Detections Combine

Class: DetectionsCombineBlockV1

Source: inference.core.workflows.core_steps.transformations.detections_combine.v1.DetectionsCombineBlockV1

This block combines two sets of predictions into a single set of predictions.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌

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 Combine in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • prediction_one (Union[instance_segmentation_prediction, object_detection_prediction]): First set of predictions..
  • prediction_two (Union[instance_segmentation_prediction, object_detection_prediction]): Second set of predictions..

• output

  • predictions (Union[object_detection_prediction, instance_segmentation_prediction]): Prediction with detected bounding boxes in form of sv.Detections(...) object if object_detection_prediction or Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object if instance_segmentation_prediction.

Example JSON definition of step Detections Combine in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/detections_combine@v1",
    "prediction_one": "$steps.my_object_detection_model.predictions",
    "prediction_two": "$steps.my_object_detection_model.predictions"
}