Line Crossing
Line Crossing is used to detect and generate events when a person crosses a predefined virtual line. It can be configured to monitor crossings in a specific direction or in both directions.
This guide explains how to configure the Line Crossing application in App Stack.
1. Finding the Line Crossing Application in App Stack
- Open App Stack on the platform.
- Use the search bar (usually at the top right of the dashboard).
- Enter Line Crossing.
- In the results, click once on the application to open it.
2. Device Configuration
After the application opens, you will be directed to the Device Configuration page.
- On the right side of the page, click Add Device to add the required camera(s).
- 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.
- Select the desired device.
- Click Add ROI (top right of the page).
Fill in ROI Details
| Field | Guidance for Line Crossing |
|---|---|
| ROI Name | Enter a meaningful name for the ROI. |
| ROI Color | Select a color for visualization. |
| ROI Type | Select LINE. |
| Lane Direction | Select IN, OUT, or NONE depending on the required monitoring direction. |
| ROI Classes | Not required. |
Lane Direction Explanation
| Direction | Description |
|---|---|
| IN | Generates events when a person crosses into the monitored area. |
| OUT | Generates events when a person exits the monitored area. |
| NONE | Generates events regardless of crossing direction. |
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.
4.1 Default vs Custom Configuration
You can either:
- Use a default configuration, or
- Create a custom configuration.
Default Configuration Nodes
- Device
- People Detection
- Region of Interest (ROI)
- Event
- Alert
5. Device Node Settings
Click on the Device node and select the required camera.
Available Settings
Duplicate
| Value | Description |
|---|---|
| 0 | No duplicate events (recommended for zig-zag movement scenarios). |
| 1 | Allows duplicate event generation. |
IN/OUT Direction
| Value | Description |
|---|---|
| 0 | Generate all crossing events. |
| 1 | Generate only IN events. |
| 2 | Generate only OUT events. |
For most deployments, Duplicate = 0 is recommended to avoid multiple event generations caused by repeated movements near the line.
6. People Detection Node Settings
Confidence Threshold
- Default value: 0.45
- Can be adjusted based on:
- Camera angle
- Lighting conditions
- Scene complexity
- Deployment requirements
Increase the confidence threshold to reduce false detections or decrease it if valid detections are being missed.
7. Final Configuration
After selecting the required device and ROI:
- Configure the required parameters.
- Enter a Configuration Name.
- Select the hardware type:
- CPU
- GPU
- Configure the Batch Size if required.
- Select the required Analytic Server for deployment.
Additional Recommendations
- Use GPU deployment for better performance when processing multiple camera streams.
- Configure batch size based on recommendations from the Development/CV Team.
- Verify ROI placement before saving the configuration.
8. Saving the Configuration
After verifying all settings:
- Confirm device selection.
- Verify ROI placement.
- Review direction settings.
- Review confidence threshold values.
- Confirm hardware selection.
- Verify Analytic Server selection.
Click Save to activate the configuration.
Conclusion
The Line Crossing application provides real-time monitoring of people crossing predefined virtual lines. It can be configured for directional or non-directional event generation, making it suitable for entry/exit monitoring, restricted area surveillance, and perimeter security applications.
By correctly configuring line placement, direction settings, and detection thresholds, users can achieve reliable and accurate line crossing event detection.