-
-
Notifications
You must be signed in to change notification settings - Fork 45
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 2 frame lookback to determine fall instead of 1 #282
Comments
bhavikapanara
added a commit
to bhavikapanara/ambianic-edge
that referenced
this issue
Jan 27, 2021
github-actions bot
pushed a commit
that referenced
this issue
Feb 6, 2021
# [1.13.0](v1.12.14...v1.13.0) (2021-02-06) ### Bug Fixes * failing fall detection test; closes [#294](https://github.com/ambianic/ambianic-edge/issues/294) ([8b06fc0](8b06fc0)), closes [#298](#298) * fall detection issue [#282](#282) ([9dd818b](9dd818b)) * fall-detection bug [#294](https://github.com/ambianic/ambianic-edge/issues/294) ([d0814e1](d0814e1)), closes [#295](#295) ### Features * improved fall detection with 2 frame lookback instead of 1; closes [#282](#282) ([4abcfc3](4abcfc3)), closes [#289](#289)
🎉 This issue has been resolved in version 1.13.0 🎉 The release is available on GitHub release Your semantic-release bot 📦🚀 |
github-actions bot
pushed a commit
to ivelin/ambianic-edge
that referenced
this issue
Feb 6, 2021
# [1.10.0](v1.9.5...v1.10.0) (2021-02-06) ### Bug Fixes * clean up fall detections logging ([f086405](f086405)), closes [ambianic#287](https://github.com/ivelin/ambianic-edge/issues/287) * clean up fall detections logging ([88a4352](88a4352)) * failing fall detection test; closes [#294](https://github.com/ivelin/ambianic-edge/issues/294) ([8b06fc0](8b06fc0)), closes [ambianic#298](https://github.com/ivelin/ambianic-edge/issues/298) * fall detect runtime exception, closes [ambianic#285](https://github.com/ivelin/ambianic-edge/issues/285) ([41c9d4c](41c9d4c)), closes [ambianic#286](https://github.com/ivelin/ambianic-edge/issues/286) * fall detection issue [ambianic#282](https://github.com/ivelin/ambianic-edge/issues/282) ([9dd818b](9dd818b)) * fall-detection bug [#294](https://github.com/ivelin/ambianic-edge/issues/294) ([d0814e1](d0814e1)), closes [ambianic#295](https://github.com/ivelin/ambianic-edge/issues/295) * look for timeline-event log files in a flat dir not recursively ([e7873ec](e7873ec)) * merge remote-tracking branch 'upstream/master' ([8e313be](8e313be)) ### Features * improved fall detection with 2 frame lookback instead of 1; closes [ambianic#282](https://github.com/ivelin/ambianic-edge/issues/282) ([4abcfc3](4abcfc3)), closes [ambianic#289](https://github.com/ivelin/ambianic-edge/issues/289)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is your feature request related to a problem? Please describe.
Currently with look back 1 image frame with 1 second spacing between images to detect a fall.
This research study concludes that falls last anywhere between 600 and 800 ms. We currently expect 1 second gap between frames, which seems to be a reasonable choice that should be long enough to capture an image before and after a fall. The question remains open how to handle sequence of frames that may come in (before and middle) of a fall or (middle and after) a fall. In these cases the fall may be incomplete between the two comparison frames and we won't detect it with the current algorithm. Something to think about. May we look 2 frames back instead of 1, which ensures that a fall is certainly captured either in the (1,2), (2,3) or (1,3) pair of frames.
Describe the solution you'd like
Let's assume
image[t]
is the camera image input at time t.Currently with only 1 image lookback with 1 second spacing between images and a fall taking between 600-800ms, we have these possible cases:
[image[t-1], fall_start, fall_end, image[t]]
- > detection! (body vector angle between image[t] and image[t-1] should be close to 90', certainly over 60')[image[t-1], fall_start, image[t], fall_end]
- > no detection (body vector angle between image1 and image2 could be less than 60')[ fall_start, image[t-1], fall_end, image[t]]
- > no detection (body vector angle between image1 and image2 could be less than 60')What if we look not only 1 but 2 images back with 1 second spacing between each:
[image[t-2], image[t-1], fall_start, fall_end, image[t]]
- > detection! (body vector angle between image[t] and image[t-1] should be close to 90', certainly over 60')[image[t-2], fall_start, image[t-1], fall_end, image[t]]
- > detection (body vector angle between image[t-2] and image[t] should be close to 90', certainly over 60')It seems like with 3 frames (current time t, t-1 and t-2) lookback we should be able to capture any true fall as long as these assumptions hold true:
With the assumptions above, a true will be detected either between
[image[t-1], image[t]]
or between[image[t-2], image[t]
.Additional context
A different research study on ambient health monitoring discovered that only 2% of video frames are needed to accurately detect a person activity. 2% at 60fps is 1.2fps. This is consistent with the 600-800ms finding of the study above. Although Dr. Fei's study relies on RNNs to find which 2% are the ones required for the activity detection, it is still helpful to educate our simpler heuristic formula.
The text was updated successfully, but these errors were encountered: