection from PoseNet MobileNetV1 to MoveNet, PoseNet 2.0 ResNet50, or BlazePose
enhancement
New feature or request
#5
opened Dec 18, 2020 by
ivelin
ProTip!
Find all open issues with in progress development work with linked:pr.