fixtSE
FixtSEFixtSE
Blog
Membership
Shop
Booking
About
Blog
Membership
Shop
Booking
About

Youtube
Instagram
RSS
Github
Patreon
Privacy
Fixt•© 2025
Updated: Feb 19, 2025—3 min read

Coral AI Person Detection with Home Assistant & Frigate

Written by: Fixt

If you're subscribed to our Channel
Login with your Google account to get our Smart Tutorial Experience!

TABLE OF CONTENTS
PrerequisitesFrigate Full Access Add-OnFrigate IntegrationAdvanced Camera CardMosquitto Broker Add-OnConfigurationAdvanced Camera ExampleMobile Notifications Blueprint

Featured

Beginner DIY ESPHome mmWave Presence SensorBeginner DIY ESPHome mmWave Presence Sensor
Mini DIY ESPHome mmWave Presence Sensor
 ESP32 C3 + LD2450Mini DIY ESPHome mmWave Presence Sensor ESP32 C3 + LD2450

Related

Tags

Dashboard
Add-on
Home-Assistant
Presence-Detection
Integration
Tutorial
Blueprint

If you like my work, please consider supporting me on Ko-fi! ☕🎉

← Back to the blog
Coral TPU Acelerator
Using the affiliate links below helps support the channel and all the content I create 🎉🙌

Prerequisites
#

  • Coral TPU USB Accelerator
    • Amazon
    • Aliexpress

Frigate Full Access Add-On
#

By blakeblackshear
Open your Home Assistant instance and show the dashboard of a Supervisor add-on.

Frigate Integration
#

By blakeblackshear
Open your Home Assistant instance and open a repository inside the Home Assistant Community Store.

Advanced Camera Card
#

By dermotduffy
Open your Home Assistant instance and open a repository inside the Home Assistant Community Store.

Mosquitto Broker Add-On
#

Open your Home Assistant instance and show the dashboard of a Supervisor add-on.

Configuration
#

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:





















































📖 FFmpeg pressets here

Advanced Camera Example
#

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:







Mobile Notifications Blueprint
#

Open your Home Assistant instance and show the blueprint import dialog with a specific blueprint pre-filled.

Tags

Dashboard
Add-on
Home-Assistant
Presence-Detection
Integration
Tutorial
Blueprint
← Back to the blog

Featured

Beginner DIY ESPHome mmWave Presence SensorBeginner DIY ESPHome mmWave Presence Sensor
Mini DIY ESPHome mmWave Presence Sensor
 ESP32 C3 + LD2450Mini DIY ESPHome mmWave Presence Sensor ESP32 C3 + LD2450

Related

Tags

Dashboard
Add-on
Home-Assistant
Presence-Detection
Integration
Tutorial
Blueprint
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