Detections Merge

Class: DetectionsMergeBlockV1

Source: inference.core.workflows.core_steps.transformations.detections_merge.v1.DetectionsMergeBlockV1

The DetectionsMerge block combines multiple detections into a single bounding box that encompasses all input detections. This is useful when you want to: - Merge overlapping or nearby detections of the same object - Create a single region that contains multiple detected objects - Simplify multiple detections into one larger detection

The resulting detection will have: - A bounding box that contains all input detections - The classname of the merged detection is set to "merged_detection" by default, but can be customized via the class_name parameter - The confidence is set to the lowest confidence among all detections

Type identifier

Use the following identifier in step "type" field: roboflow_core/detections_merge@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
class_name	str	The class name to assign to the merged detection..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Detections Merge in version v1.

• inputs: Detection Offset, Moondream2, Path Deviation, VLM as Detector, Detections Classes Replacement, Gaze Detection, Bounding Rectangle, Detections Stitch, Template Matching, Instance Segmentation Model, Byte Tracker, Keypoint Detection Model, Object Detection Model, Path Deviation, Line Counter, Detections Stabilizer, Detections Transformation, Byte Tracker, Google Vision OCR, Dynamic Zone, Perspective Correction, Object Detection Model, Detections Filter, Instance Segmentation Model, YOLO-World Model, VLM as Detector, Detections Merge, Velocity, Segment Anything 2 Model, Time in Zone, Time in Zone, Keypoint Detection Model, Overlap Filter, Byte Tracker, Dynamic Crop, Detections Consensus
• outputs: Size Measurement, Detection Offset, Roboflow Custom Metadata, Path Deviation, Florence-2 Model, Distance Measurement, Label Visualization, Detections Classes Replacement, Background Color Visualization, Detections Stitch, Byte Tracker, Triangle Visualization, Path Deviation, Line Counter, Detections Stabilizer, Detections Transformation, Byte Tracker, Stitch OCR Detections, Roboflow Dataset Upload, Bounding Box Visualization, Perspective Correction, Ellipse Visualization, Color Visualization, Crop Visualization, Dot Visualization, Pixelate Visualization, Detections Filter, Model Comparison Visualization, Detections Merge, Velocity, Overlap Filter, Roboflow Dataset Upload, Segment Anything 2 Model, Time in Zone, Line Counter, Time in Zone, Trace Visualization, Corner Visualization, Blur Visualization, Model Monitoring Inference Aggregator, Florence-2 Model, Circle Visualization, Byte Tracker, Dynamic Crop, Detections Consensus

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Detections Merge in version v1 has.

Bindings

• input

  • predictions (Union[instance_segmentation_prediction, object_detection_prediction, keypoint_detection_prediction]): Object detection predictions to merge into a single bounding box..

• output

  • predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.

Example JSON definition of step Detections Merge in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/detections_merge@v1",
    "predictions": "$steps.object_detection_model.predictions",
    "class_name": "<block_does_not_provide_example>"
}