🟠 Detection Result Class Selection

Function Description

This operator is used to filter detection results of specific classes from detection instances, facilitating more precise target analysis in subsequent processes.

Usage Scenarios

  • Quickly extract targets of specific classes in multi-class detection scenarios.

  • Subsequent analysis processes focus only on single target classes, such as target statistics, tracking, or classification tasks for specific classes.

  • When the target class is not detected, you can choose whether to use detection instances of other classes as alternative solutions.

Input Output

Input

Detection results: Detection instances output by deep learning models or other detection algorithms, including bounding boxes, classification information, confidence scores, and polygon contours for each target.

Output

Single-class detection results: Filtered detection instances containing only the specified class.

Parameter Description

Class

Parameter Description

Specifies the detection class number to be retained.

Parameter Adjustment

Set to the class number of the target you want to retain. For example, "0" represents retaining detection results with class identifier 0.

Parameter Range

[0,1,2,3,4,5,6,7,8,9]

Use Substitute Class

Parameter Description

Controls whether to use remaining classes for substitute processing when the specified class is not detected.

Parameter Adjustment

  • Enable: Output detection results of all classes when the specified class does not exist.

  • Disable: Return empty detection results when the specified class does not exist.

Enable Node

Parameter Description

Controls whether this operator executes computations.

Parameter Adjustment

  • Enable (default): Normally run this operator’s functionality.

  • Disable: The operator performs no operations and directly outputs the input data.