NVR with realtime local object detection for IP cameras
Go to file
Blake Blackshear 911c1b2bfa
Merge pull request #32 from tubalainen/patch-2
Clarification on username and password for MQTT
2019-05-11 07:14:19 -05:00
config Clarification on username and password for MQTT 2019-05-10 16:36:22 +02:00
frigate add the ability to mask the standing location of a person 2019-04-30 20:35:22 -05:00
.dockerignore initial commit 2019-01-26 08:02:59 -06:00
.gitignore initial refactoring 2019-02-25 20:27:02 -06:00
detect_objects.py cleanup and update readme 2019-03-30 07:58:31 -05:00
diagram.png update diagram 2019-03-30 08:22:41 -05:00
Dockerfile cleanup and update readme 2019-03-30 07:58:31 -05:00
LICENSE initial commit 2019-01-26 08:02:59 -06:00
README.md Update of the home assistant integration example 2019-05-10 16:47:40 +02:00

Frigate - Realtime Object Detection for RTSP Cameras

Note: This version requires the use of a Google Coral USB Accelerator

Uses OpenCV and Tensorflow to perform realtime object detection locally for RTSP cameras. Designed for integration with HomeAssistant or others via MQTT.

  • Leverages multiprocessing and threads heavily with an emphasis on realtime over processing every frame
  • Allows you to define specific regions (squares) in the image to look for objects
  • No motion detection (for now)
  • Object detection with Tensorflow runs in a separate thread
  • Object info is published over MQTT for integration into HomeAssistant as a binary sensor
  • An endpoint is available to view an MJPEG stream for debugging

Diagram

Example video (from older version)

You see multiple bounding boxes because it draws bounding boxes from all frames in the past 1 second where a person was detected. Not all of the bounding boxes were from the current frame.

Getting Started

Build the container with

docker build -t frigate .

The mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite model is included and used by default. You can use your own model and labels by mounting files in the container at /frozen_inference_graph.pb and /label_map.pbtext. Models must be compatible with the Coral according to this.

Run the container with

docker run --rm \
--privileged \
-v /dev/bus/usb:/dev/bus/usb \
-v <path_to_config_dir>:/config:ro \
-p 5000:5000 \
-e RTSP_PASSWORD='password' \
frigate:latest

Example docker-compose:

  frigate:
    container_name: frigate
    restart: unless-stopped
    privileged: true
    image: frigate:latest
    volumes:
      - /dev/bus/usb:/dev/bus/usb
      - <path_to_config>:/config
    ports:
      - "5000:5000"
    environment:
      RTSP_PASSWORD: "password"

A config.yml file must exist in the config directory. See example here.

Access the mjpeg stream at http://localhost:5000/<camera_name> and the best person snapshot at http://localhost:5000/<camera_name>/best_person.jpg

Integration with HomeAssistant

camera:
  - name: Camera Last Person
    platform: generic
    still_image_url: http://<ip>:5000/<camera_name>/best_person.jpg

binary_sensor:
  - name: Camera Person
    platform: mqtt
    state_topic: "frigate/<camera_name>/objects"
    value_template: '{{ value_json.person }}'
    device_class: motion
    availability_topic: "frigate/available"

Tips

  • Lower the framerate of the RTSP feed on the camera to reduce the CPU usage for capturing the feed

Future improvements

  • Remove motion detection for now
  • Try running object detection in a thread rather than a process
  • Implement min person size again
  • Switch to a config file
  • Handle multiple cameras in the same container
  • Attempt to figure out coral symlinking
  • Add object list to config with min scores for mqtt
  • Move mjpeg encoding to a separate process
  • Simplify motion detection (check entire image against mask, resize instead of gaussian blur)
  • See if motion detection is even worth running
  • Scan for people across entire image rather than specfic regions
  • Dynamically resize detection area and follow people
  • Add ability to turn detection on and off via MQTT
  • Output movie clips of people for notifications, etc.
  • Integrate with homeassistant push camera
  • Merge bounding boxes that span multiple regions
  • Implement mode to save labeled objects for training
  • Try and reduce CPU usage by simplifying the tensorflow model to just include the objects we care about
  • Look into GPU accelerated decoding of RTSP stream
  • Send video over a socket and use JSMPEG
  • Look into neural compute stick