frigate: [Support]: Events triggering outside required zones

Describe the problem you are having

I have been fighting with one camera for a while now, it mostly works great but I keep getting random events when I have a lot of motion, be it wind, rain (under IR), lighting changes, and especially when my main house lights dim at night when an automation runs. The lighting change creates large amounts of motion, and the resulting chance for a false positive goes up and I get a couple events per week during this time. Attached are a couple photos from my camera during these events.

This was one triggered during a rainstorm at night. This is typical of what I see most of, be it rain or wind. car1

This one was me driving my golf cart through the zone, and it rightly picked up the motion, but ended up triggering on a house across the street. image

In this one, the actual motion event of a vehicle driving down my driveway triggered via a car on the road (outside the motion zone, and inside the motion mask). image

This one, again outside the required zone, and inside the motion mask, triggered when a person was being tracked, but a car presumably drove through the “person” bounding box, and triggered a car event. image

These two are a similar event. A vehicle drove into the required zone, and its bounding box captured a car on the road.
image image

This is one that happened when the camera switched on its IR: image

I feel like this is a simple thing, maybe to do with masking, but I have been playing with everything I can find in the docs and been unable to reduce the false positives. I also have a decent amount of false negatives, which is why the default min_score and thresholds are changed. That being said, I have been getting these types of false positives since long before I changed those values.

One more thing, I do not have a sub-stream that is usable from this camera for detection. The camera is an Amcrest 5MP bullet, and has a very very low (unusable) resolution sub-stream. Since I am running in a VM, the CPU detectors actually work well enough for me, without getting into trying to pass a USB Coral to the VM. Inference speeds are in the low 40’s at all times.

Version

0.11.1-2EADA21

Frigate config file

mqtt:
  host: redacted
  user: redacted
  password: redacted

cameras:
  Front-Yard:
    ffmpeg:
      inputs:
        - path: rtsp://redacted:redacted@redacted/cam/realmonitor?channel=1&subtype=0&unicast=true&proto=Onvif
          roles:
            - rtmp
            - detect
            - record
    detect:
      width: 2592
      height: 1944
      fps: 3
    snapshots:
      required_zones:
        - motion_area
      enabled: true
      timestamp: true
      bounding_box: true
      retain:
        default: 180
    record:
      enabled: true
      retain:
        days: 1
        mode: motion
      events:
        required_zones:
          - motion_area
        retain:
          default: 30
    objects:
      track:
      - person
      - car
      - bus
      filters:
        car:
          min_score: 0.5
          threshold: 0.57
    motion:
        mask:
            - 814,614,1487,503,1931,545,2592,710,2592,0,0,0,0,825
    zones:
      motion_area:
        coordinates: 1487,503,1931,545,2592,710,2592,1944,0,1944,0,859,0,599
        objects:
          - person
          - car
          - bus

detectors:
    cpu1:
        type: cpu
    cpu2:
        type: cpu
    cpu3:
        type: cpu
    cpu4:
        type: cpu
    cpu5:
        type: cpu
    cpu6:
        type: cpu
    cpu7:
        type: cpu
    cpu8:
        type: cpu
timestamp_style:
  # Optional: Position of the timestamp (default: shown below)
  #           "tl" (top left), "tr" (top right), "bl" (bottom left), "br" (bottom right)
  position: "tl"
  # Optional: Format specifier conform to the Python package "datetime" (default: shown below)
  #           Additional Examples:
  #             german: "%d.%m.%Y %H:%M:%S"
  format: "%m/%d/%Y %H:%M:%S"
  # Optional: Color of font
  color:
    # All Required when color is specified (default: shown below)
    red: 255
    green: 255
    blue: 255
  # Optional: Line thickness of font (default: shown below)
  thickness: 2
  # Optional: Effect of lettering (default: shown below)
  #           None (No effect),
  #           "solid" (solid background in inverse color of font)
  #           "shadow" (shadow for font)
  effect: solid
ffmpeg:
  hwaccel_args:
    - -hwaccel
    - qsv
    - -qsv_device
    - /dev/dri/renderD128

Relevant log output

N/A

FFprobe output from your camera

ffprobe version 5.1.2-essentials_build-www.gyan.dev Copyright (c) 2007-2022 the FFmpeg developers
  built with gcc 12.1.0 (Rev2, Built by MSYS2 project)
  configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-lzma --enable-zlib --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-sdl2 --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxvid --enable-libaom --enable-libopenjpeg --enable-libvpx --enable-libass --enable-libfreetype --enable-libfribidi --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-ffnvcodec --enable-nvdec --enable-nvenc --enable-d3d11va --enable-dxva2 --enable-libmfx --enable-libgme --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libtheora --enable-libvo-amrwbenc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-librubberband
  libavutil      57. 28.100 / 57. 28.100
  libavcodec     59. 37.100 / 59. 37.100
  libavformat    59. 27.100 / 59. 27.100
  libavdevice    59.  7.100 / 59.  7.100
  libavfilter     8. 44.100 /  8. 44.100
  libswscale      6.  7.100 /  6.  7.100
  libswresample   4.  7.100 /  4.  7.100
  libpostproc    56.  6.100 / 56.  6.100
Input #0, rtsp, from 'rtsp://redacted@redacted:554':
  Metadata:
    title           : Media Server
  Duration: N/A, start: 0.200000, bitrate: N/A
  Stream #0:0: Video: h264 (Main), yuv420p(progressive), 2592x1944, 10 fps, 10 tbr, 90k tbn

Frigate stats

No response

Operating system

HassOS

Install method

HassOS Addon

Coral version

CPU (no coral)

Network connection

Wired

Camera make and model

Amcrest IP5M-B1186EW-28MM

Any other information that may be helpful

No response

About this issue

  • Original URL
  • State: closed
  • Created 2 years ago
  • Comments: 29 (3 by maintainers)

Most upvoted comments

Thank you. I had it completely backwards. I’ll try that setup now.