Closed bhavikapanara closed 3 years ago
Check out this pull request on
See visual diffs & provide feedback on Jupyter Notebooks.
Powered by ReviewNB
Merging #22 (db3d7c2) into main (b84a92d) will not change coverage. The diff coverage is
n/a
.
@@ Coverage Diff @@
## main #22 +/- ##
=======================================
Coverage 92.29% 92.29%
=======================================
Files 14 14
Lines 1272 1272
=======================================
Hits 1174 1174
Misses 98 98
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:13Z ----------------------------------------------------------------
Thank you!
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:14Z ----------------------------------------------------------------
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:15Z ----------------------------------------------------------------
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:15Z ----------------------------------------------------------------
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:16Z ----------------------------------------------------------------
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:16Z ----------------------------------------------------------------
View / edit / reply to this conversation on ReviewNB
ivelin commented on 2021-09-02T16:27:15Z
bhavikapanara This sequence also misses the frames with the person actually fallen on the floor. Can you check why that is the case and add them to the detection samples.
Actually, I am skipping few frames because it is complicated to show all frames
I think it's reasonable to take snapshots once a second (1fps). That is how we implement it in production relying on the fact that falls take between 600-800ms. this should be sufficient to capture all before and after fall scenes.
On Fri, Sep 3, 2021 at 11:46 PM bhavika panara @.***> wrote:
View / edit / reply to this conversation https://app.reviewnb.com/ambianic/fall-detection/pull/22/discussion/ on ReviewNB ivelin commented on 2021-09-02T16:27:15Z bhavikapanara https://github.com/bhavikapanara This sequence also misses the frames with the person actually fallen on the floor. Can you check why that is the case and add them to the detection samples.
Actually, I am skipping few frames because it is complicated to show all frames [image: image] https://user-images.githubusercontent.com/19815572/132082709-b2593118-2f06-49ef-95ed-40a33a829098.png
— You are receiving this because your review was requested. Reply to this email directly, view it on GitHub https://github.com/ambianic/fall-detection/pull/22#issuecomment-912906764, or unsubscribe https://github.com/notifications/unsubscribe-auth/AARBUFLOA6BMOE4ZF6OEG73UAGQD5ANCNFSM5DJAOSFQ .
I think it's reasonable to take snapshots once a second (1fps). That is how we implement it in production relying on the fact that falls take between 600-800ms. this should be sufficient to capture all before and after fall scenes. … On Fri, Sep 3, 2021 at 11:46 PM bhavika panara @.**> wrote: View / edit / reply to this conversation https://app.reviewnb.com/ambianic/fall-detection/pull/22/discussion/ on ReviewNB ivelin commented on 2021-09-02T16:27:15Z* bhavikapanara https://github.com/bhavikapanara This sequence also misses the frames with the person actually fallen on the floor. Can you check why that is the case and add them to the detection samples. Actually, I am skipping few frames because it is complicated to show all frames [image: image] https://user-images.githubusercontent.com/19815572/132082709-b2593118-2f06-49ef-95ed-40a33a829098.png — You are receiving this because your review was requested. Reply to this email directly, view it on GitHub <#22 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AARBUFLOA6BMOE4ZF6OEG73UAGQD5ANCNFSM5DJAOSFQ .
@ivelin Please see the updated notebook
Thank you!
--- View entire conversation on ReviewNB
@bhavikapanara Thank you for adding all important frames in the videos with before and after poses. Can you please print the confidence scores for keypoints under each detection frame as you did for the individual photos in this notebook.
Thank you!
View entire conversation on ReviewNB
@ivelin Please review the updated notebook
:tada: This PR is included in version 1.0.0 :tada:
The release is available on GitHub release
Your semantic-release bot :package::rocket:
Added human fall video samples to the existing notebook. Here is the link to access the notebook. link