App Stack
Stray Animal Detection

Stray Animal Detection

Stray Animal Detection is used to detect and generate events when animals enter a defined area. It can be configured to work with RGB cameras, thermal cameras, or both, depending on deployment requirements.

This guide explains how to configure the Stray Animal Detection application in App Stack.


1. Finding the Stray Animal Detection Application in App Stack

  1. Open App Stack on the platform.
  2. Use the search bar (usually at the top right of the dashboard).
  3. Enter Stray Animal Detection.
  4. In the results, click once on the application to open it.

Search Stray Animal Detection


2. Device Configuration

After the application opens, you will be directed to the Device Configuration page.

Device Configuration

  • On the right side of the page, click Add Device to add the required camera(s).

Stray Animal Dashboard

  • Configure the required device settings.
  • Once the devices are added, proceed to the ROI Configuration page.

Ensure all required cameras are added before proceeding to ROI configuration.


3. ROI (Region of Interest) Configuration

All added devices will be displayed on this page for ROI configuration.

ROI Configuration

  1. Select the desired device.
  2. Click Add ROI (top right of the page).

Add ROI

Fill in ROI Details

FieldGuidance for Stray Animal Detection
ROI NameEnter a meaningful name for the ROI.
ROI ColorSelect a color for visualization.
ROI TypeSelect Junction.
Lane DirectionSet to None.
ROI ClassesNot required.

You can update or delete any ROI by selecting it and using the available options.


4. Meta Parameters Configuration

After ROI setup, navigate to the Meta Parameters page.

Meta Parameters

4.1 Default vs Custom Configuration

You can either:

  • Use a default configuration, or
  • Create a custom configuration.

Default Configuration Nodes

  • Device
  • Intozi Custom
  • Region of Interest (ROI)
  • Event
  • Alert

Device Node Settings

5. Device Node Settings

Select the required device and configure the following settings.

Duration

  • Defines the time interval (in seconds) after which a new event can be generated for the same device.
  • Configure the value according to project requirements.

Tracker Distance Threshold

  • Used for tracking detected animals across frames.
  • Default value: 200
  • Can be adjusted according to deployment requirements.

The Tracker Distance Threshold helps maintain consistent tracking of animals between consecutive frames.


6. Intozi Custom Node Settings

Confidence Threshold

  • Default value: 0.45
  • Can be adjusted based on:
    • Camera angle
    • Lighting conditions
    • Environmental factors
    • Deployment requirements

Adjust the confidence threshold carefully to balance detection accuracy and false alarms.


7. Final Configuration

After selecting the required device and associated ROI:

  1. Enter a Configuration Name.
  2. Select the hardware type:
    • CPU
    • GPU
  3. Configure the Batch Size if required.

Final Configuration

RGB

ValueDescription
1Enable event generation from RGB cameras
0Disable event generation from RGB cameras

Thermal

ValueDescription
1Enable event generation from thermal cameras
0Disable event generation from thermal cameras

Note

  • Enable the appropriate option based on the camera type being used.
  • Both options can be enabled if the deployment includes both RGB and thermal cameras.

For hybrid deployments, both RGB and Thermal event generation can be enabled simultaneously.


8. Analytics Server Selection

  • Select the appropriate Analytics Server from the available list.
  • Verify all configuration settings before saving.

9. Saving the Configuration

After verifying all settings:

  • Confirm device selection.
  • Verify ROI placement.
  • Review Duration settings.
  • Verify Tracker Distance Threshold.
  • Confirm RGB/Thermal configuration.
  • Review confidence threshold settings.
  • Verify Analytics Server selection.
  • Confirm hardware and batch size configuration.

Click Save Configuration to activate the deployment.


Conclusion

The Stray Animal Detection application provides automated monitoring of animal intrusion within defined areas. It supports both RGB and thermal camera deployments, making it suitable for perimeter protection, railway safety, industrial facilities, and wildlife monitoring applications.

By properly configuring ROI placement, camera source selection, tracking parameters, and confidence thresholds, users can achieve reliable stray animal detection and timely event generation.