Viseron is a self-hosted, local only NVR implemented in Python. The goal is ease of use while also leveraging hardware acceleration for minimal system load.

• Records videos on detected objects

• Lookback, buffers frames to record before the event actually happened

• Multiplatform, should support any x86-64 machine running Linux, aswell as RPi3 Builds are tested and verified on the following platforms:

  • Ubuntu 18.04 with Nvidia GPU
  • Ubuntu 18.04 running on an Intel NUC
  • RaspberryPi 3B+

• Supports multiple different object detectors:

  • Yolo Darknet using OpenCV
  • Tensorflow via Google Coral EdgeTPU

• Supports hardware acceleration on different platforms

  • CUDA for systems with a supported GPU
  • OpenCL
  • OpenMax and MMAL on the RaspberryPi 3B+

Choose the appropriate docker container for your machine.

docker run --rm \
--privileged \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
-v /dev/bus/usb:/dev/bus/usb \
-v /opt/vc/lib:/opt/vc/lib \
--name viseron \
--device /dev/vchiq:/dev/vchiq --device /dev/vcsm:/dev/vcsm \
roflcoopter/viseron-rpi:latest

version: "2.4"
services:
  viseron:
    image: roflcoopter/viseron-rpi:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
      - /dev/bus/usb:/dev/bus/usb
      - /opt/vc/lib:/opt/vc/lib
    devices:
      - /dev/vchiq:/dev/vchiq
      - /dev/vcsm:/dev/vcsm
    privileged: true

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
roflcoopter/viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
--device /dev/dri \
roflcoopter/viseron-vaapi:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron-vaapi:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    devices:
      - /dev/dri

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
--runtime=nvidia \
roflcoopter/viseron-cuda:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron-cuda:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    runtime: nvidia

VAAPI support is built into every container. To utilize it you need to add --device /dev/dri to your docker command.
EdgeTPU support is also included in all containers. To use it, add -v /dev/bus/usb:/dev/bus/usb --privileged to your docker command.

The config.yaml has to be mounted to the folder /config.
If no config is present, a default minimal one will be created.
Here you need to fill in atleast your cameras and you should be good to go.

Used to build the FFMPEG command to decode camera stream.
The command is built like this:
"ffmpeg" + global_args + input_args + hwaccel_args + codec + "-rtsp_transport tcp -i " + (stream url) + filter_args + output_args

The default command varies a bit depending on the supported hardware:

ffmpeg -hide_banner -loglevel panic -avoid_negative_ts make_zero -fflags nobuffer -flags low_delay -strict experimental -fflags +genpts -stimeout 5000000 -use_wallclock_as_timestamps 1 -vsync 0 -c:v h264_cuvid -rtsp_transport tcp -i rtsp://<username>:<password>@<host>:<port><path> -f rawvideo -pix_fmt nv12 pipe:1

ffmpeg -hide_banner -loglevel panic -avoid_negative_ts make_zero -fflags nobuffer -flags low_delay -strict experimental -fflags +genpts -stimeout 5000000 -use_wallclock_as_timestamps 1 -vsync 0 -hwaccel vaapi -vaapi_device /dev/dri/renderD128 -rtsp_transport tcp -i rtsp://<username>:<password>@<host>:<port><path> -f rawvideo -pix_fmt nv12 pipe:1

ffmpeg -hide_banner -loglevel panic -avoid_negative_ts make_zero -fflags nobuffer -flags low_delay -strict experimental -fflags +genpts -stimeout 5000000 -use_wallclock_as_timestamps 1 -vsync 0 -c:v h264_mmal -rtsp_transport tcp -i rtsp://<username>:<password>@<host>:<port><path> -f rawvideo -pix_fmt nv12 pipe:1

TODO Future releases will make the motion detection easier to fine tune. Right now its a guessing game

The default command varies a bit depending on the supported hardware:

ffmpeg -hide_banner -loglevel panic -f rawvideo -pix_fmt nv12 -s:v <width>x<height> -r <fps> -i pipe:0 -y -c:v h264_nvenc <file>

ffmpeg -hide_banner -loglevel panic -hwaccel vaapi -vaapi_device /dev/dri/renderD128 -f rawvideo -pix_fmt nv12 -s:v <width>x<height> -r <fps> -i pipe:0 -y -c:v h264_vaapi -vf "format=nv12|vaapi,hwupload" <file>

ffmpeg -hide_banner -loglevel panic -f rawvideo -pix_fmt nv12 -s:v <width>x<height> -r <fps> -i pipe:0 -y -c:v h264_omx <file>

• UI

  • Create a UI for configuration and viewing of recordings

• Detectors

  • Pause detection via MQTT
  • Move detectors to specific folder
  • Allow specified confidence to override height/width thresholds
  • Refactor Darknet
  • Darknet Choose backend via config
  • Dynamic detection interval, speed up interval when detection happens for all types of detectors
  • Implement an object tracker for detected objects
  • Make it easier to implement custom detectors

• Watchdog Build a watchdog for the camera process

• Recorder

  • Weaving, If detection is triggered close to previous detection, send silent alarm and "weave" the videos together.
  • Dynamic lookback based on motion

• Properties: All public vars should be exposed by property

• Decouple MQTT

  • One client object.
  • Start all camera threads, which need to expose an on_message function
  • Pass list of camera objects to MQTT

• Docker

  • Try to reduce container footprint

• Logger

  • Set loglevel individually for each component

https://devblogs.nvidia.com/object-detection-pipeline-gpus/