-
-
Notifications
You must be signed in to change notification settings - Fork 20
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
Nothing Detected From Security Camera Image #77
Comments
How large is the image? |
The security camera images are 4K (3840 by 2160 pixels) and 3.3MB. The image that worked was 2048 by 1365 pixels and 563KB |
I think they are being resized to 640 so all the details are getting lost |
Is that a hardware limitation of a software limitation? |
The model requires that size as input. A larger model could alternatively be used |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
So I have been testing this out to see if I can get it to work for my security cameras. I took one of my alert images with a car and a person standing with their back to the view. I pushed this image to the application via curl and the application returned that nothing was detected. If I took a random stock image form the web of just a person's face, pushed it to the application fro analysis it would return that there is a person detected.
Is this a limitation to the model currently being used or is there another limitation within the application that doesn't detect cars or people standing from a distance?
The text was updated successfully, but these errors were encountered: