Detection Offset

Class: DetectionOffsetBlockV1

Source: inference.core.workflows.core_steps.transformations.detection_offset.v1.DetectionOffsetBlockV1

Apply a fixed offset to the width and height of a detection.

You can use this block to add padding around the result of a detection. This is useful to ensure that you can analyze bounding boxes that may be within the region of an object instead of being around an object.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
offset_width	int	Offset for box width..	✅
offset_height	int	Offset for box height..	✅
units	str	Units for offset dimensions..	❌

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 Detection Offset in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Detection Offset in version v1 has.

Bindings

• input

  • predictions (Union[keypoint_detection_prediction, instance_segmentation_prediction, object_detection_prediction]): Model predictions to offset dimensions for..
  • offset_width (integer): Offset for box width..
  • offset_height (integer): Offset for box height..

• output

  • predictions (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_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 or Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object if keypoint_detection_prediction.

Example JSON definition of step Detection Offset in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/detection_offset@v1",
    "predictions": "$steps.object_detection_model.predictions",
    "offset_width": 10,
    "offset_height": 10,
    "units": "Pixels"
}