Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2025-04-01 01:17:00 +02:00
Code Issues Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
blakeblackshear 2019-02-04 07:10:42 -06:00
parent 0359e2d2a1
commit 4a77046c7c
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -1,10 +1,12 @@
# Realtime Object Detection for RTSP Cameras # Realtime Object Detection for RTSP Cameras
This results in a MJPEG stream with objects identified that has a lower latency than directly viewing the RTSP feed with VLC.
- Prioritizes realtime processing over frames per second. Dropping frames is fine. - Prioritizes realtime processing over frames per second. Dropping frames is fine.
- OpenCV runs in a separate process so it can grab frames as quickly as possible to ensure there aren't old frames in the buffer - OpenCV runs in a separate process so it can grab frames as quickly as possible to ensure there aren't old frames in the buffer
- Object detection with Tensorflow runs in a separate process and ignores frames that are more than 0.5 seconds old - Object detection with Tensorflow runs in a separate process and ignores frames that are more than 0.5 seconds old
- Uses shared memory arrays for handing frames between processes - Uses shared memory arrays for handing frames between processes
- Provides a url for viewing the video feed at a hard coded ~5FPS as an mjpeg stream - Provides a url for viewing the video feed at a hard coded ~5FPS as an mjpeg stream
- Frames are only encoded into mjpeg stream when it is being viewed - Frames are only encoded into mjpeg stream when it is being viewed
- A process is created per detection region
## Getting Started ## Getting Started
Build the container with Build the container with
@ -23,13 +25,18 @@ docker run -it --rm \
-v <path_to_labelmap.pbtext>:/label_map.pbtext:ro \ -v <path_to_labelmap.pbtext>:/label_map.pbtext:ro \
-p 5000:5000 \ -p 5000:5000 \
-e RTSP_URL='<rtsp_url>' \ -e RTSP_URL='<rtsp_url>' \
-e REGIONS='<box_size_1>,<x_offset_1>,<y_offset_1>:<box_size_2>,<x_offset_2>,<y_offset_2>' \
realtime-od:latest realtime-od:latest
``` ```
Access the mjpeg stream at http://localhost:5000 Access the mjpeg stream at http://localhost:5000
## Tips
- Lower the framerate of the RTSP feed on the camera to what you want to reduce the CPU usage for capturing the feed
## Future improvements ## Future improvements
- MQTT messages when detected objects change - MQTT messages when detected objects change
- Dynamic changes to processing speed, ie. only process 1FPS unless motion detected - Dynamic changes to processing speed, ie. only process 1FPS unless motion detected
- Break incoming frame into multiple smaller images and run detection in parallel for lower latency (rather than input a lower resolution)
- Parallel processing to increase FPS - Parallel processing to increase FPS
- Look into GPU accelerated decoding of RTSP stream
- Send video over a socket and use JSMPEG