mirror of
https://github.com/blakeblackshear/frigate.git
synced 2024-12-23 19:11:14 +01:00
update config example
This commit is contained in:
parent
ebcf1482f8
commit
6ecf87fc60
@ -47,16 +47,24 @@ mqtt:
|
|||||||
# - rgb24
|
# - rgb24
|
||||||
|
|
||||||
####################
|
####################
|
||||||
# Global object configuration. Applies to all cameras and regions
|
# Global object configuration. Applies to all cameras
|
||||||
# unless overridden at the camera/region levels.
|
# unless overridden at the camera levels.
|
||||||
# Keys must be valid labels. By default, the model uses coco (https://dl.google.com/coral/canned_models/coco_labels.txt).
|
# Keys must be valid labels. By default, the model uses coco (https://dl.google.com/coral/canned_models/coco_labels.txt).
|
||||||
# All labels from the model are reported over MQTT. These values are used to filter out false positives.
|
# All labels from the model are reported over MQTT. These values are used to filter out false positives.
|
||||||
|
# min_area (optional): minimum width*height of the bounding box for the detected person
|
||||||
|
# max_area (optional): maximum width*height of the bounding box for the detected person
|
||||||
|
# threshold (optional): The minimum decimal percentage (50% hit = 0.5) for the confidence from tensorflow
|
||||||
####################
|
####################
|
||||||
objects:
|
objects:
|
||||||
person:
|
track:
|
||||||
min_area: 5000
|
- person
|
||||||
max_area: 100000
|
- car
|
||||||
threshold: 0.5
|
- truck
|
||||||
|
filters:
|
||||||
|
person:
|
||||||
|
min_area: 5000
|
||||||
|
max_area: 100000
|
||||||
|
threshold: 0.5
|
||||||
|
|
||||||
cameras:
|
cameras:
|
||||||
back:
|
back:
|
||||||
@ -91,18 +99,21 @@ cameras:
|
|||||||
################
|
################
|
||||||
take_frame: 1
|
take_frame: 1
|
||||||
|
|
||||||
|
################
|
||||||
|
# Overrides for global object config
|
||||||
|
################
|
||||||
objects:
|
objects:
|
||||||
person:
|
track:
|
||||||
min_area: 5000
|
- person
|
||||||
max_area: 100000
|
filters:
|
||||||
threshold: 0.5
|
person:
|
||||||
|
min_area: 5000
|
||||||
|
max_area: 100000
|
||||||
|
threshold: 0.5
|
||||||
|
|
||||||
################
|
################
|
||||||
# size: size of the region in pixels
|
# size: size of the region in pixels
|
||||||
# x_offset/y_offset: position of the upper left corner of your region (top left of image is 0,0)
|
# x_offset/y_offset: position of the upper left corner of your region (top left of image is 0,0)
|
||||||
# min_person_area (optional): minimum width*height of the bounding box for the detected person
|
|
||||||
# max_person_area (optional): maximum width*height of the bounding box for the detected person
|
|
||||||
# threshold (optional): The minimum decimal percentage (50% hit = 0.5) for the confidence from tensorflow
|
|
||||||
# Tips: All regions are resized to 300x300 before detection because the model is trained on that size.
|
# Tips: All regions are resized to 300x300 before detection because the model is trained on that size.
|
||||||
# Resizing regions takes CPU power. Ideally, all regions should be as close to 300x300 as possible.
|
# Resizing regions takes CPU power. Ideally, all regions should be as close to 300x300 as possible.
|
||||||
# Defining a region that goes outside the bounds of the image will result in errors.
|
# Defining a region that goes outside the bounds of the image will result in errors.
|
||||||
@ -111,18 +122,9 @@ cameras:
|
|||||||
- size: 350
|
- size: 350
|
||||||
x_offset: 0
|
x_offset: 0
|
||||||
y_offset: 300
|
y_offset: 300
|
||||||
objects:
|
|
||||||
car:
|
|
||||||
threshold: 0.2
|
|
||||||
- size: 400
|
- size: 400
|
||||||
x_offset: 350
|
x_offset: 350
|
||||||
y_offset: 250
|
y_offset: 250
|
||||||
objects:
|
|
||||||
person:
|
|
||||||
min_area: 2000
|
|
||||||
- size: 400
|
- size: 400
|
||||||
x_offset: 750
|
x_offset: 750
|
||||||
y_offset: 250
|
y_offset: 250
|
||||||
objects:
|
|
||||||
person:
|
|
||||||
min_area: 2000
|
|
||||||
|
Loading…
Reference in New Issue
Block a user