Hello. I’ve recently been using Frigate to detect movement on the front door with my DoorBird bell. Unfortunately, I’m having trouble configuring the intelligence so I’m not overwhelmed with alarms. 60-80 alarms a day are not uncommon. And the problem with that: they are triggered by two chimneys, a tree, etc. So: nothing adequate. However, I cannot mask these areas as my door is about 2 meters from the floor and I mask the person coming in front of the camera as soon as they come up the stairs. Here are a few photos. Masked for privacy. Sorry! I hope you can still read something from it.
My configuration:
mqtt:
host: 192.168.1.16
user: #username
password: #password
timestamp_style:
position: "tl"
format: "%d/%m/%Y %H:%M:%S"
color:
red: 255
green: 255
blue: 255
thickness: 2
effect: "solid"
cameras:
Kamera_Haustuer_Frigate:
ffmpeg:
inputs:
- path: rtsp://#username:#password@#IP/mpeg/media.amp
roles:
- record
- detect
- clips
- rtmp
objects:
track:
- person
- car
- cat
filters:
person:
# Optional: minimum width*height of the bounding box for the detected object. Vorher: 5000. Default 0
min_area: 0
# Optional: maximum width*height of the bounding box for the detected object (default: 24000000)
max_area: 100000
# Optional: minimum score for the object to initiate tracking (default: shown below)
min_score: 0.2
# Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
threshold: 0.5
snapshots: # <----- Enable snapshots
enabled: True
timestamp: True
retain:
default: 1
objects:
person: 2
record: # <----- Enable recording
enabled: True
events:
retain:
default: 1
expire_interval: 1440
rtmp:
enabled: True # <-- RTMP should be disabled if your stream is not H264
detect:
width: 1280
height: 720
motion:
threshold: 300
detectors:
cpu1:
type: cpu