administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-08 20:25:26 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
NVR with realtime local object detection for IP cameras
2,330 Commits 57 Branches 152 Tags 730 MiB
TypeScript 51.9%
Python 46.1%
CSS 0.6%
Shell 0.5%
Dockerfile 0.4%
Other 0.3%
5e8f482bb7
Go to file
chamila 5e8f482bb7 Add PoC implementation of batch delete 
The batch delete goes through all the already displayed Events pages and
deletes any Event that is not marked as favorite/saved. It doesn't query
the database to get the full list of Events, as the user should be able
to clearly understand which Events will be cleaned up.

After the list of Events to be deleted is identified, it will prompt the
user to confirm the deletion of the number of Events. It will then show
a spinner until the Events are deleted and then show a feedback dialog
mentioning the number of Events deleted.

The button for the Cleanup operation is put on the same row as the
filters as adding a new row for a single button seemed ugly. It's marked
to be different with a border, since the Cleanup operation is not a
filtering option. The SVG was downloaded from [1] and it's licensed
as Public Domain [2].

1 - https://www.svgrepo.com/svg/494112/clean-up
2 - https://www.svgrepo.com/page/licensing/#CC0
2024-02-26 23:28:17 +13:00
.devcontainer Remove deprecated RTMP port 1935 (#9137) 2024-01-31 12:56:11 +00:00
.github another name fix (#9886) 2024-02-16 06:51:19 -06:00
.vscode Set User Agent for FFmpeg calls (#4555) 2022-11-30 16:53:45 -06:00
config Improve the devcontainer experience (#3492) 2022-11-20 07:34:12 -06:00
docker Update FFmpeg for Rockchip image (#9912) 2024-02-20 23:21:24 +00:00
docs fix typos (#9895) 2024-02-17 16:01:50 -06:00
frigate Fix reviewed filter (#10039) 2024-02-25 15:36:18 -07:00
migrations Create ReviewSegment table in DB for organizing detections to be reviewed (#9918) 2024-02-20 16:26:09 -07:00
web Fix reviewed filter (#10039) 2024-02-25 15:36:18 -07:00
web-old Add PoC implementation of batch delete 2024-02-26 23:28:17 +13:00
.dockerignore Improve the devcontainer experience (#3492) 2022-11-20 07:34:12 -06:00
.gitignore Small autotracking changes (#9571) 2024-02-02 06:23:14 -06:00
.pylintrc use fstr log style 2021-02-25 07:01:59 -06:00
audio-labelmap.txt Audio events (#6848) 2023-07-01 08:18:33 -05:00
benchmark_motion.py use a different method for blur and contrast to reduce CPU (#6940) 2023-06-30 07:27:31 -05:00
benchmark.py Add isort and ruff linter (#6575) 2023-05-29 05:31:17 -05:00
CODEOWNERS AMD GPU support with the rocm detector and YOLOv8 pretrained model download (#9762) 2024-02-10 06:41:46 -06:00
docker-compose.yml Docs improvements (#8641) 2023-11-18 08:04:43 -06:00
labelmap.txt Cleanup Detector labelmap (#4932) 2023-01-06 07:03:16 -06:00
LICENSE switch to MIT license 2020-07-26 12:07:47 -05:00
Makefile Update Makefile for 0.13.2 (#9687) 2024-02-05 17:50:35 -06:00
netlify.toml Docs improvements (#8641) 2023-11-18 08:04:43 -06:00
process_clip.py Remove rtmp (#8941) 2024-01-31 12:56:11 +00:00
pyproject.toml Docs improvements (#8641) 2023-11-18 08:04:43 -06:00
README.md Clarify docs about rtmp (#5052) 2023-01-13 07:20:25 -06:00

README.md

logo

Frigate - NVR With Realtime Object Detection for IP Cameras

A complete and local NVR designed for Home Assistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras.

Use of a Google Coral Accelerator is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.

  • Tight integration with Home Assistant via a custom component
  • Designed to minimize resource use and maximize performance by only looking for objects when and where it is necessary
  • Leverages multiprocessing heavily with an emphasis on realtime over processing every frame
  • Uses a very low overhead motion detection to determine where to run object detection
  • Object detection with TensorFlow runs in separate processes for maximum FPS
  • Communicates over MQTT for easy integration into other systems
  • Records video with retention settings based on detected objects
  • 24/7 recording
  • Re-streaming via RTSP to reduce the number of connections to your camera
  • WebRTC & MSE support for low-latency live view

Documentation

View the documentation at https://docs.frigate.video

Donations

If you would like to make a donation to support development, please use Github Sponsors.

Screenshots

Integration into Home Assistant

Also comes with a builtin UI:

Events