administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-01-22 20:18:30 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Adding references and help to the config.yml

Browse Source 
Adding a "reference" section where the different configuration attributes are described.

@blakeblackshear please check that Ive got it right. :)
This commit is contained in:
tubalainen 2019-05-13 17:15:41 +02:00 committed by GitHub
parent e791d6646b
commit 67acb8fdff
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
config/config.yml
View File

@ -32,3 +32,9 @@ cameras:
y_offset: 250
min_person_area: 2000
threshold: 0.5
## Reference to the different attributes for the "back" camera in the example above
## NOTE to size:, x_offset: and y_offset: attributes -- They are all dependent up on the video feed resolution. You will need to adjust this to suit your setup. The numbers are pixels. The different "regions" does not have to be three.
## Tip, adjust your regions for detection. If you define one "large" region it will just cause un-necessary load on TensorFlow
## min_person_area: The person area is calculated by width x height of the bounding box (region). Anything smaller than the min_person_area is ignored for that region. It is designed to filter false positives when you know a person couldn’t be that small.
## threshold: The minimum decimal percentage (50% hit = 0.5) of "Person detected" from Tensorflow that will be reported as "positive" to the MQTT