Detections Stitch

Class: DetectionsStitchBlockV1

Source: inference.core.workflows.core_steps.fusion.detections_stitch.v1.DetectionsStitchBlockV1

This block merges detections that were inferred for multiple sub-parts of the same input image into single detection.

Block may be helpful in the following scenarios: * to apply Slicing Adaptive Inference (SAHI) technique, as a final step of procedure, which involves Image Slicer block and model block at previous stages. * to merge together detections performed by precise, high-resolution model applied as secondary model after coarse detection is performed in the first stage and Dynamic Crop is applied later.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
overlap_filtering_strategy	str	Which strategy to employ when filtering overlapping boxes. None does nothing, NMS discards lower-confidence detections, NMM combines them..	✅
iou_threshold	float	Minimum overlap threshold between boxes. If intersection over union (IoU) is above this ratio, discard or merge the lower confidence box..	✅

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 Stitch in version v1.

• inputs: Image Contours, Line Counter, Stability AI Inpainting, Detections Consensus, Corner Visualization, Time in Zone, CSV Formatter, Google Gemini, Line Counter Visualization, Reference Path Visualization, Keypoint Detection Model, Model Monitoring Inference Aggregator, Florence-2 Model, YOLO-World Model, Circle Visualization, OCR Model, Llama 3.2 Vision, Relative Static Crop, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Dynamic Zone, Detections Classes Replacement, Image Convert Grayscale, Byte Tracker, Pixelate Visualization, Object Detection Model, Model Comparison Visualization, Trace Visualization, Detections Stitch, Path Deviation, Velocity, LMM, Twilio SMS Notification, Bounding Rectangle, Roboflow Dataset Upload, Depth Estimation, Label Visualization, Classification Label Visualization, Blur Visualization, OpenAI, Color Visualization, Moondream2, Bounding Box Visualization, Template Matching, Anthropic Claude, Ellipse Visualization, Detection Offset, Instance Segmentation Model, Polygon Zone Visualization, Detections Transformation, Object Detection Model, Roboflow Custom Metadata, Image Slicer, Image Slicer, VLM as Detector, Email Notification, Crop Visualization, Perspective Correction, Halo Visualization, Dot Visualization, Mask Visualization, Keypoint Visualization, Detections Stabilizer, Local File Sink, Absolute Static Crop, Stitch OCR Detections, Image Blur, OpenAI, VLM as Classifier, Path Deviation, Clip Comparison, Byte Tracker, Detections Merge, Identify Changes, Instance Segmentation Model, Overlap Filter, Triangle Visualization, Segment Anything 2 Model, Background Color Visualization, SIFT Comparison, Google Vision OCR, Camera Calibration, Florence-2 Model, Image Threshold, Single-Label Classification Model, Image Preprocessing, OpenAI, CogVLM, Slack Notification, VLM as Detector, Stability AI Image Generation, SIFT, Grid Visualization, Camera Focus, Stitch Images, Stability AI Outpainting, Identify Outliers, Polygon Visualization, Multi-Label Classification Model, Webhook Sink, Dynamic Crop, Time in Zone, Byte Tracker, Detections Filter, LMM For Classification
• outputs: Line Counter, Stability AI Inpainting, Detections Consensus, Corner Visualization, Mask Visualization, Time in Zone, Detections Stabilizer, Model Monitoring Inference Aggregator, Florence-2 Model, Circle Visualization, Line Counter, Stitch OCR Detections, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Path Deviation, Dynamic Zone, Byte Tracker, Detections Classes Replacement, Detections Merge, Byte Tracker, Pixelate Visualization, Model Comparison Visualization, Distance Measurement, Detections Stitch, Trace Visualization, Overlap Filter, Path Deviation, Velocity, Segment Anything 2 Model, Roboflow Dataset Upload, Bounding Rectangle, Triangle Visualization, Background Color Visualization, Florence-2 Model, Label Visualization, Blur Visualization, Color Visualization, Bounding Box Visualization, Detection Offset, Ellipse Visualization, Detections Transformation, Halo Visualization, Roboflow Custom Metadata, Size Measurement, Polygon Visualization, Time in Zone, Byte Tracker, Dynamic Crop, Crop Visualization, Detections Filter, Perspective Correction, Dot Visualization

Input and Output Bindings

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

Bindings

• input

  • reference_image (image): Original image that was cropped to produce the predictions..
  • predictions (Union[object_detection_prediction, instance_segmentation_prediction]): Model predictions to be merged into the original image..
  • overlap_filtering_strategy (string): Which strategy to employ when filtering overlapping boxes. None does nothing, NMS discards lower-confidence detections, NMM combines them..
  • iou_threshold (float_zero_to_one): Minimum overlap threshold between boxes. If intersection over union (IoU) is above this ratio, discard or merge the lower confidence box..

• 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 Stitch in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/detections_stitch@v1",
    "reference_image": "$inputs.image",
    "predictions": "$steps.my_object_detection_model.predictions",
    "overlap_filtering_strategy": "nms",
    "iou_threshold": 0.4
}