App Stack
VIDS

Vehicle Incident Detection System (VIDS)

Vehicle Incident Detection System (VIDS) is used to detect and monitor traffic-related incidents such as slow-moving vehicles, stopped vehicles, accidents, and wrong-way vehicle movement. This guide walks through opening the VIDS application in App Stack, configuring devices and ROIs, and setting Meta Parameters for a typical deployment.


1. Finding the VIDS 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 VIDS.
  4. In the results, click once on the application to open it.

VIDS Dashboard


2. Device Configuration

After the application opens, you are taken to the Device Configuration page.

Device Configuration

  • On the right side of the page, use the option to add devices and connect the cameras you need. VIDS Dashboard
  • When finished, continue to the next step (ROI Configuration).

Ensure all required cameras are connected properly before proceeding to ROI configuration.


3. ROI (Region of Interest) Configuration

All devices added during the device configuration step appear here so you can draw ROIs on the correct feeds.

ROI Configuration

  1. Select the device you want to configure.
  2. Click Add ROI (top right of the ROI Configuration page).

Add ROI

In VIDS, ROI types may vary depending on the selected analytics.

  • ROI can be either Line or Junction type.
  • Lane direction depends on the analytics use case.
  • Pair ID is used in some analytics for linking ROIs of the same lane.

4. Analytics Configuration

VIDS supports multiple analytics within a single application.


4.1 Slow Moving

FieldGuidance
ROI NameEnter the name of the ROI.
ROI ColorChoose the color for the ROI.
ROI TypeSelect Line.
Lane DirectionSet to None.
Analytics NameSlow Moving
Pair IDCan be empty
ROI ClassesNot required

Slow Moving ROI Guidelines

  • Two ROI lines are drawn for the same lane.
  • The first ROI is drawn where the vehicle first intersects in the traffic flow.
  • The second ROI is drawn at some distance ahead in the same traffic flow.
  • The distance between these two ROI lines is used in further configuration.

Example:

If there are 2 lanes visible in a camera, then 4 ROI lines will be drawn using the same configuration.

Slow Moving ROI


4.2 Stopped Vehicle

FieldGuidance
ROI NameEnter the name of the ROI.
ROI ColorChoose the color for the ROI.
ROI TypeSelect Junction.
Lane DirectionSet to None.
Analytics NameStopped Vehicle
Pair IDCan be empty
ROI ClassesNot required

Stopped Vehicle ROI


4.3 Accident Detection

FieldGuidance
ROI NameEnter the name of the ROI.
ROI ColorChoose the color for the ROI.
ROI TypeSelect Junction.
Lane DirectionSet to None.
Analytics NameAccident Detection
Pair IDCan be empty
ROI ClassesNot required

Accident Detection ROI


4.4 Wrong Way

FieldGuidance
ROI NameEnter the name of the ROI.
ROI ColorChoose the color for the ROI.
ROI TypeSelect Line.
Lane DirectionConfigure based on traffic flow direction.
Analytics NameWrong Way
Pair IDApplicable
ROI ClassesNot required

Wrong Way ROI Guidelines

  • Two ROI lines are drawn for a single lane.
  • ROIs belonging to the same lane must use the same Pair ID.
  • Lane direction depends on the legal traffic flow direction.
  • If a vehicle moves opposite to the configured direction, the event is captured as a Wrong Way Vehicle event.

Example:

If there are 3 lanes, then 6 ROI lines will be drawn.

Wrong Way ROI


5. Meta Parameters Configuration

After ROI setup, open the Meta Parameters page.

Meta Parameters

5.1 Default vs. Custom Configuration

You can either:

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

A default configuration typically includes these modules in the flow:

  • Device
  • Vehicle Classification or Vehicle Classification Highway
  • Region of Interest (ROI)
  • Event
  • Alert

Vehicle Classification Highway is generally used for highway-based analytics.


6. Device Settings in Device Node

Select the required device and configure the following settings.

Device Settings

Available Settings

Stopped

ValueBehavior
0Stopped vehicle detection disabled
1Enables stopped vehicle detection

Accident Detection

ValueBehavior
0Accident detection disabled
1Enables accident detection

Wrong Way

ValueBehavior
0Wrong-way detection disabled
1Enables wrong-way detection

Speed Threshold

  • Default value: 15
  • Used for slow-moving vehicle analytics.

Slow Moving

ValueBehavior
0Slow-moving detection disabled
1Enables slow-moving detection

Slow Time Threshold

  • Default value: 15 seconds
  • Defines the maximum allowed time between the first and second slow-moving ROI lines.
  • If the vehicle does not cross the second line within the configured duration, it is detected as a slow-moving vehicle.

Stop Time Threshold

  • Default value: 15 seconds
  • Defines the duration a vehicle remains inside the Junction ROI.
  • If the vehicle does not leave the ROI within the configured time, it is detected as a stopped vehicle.

Slow Speed Threshold

  • Default value: 40 km/h
  • Defines the vehicle speed threshold for slow-moving analytics.

Displacement Threshold

  • Default value: 100
  • Recommended to keep at the default value.

SMV Distance

  • Defines the distance between the two slow-moving ROI lines.

Stop Coordinate Buffer Size

  • Default value: 30
  • Recommended to keep at the default setting.

7. Vehicle Classification / Vehicle Classification Highway

Confidence Threshold

  • The default value is 0.45.
  • Can be adjusted based on camera angle, lighting conditions, and deployment scenario.

8. Final Configuration

  1. Select all required devices.
  2. Configure the required device parameters.
  3. Select the corresponding ROIs.
  4. Enter a configuration name.
  5. Select the hardware type (CPU or GPU).
  6. Configure batch size if required.

Final Configuration

Vehicle Top View

ValueBehavior
0Normal camera view
1Highway or top-view camera scenarios

When everything is configured, click Save.


Conclusion

The VIDS application helps automate traffic incident detection using configurable analytics such as slow-moving vehicles, stopped vehicles, accident detection, and wrong-way vehicle monitoring.

By properly configuring devices, ROIs, analytics parameters, and hardware settings, users can achieve accurate and efficient vehicle incident monitoring for real-time traffic management applications.