-
-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
False detections at night / 1-channel greyscale issue? #67
Comments
I get these false positives from time to time too. They rarely cause my mqtt sensor to trigger because they are moving so fast. There are several ways I could approach this, but haven't gotten to it yet. One of my main goals is for this to be reliable enough to wake me up in the night if needed, so I will iron this out eventually. |
One thing that helps with spiders close to the cameras at least is external IR illuminators. But, I also have a lot more false positives at night. Would be nice to see similar accuracy at night as what's possible during the day. |
I am having this problem with birds/spiders at night as well. Unfortunately, it happened right after 12 months of no issues and after I had set up alarms that woke us up in the night. |
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. |
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. |
Going to add a particularly annoying example for me, when my cameras switch from day to night mode the driver and passenger seats get detected as people. |
Add spark configuration variable
I get lots of false detections from spider webs and moths etc at night in infrared.
This article suggests that images from an infrared camera are single channel, while most models are trained on 3 channel RGB Images.
There is also this on tensorflow github with some more info if needed.
Solution as per the links appears to be to stack the single channel 3 times to form a 3-channel input.
Hopeful this is possible and not too much work :)
The text was updated successfully, but these errors were encountered: