Updated: Feb 19, 2025 — 3 min read
Coral AI Person Detection with Home Assistant & Frigate
Watch Tutorial on Youtube If you're subscribed to our Channel Login with your Google account to get our Smart Tutorial Experience!
If you like my work, please consider supporting me on Ko-fi! ☕🎉
Support me← Back to the blog Using the affiliate links below helps support the channel and all the content I create 🎉 🙌
Coral TPU USB Accelerator Base frigate.yaml configuration file
homeassistant/frigate.yml
detectors :
coral :
type : edgetpu
device : usb
mqtt :
host : homeassistant.local
port : 1883
topic_prefix : frigate
client_id : frigate
user : #your mqtt user
password : #your mqtt password
stats_interval : 60
cameras :
#simple camera example
entrance :
homeassistant/frigate.yml
#advanced camera example
livingroom :
ffmpeg :
output_args :
record : preset-record-generic-audio-aac
inputs :
- path : rtsp://user:password@ip-hi-res-stream:port
roles :
- record
- path : rtsp://user:password@ip-low-res-stream:port
roles :
- detect
detect :
height : 720
fps : 5
motion :
ffmpeg
:
inputs :
- path : rtsp://user:password@ip:port
roles : - record - detect
detect :
height : 720
fps : 5
record :
enabled : True
retain :
days : 7
mode : all
alerts :
retain :
days : 15
mode : motion
detections :
retain :
days : 10
mode : active_objects
review :
# Optional: alerts configuration
alerts :
# Optional: labels that qualify as an alert (default: shown below)
labels :
- person
- car
detections :
# Optional: labels that qualify as a detection (default: all labels that are tracked / listened to)
labels :
- dog
- cat
ffmpeg :
hwaccel_args : preset-rpi-64-h264
objects :
track :
- person
- car
- dog
- cat
filters :
person :
# Optional: minimum width*height of the bounding box for the detected object (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 : 0.5
# Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
threshold : 0.7
mask :
- 1280,0,1280,49,1123,0
zones :
fixt_desk :
coordinates : 445,486,419,177,542,0,679,0,829,0,810,285,686,453,572,512
snapshots :
required_zones :
- fixt_desk