Skip to content
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

Counting Total Number of Objects detected using tf_od_predict.py? #131

Open
Geo-Trackers opened this issue Jan 9, 2019 · 1 comment
Open

Comments

@Geo-Trackers
Copy link

Dear All,

Has anyone worked on counting the total number of detected objects using tf_od_record.py ?

Thanks in advance.

Best,
Suman

@Geoyi
Copy link
Contributor

Geoyi commented Jan 11, 2019

yes, @Geo-Trackers, go to these few lines from here.

You can write a simple helper function to loop through and write down each bbox, the associated class, and the tile ID to either a dataframe, list or dictionary, and you can count the total number of bboxes (group by their classes).

Additionally, you would want to write a function to get rid the double counting too. Assuming you will see duplicated bboxes over the tile borders. I would write something like, if neighboring two bboxes' IOU > 80%, you will count them as one bbox instead of two.

Hope this is helpful.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants