Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2024-11-21 19:07:46 +01:00
Code Issues Projects Releases Wiki Activity
NVR with realtime local object detection for IP cameras
1,805 Commits 60 Branches 126 Tags 151 MiB
Python 47.8%
TypeScript 47.5%
CSS 1.4%
C++ 1.1%
Dockerfile 0.7%
Other 1.5%
ef14a43930
Go to file
Cody Cutrer ef14a43930
optimize frame-per-second calculations (#6887) 
* optimize frame-per-second calculations

FPS is never calculated over differing periods for even given
counter. By only storing timestamps within the period that is
used, we avoid having to iterate 1000 entries every time it's
re-calculated (multiple times per second). 1000 entries would
normally only be needed if something is running at 100fps. A
more common speed - anywhere from 5 to 30fps, only needs 50
to 300 entries.

This isn't a huge improvement in the grand scheme, but when motion
detection is disabled, it takes nearly as much time in a flamegraph
as actually transferring the video frame.

* fix python checks
2023-06-28 05:55:53 -05:00
.devcontainer Fix max_frames, improve stationary objects in masked areas (#6815) 2023-06-16 07:32:43 -05:00
.github Bump docker/login-action from 2.1.0 to 2.2.0 (#6740) 2023-06-11 07:21:59 -05:00
.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 Add API and WebUI to export recordings (#6550) 2023-06-08 07:32:35 -04:00
docs reduce grid size for contrast improvement (#6870) 2023-06-21 08:38:51 -05:00
frigate optimize frame-per-second calculations (#6887) 2023-06-28 05:55:53 -05:00
migrations DB Optimizations (#6712) 2023-06-11 07:23:18 -05:00
web Load labels dynamically for event filters (#6896) 2023-06-28 05:51:53 -05:00
.dockerignore Improve the devcontainer experience (#3492) 2022-11-20 07:34:12 -06:00
.gitignore Migrate default database path from /media/frigate to /config (#5219) 2023-04-23 11:35:40 -05:00
.pylintrc use fstr log style 2021-02-25 07:01:59 -06:00
benchmark_motion.py reduce grid size for contrast improvement (#6870) 2023-06-21 08:38:51 -05:00
benchmark.py Add isort and ruff linter (#6575) 2023-05-29 05:31:17 -05:00
docker-compose.yml Migrate default database path from /media/frigate to /config (#5219) 2023-04-23 11:35:40 -05:00
Dockerfile Performance: multiprocessing improvement (#6936) 2023-06-28 05:39:39 -05:00
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 Migrate default database path from /media/frigate to /config (#5219) 2023-04-23 11:35:40 -05:00
process_clip.py Improve tracking (#6516) 2023-05-31 08:12:43 -06:00
pyproject.toml Fix bug introduced in new linter (#6754) 2023-06-11 07:18:47 -05:00
README.md Clarify docs about rtmp (#5052) 2023-01-13 07:20:25 -06:00
requirements-dev.txt Add isort and ruff linter (#6575) 2023-05-29 05:31:17 -05:00
requirements-ov.txt update python deps (#6101) 2023-04-16 07:20:51 -05:00
requirements-tensorrt.txt Update library loading for tensorrt (#5087) 2023-01-14 13:14:27 -06:00
requirements-wheels.txt Performance: multiprocessing improvement (#6936) 2023-06-28 05:39:39 -05:00
requirements.txt dependency updates (#6246) 2023-04-26 06:20:29 -05:00

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