Camera not detecting people on drive. #7877

dopeytree · 2023-09-19T14:03:26Z

dopeytree
Sep 19, 2023

Having some trouble detecting people. New camera on the drive. covers porch & the drive so it should capture people leaving the house or the postman walking down the drive towards camera and putting post through the door...

Camera is question in the last camera in the config the 'HOUSE_FRONT_2'

It's got 2x zones to stop notifications of the car being on the drive. Instead it detects if a car is leaving or entering the drive.

Any pointers in how to best set up people detection? Do I need to move the camera?

It doesn't detect some people but it's very inconsistent.

This is a new camera so trying to pinpoint if its a camera issue or my config needs tweaking.

https://imgur.com/a/JI1kaf6

# Configuration File
# Used https://docs.frigate.video/configuration/#vscode-configuration-schema

mqtt:
  enabled: true
  host: 192.168.22.2
  port: 1883
   # Optional: topic prefix (default: shown below)
  # WARNING: must be unique if you are running multiple instances
  topic_prefix: frigate
  # Optional: client id (default: shown below)
  # WARNING: must be unique if you are running multiple instances
  client_id: frigate
  # Optional: user
  user:
  # Optional: password
  # NOTE: Environment variables that begin with 'FRIGATE_' may be referenced in {}.
  #       eg. password: '{FRIGATE_MQTT_PASSWORD}'
  password:
  # Optional: interval in seconds for publishing stats (default: shown below)
  stats_interval: 60


# Optional: Restream configuration
# Uses https://github.com/AlexxIT/go2rtc (v1.2.0)
go2rtc:
   streams:
    barn HQ:
      - rtsp://MPG7QbYQ:ICRGvtBU2xo3DxMy@192.168.22.202:554/live/ch0
    #barn SQ:
     # - rtsp:https://MPG7QbYQ:[email protected]:554/live/ch1
    bird HQ:
      - rtsp://pSrUq7TZ:4ua2cFC2dq2UNEXx@192.168.22.201:554/live/ch0
    #bird SQ:
     # - rtsp:https://pSrUq7TZ:[email protected]:554/live/ch1
    house_front HQ:
      - rtsp://EWLHSHKY:XGEJzBByF2IE3c@192.168.44.5:554/live/ch0
    house_front_2 HQ:
      - rtsp://admin:annke2023@192.168.44.6:554/H265/ch1/main/av_stream
    
    #house_front SQ:
     # - rtsp:https://EWLHSHKY:[email protected]:554/live/ch1
    #wyze:
      #- rtsp:https://admin:[email protected]:8554/live/ch0

# Optional: ffmpeg configuration
# More information about presets at https://docs.frigate.video/configuration/ffmpeg_presets
ffmpeg:
  # Optional: global ffmpeg args (default: shown below)
  global_args: -hide_banner -loglevel warning -threads 16
  # Optional: global hwaccel args (default: shown below)
  # NOTE: See hardware acceleration docs for your specific device
  hwaccel_args: preset-vaapi
  # Optional: global input args (default: shown below)
  input_args: preset-rtsp-generic-audio-aac
  # Optional: global output args
  output_args:
    # Optional: output args for detect streams (default: shown below)
    detect: -threads 16 -f rawvideo -pix_fmt yuv420p
    # Optional: output args for record streams (default: shown below)
    record: preset-record-generic-audio-aac
    # Optional: output args for rtmp streams (default: shown below)
    rtmp: preset-rtmp-generic
  
detectors:
  coral:
    type: edgetpu
    device: usb   


# Optional: Detect configuration
# NOTE: Can be overridden at the camera level
detect:
  # Optional: width of the frame for the input with the detect role (default: shown below)
  #width: 1280
  # Optional: height of the frame for the input with the detect role (default: shown below)
  #height: 720
  # Optional: desired fps for your camera for the input with the detect role (default: shown below)
  # NOTE: Recommended value of 5. Ideally, try and reduce your FPS on the camera.
  #fps: 5
  # Optional: enables detection for the camera (default: True)
  enabled: true
  # Optional: Number of frames without a detection before Frigate considers an object to be gone. (default: 5x the frame rate)
  max_disappeared: 75
  # Optional: Configuration for stationary object tracking
  stationary:
    # Optional: Frequency for confirming stationary objects (default: shown below)
    # When set to 0, object detection will not confirm stationary objects until movement is detected.
    # If set to 10, object detection will run to confirm the object still exists on every 10th frame.
    interval: 10
    # Optional: Number of frames without a position change for an object to be considered stationary (default: 10x the frame rate or 10s)
    threshold: 10

# Optional: Motion configuration
# NOTE: Can be overridden at the camera level
motion:
  # Optional: The threshold passed to cv2.threshold to determine if a pixel is different enough to be counted as motion. (default: shown below)
  # Increasing this value will make motion detection less sensitive and decreasing it will make motion detection more sensitive.
  # The value should be between 1 and 255.
  threshold: 20
  # Optional: Minimum size in pixels in the resized motion image that counts as motion (default: 30)
  # Increasing this value will prevent smaller areas of motion from being detected. Decreasing will
  # make motion detection more sensitive to smaller moving objects.
  # As a rule of thumb:
  #  - 15 - high sensitivity
  #  - 30 - medium sensitivity
  #  - 50 - low sensitivity
  contour_area: 20
  # Optional: Alpha value passed to cv2.accumulateWeighted when averaging the motion delta across multiple frames (default: shown below)
  # Higher values mean the current frame impacts the delta a lot, and a single raindrop may register as motion.
  # Too low and a fast moving person wont be detected as motion.
  delta_alpha: 0.3
  # Optional: Alpha value passed to cv2.accumulateWeighted when averaging frames to determine the background (default: shown below)
  # Higher values mean the current frame impacts the average a lot, and a new object will be averaged into the background faster.
  # Low values will cause things like moving shadows to be detected as motion for longer.
  # https://www.geeksforgeeks.org/background-subtraction-in-an-image-using-concept-of-running-average/
  frame_alpha: 0.3
  # Optional: Height of the resized motion frame  (default: 50)
  # This operates as an efficient blur alternative. Higher values will result in more granular motion detection at the expense
  # of higher CPU usage. Lower values result in less CPU, but small changes may not register as motion.
  frame_height: 50
  # Optional: improve contrast (default: shown below)
  # Enables dynamic contrast improvement. This should help improve night detections at the cost of making motion detection more sensitive
  # for daytime.
  improve_contrast: true
         

cameras:
         
  barn: # 1 - BARN - cam name - Brand: Wansview - Quality:1080p
    snapshots:
      enabled: true
      bounding_box: true
      quality: 99
    #  
    ffmpeg:
      output_args: 
        record: preset-record-generic-audio-aac
      hwaccel_args: preset-vaapi
      inputs:
        - path: rtsp://MPG7QbYQ:ICRGvtBU2xo3DxMy@192.168.22.202:554/live/ch1 # SD Link
          input_args: preset-rtsp-generic
          roles:
            - detect
        - path: rtsp://192.168.22.2:8554/barn%20HQ?mp4 # HD Link
          input_args: preset-rtsp-restream
          roles:
            - record
    detect:
      width: 768
      height: 432
      fps: 5
      stationary:
        interval: 0
        threshold: 70
    motion:
      mask:
        - 768,0,768,24,524,24,524,0    
    objects:
      track:
        - person
        - cat 
        - suitcase
      filters:
        #     
        person:
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        # 
        cat:
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7           
    record:
      enabled: true
      retain:
        days: 7
        mode: motion
      events:
        pre_capture: 5
        post_capture: 5
        retain:
          default: 28
          mode: active_objects 

  


  house_front: # no3 - HOUSE_FRONT - Cam name - Brand: Wansview - Quality:1080p
    snapshots:
      enabled: true
      bounding_box: true
      quality: 99
    #  
    ffmpeg:
      output_args:
        record: preset-record-generic-audio-aac 
      hwaccel_args: preset-vaapi
      inputs:
        - path: rtsp://EWLHSHKY:XGEJzBByF2IE3c@192.168.44.5:554/live/ch1 # SD Link
          input_args: preset-rtsp-generic
          roles:
            - detect
        - path: rtsp://192.168.22.2:8554/house_front%20HQ?mp4  # HD Link
          input_args: preset-rtsp-restream
          roles:
            - record
    detect:
      width: 768  
      height: 432
      fps: 7
      stationary:
        interval: 0
        threshold: 70
    motion:
      mask:
        - 768,450,768,325,724,317,653,288,614,294,606,260,596,224,518,205,414,233,371,299,332,407,444,450
        - 496,0,768,0,768,159,657,126,567,100,504,125,434,129,386,142,332,98,175,85,0,83,0,0,335,0
        - 0,215,0,296,69,305,127,265,141,225,110,167,64,136   
    objects:
      track:
        - person
        - car
        - dog
        - cat
        - bicycle
        - motorcycle
      filters:
        #
        car:  
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        #
        person:
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        #
        dog:
          min_area: 1000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        # 
        cat:
          min_area: 1000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        # 
        bicycle:
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        #  
        motorcycle:
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7          
    record:
      enabled: true
      retain:
        days: 7
        mode: motion
      events:
        pre_capture: 5
        post_capture: 5
        objects:
        - person
        - car
        - dog
        - cat
        - bicycle
        - motorcycle
        retain:
          default: 28
          mode: active_objects


  house_front_2: # no4 - HOUSE_FRONT_2 - Cam name - Brand: Annke - Quality:3k
    snapshots:
      enabled: true
      bounding_box: true
      quality: 99
    #  
    ffmpeg:
      output_args:
        record: preset-record-generic-audio-aac 
      hwaccel_args: preset-vaapi
      inputs:
        - path: rtsp://admin:annke2023@192.168.44.6:554/Streaming/Channels/102 # SQ Link
          input_args: preset-rtsp-generic
          roles:
            - detect
        - path: rtsp://192.168.22.2:8554/house_front_2%20HQ?mp4  # HQ Link
          input_args: preset-rtsp-restream
          roles:
            - record
    detect:
      width: 640  
      height: 480
      fps: 7
      stationary:
        interval: 0
        threshold: 70
    motion:
      mask:
        - 189,0,189,23,0,23,0,0,0,0,0,0
        - 640,480,640,221,608,173,503,169,408,386,378,480
        - 334,106,505,111,527,0,330,0
    zones:
      zone_0:
        coordinates: 329,62,329,179,515,189,514,210,410,480,0,480,0,31
        objects:
        - person
        - cat
        - dog  
      zone_1:
        coordinates: 325,176,578,183,584,0,323,0   
        objects:
        - car
        - person
        - cat
        - dog 
    objects:
      track:
        - person
        - car
        - dog
        - cat
      filters:
        #
        car:
          mask:
            - 331,329,538,311,532,194,328,183
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        #
        person:
          min_area: 2000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.4
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.6
        #
        dog:
          min_area: 1000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
        #
        cat:
          min_area: 1000
          max_area: 100000
          # Optional: minimum width/height of the bounding box for the detected object (default: 0)
          min_ratio: 0.5
          # Optional: maximum width/height of the bounding box for the detected object (default: 24000000)
          max_ratio: 2.0
          # Optional: minimum score for the object to initiate tracking (default: shown below)
          min_score: 0.5
          # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
          threshold: 0.7
    record:
      enabled: true
      retain:
        days: 7
        mode: motion
      events:
        pre_capture: 7
        post_capture: 7
        objects:
        - person
        - car
        - dog
        - cat
        retain:
          default: 28
          mode: active_objects 
  

    # Optional: Telemetry configuration
telemetry:
  # Optional: Enable the latest version outbound check (default: shown below)
  # NOTE: If you use the HomeAssistant integration, disabling this will prevent it from reporting new versions
  version_check: True

Answered by NickM-27

Sep 19, 2023

if you are having trouble detecting people, I would definitely suggest removing your filters

View full answer

NickM-27 · 2023-09-19T14:06:22Z

NickM-27
Sep 19, 2023
Collaborator Sponsor

if you are having trouble detecting people, I would definitely suggest removing your filters

0 replies

dopeytree · 2023-09-19T14:42:50Z

dopeytree
Sep 19, 2023
Author

Same filters are working on the other cameras fine.

Will redo the zone0 to include the full frame as I think it might be cutting people off as when they get close to the camera they will be much bigger in the frame.

1 reply

NickM-27 Sep 19, 2023
Collaborator Sponsor

An objects presence in the zone is based on the bottom center of their bounding box so I don't think that's the issue. Filters can differ, and of course filters immediately ignore detections and there's no reason to use filters when you're getting less than expected detections.

dopeytree · 2023-09-19T15:17:41Z

dopeytree
Sep 19, 2023
Author

Thanks have removed the person filters.

Have another question about different camera covering house facing a road.. what's the best way to avoid hour long recordings of parked cars outside the house... I thought about changing it to only track people. As a possible solution. To track people, cats & dogs should then catch any cars as a by product of the recording itself?

2 replies

NickM-27 Sep 19, 2023
Collaborator Sponsor

just change the recording retention mode https://docs.frigate.video/configuration/record#what-do-the-different-retain-modes-mean

dopeytree Sep 19, 2023
Author

thanks :)

dopeytree · 2023-09-19T16:41:05Z

dopeytree
Sep 19, 2023
Author

Lovely stuff its captured the amazon delivery nicely so thanks for the help.

Can I get some help with my record settings?
Should I remove the last retain setting as we've swapped to record active objects and removed motion.

 record:
      enabled: true
      retain:
        days: 7
        mode: active_objects
      events:
        pre_capture: 5
        post_capture: 3
        objects:
        - person
        - car
        - dog
        - cat
        retain:
          default: 28
          mode: active_objects

3 replies

NickM-27 Sep 19, 2023
Collaborator Sponsor

you could but there is no reason to really

dopeytree Sep 19, 2023
Author

Could you help me understand the logic of it at the moment.

7 days worth of active objects are recorded.
the events have pre & post capture.
objects list the objects recorded.

then retain: 28 days.

NickM-27 Sep 19, 2023
Collaborator Sponsor

This is the logic:

keep 7 days of 24/7 recording, keeping every segment where frigate detected ANY active object that is in the objects -> track list
keep 28 days of event recordings, keeping every segment where frigate detected ANY active object is in the objects -> track list

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Camera not detecting people on drive. #7877

{{title}}

{{editor}}'s edit

{{editor}}'s edit

Replies: 4 comments 6 replies

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

Select a reply

Camera not detecting people on drive. #7877

dopeytree Sep 19, 2023

Replies: 4 comments · 6 replies

NickM-27 Sep 19, 2023 Collaborator Sponsor

dopeytree Sep 19, 2023 Author

NickM-27 Sep 19, 2023 Collaborator Sponsor

dopeytree Sep 19, 2023 Author

NickM-27 Sep 19, 2023 Collaborator Sponsor

dopeytree Sep 19, 2023 Author

dopeytree Sep 19, 2023 Author

NickM-27 Sep 19, 2023 Collaborator Sponsor

dopeytree Sep 19, 2023 Author

NickM-27 Sep 19, 2023 Collaborator Sponsor

dopeytree
Sep 19, 2023

Replies: 4 comments 6 replies

NickM-27
Sep 19, 2023
Collaborator Sponsor

dopeytree
Sep 19, 2023
Author

NickM-27 Sep 19, 2023
Collaborator Sponsor

dopeytree
Sep 19, 2023
Author

NickM-27 Sep 19, 2023
Collaborator Sponsor

dopeytree Sep 19, 2023
Author

dopeytree
Sep 19, 2023
Author

NickM-27 Sep 19, 2023
Collaborator Sponsor

dopeytree Sep 19, 2023
Author

NickM-27 Sep 19, 2023
Collaborator Sponsor