Dynamic Zone

Class: DynamicZonesBlockV1

Source: inference.core.workflows.core_steps.transformations.dynamic_zones.v1.DynamicZonesBlockV1

The DynamicZoneBlock is a transformer block designed to simplify polygon so it's geometrically convex and then reduce number of vertices to requested amount. This block is best suited when Zone needs to be created based on shape of detected object (i.e. basketball field, road segment, zebra crossing etc.) Input detections should be filtered and contain only desired classes of interest.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
required_number_of_vertices	int	Keep simplifying polygon until number of vertices matches this number.	✅
scale_ratio	float	Expand resulting polygon along imaginary line from centroid to edge by this ratio.	✅
apply_least_squares	bool	Apply least squares algorithm to fit resulting polygon edges to base contour.	✅
midpoint_fraction	float	Fraction of vertices to keep in the middle of each edge before fitting least squares line. This parameter is useful when vertices of convex polygon are not aligned with edge that would be otherwise fitted to points closer to the center of each edge..	✅

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 Dynamic Zone in version v1.

• inputs: Camera Focus, Detections Stitch, Pixel Color Count, Velocity, Instance Segmentation Model, JSON Parser, Email Notification, Line Counter, Time in Zone, Instance Segmentation Model, Time in Zone, Cosine Similarity, Dynamic Crop, Template Matching, VLM as Detector, Bounding Rectangle, Webhook Sink, Image Contours, Identify Outliers, Email Notification, Roboflow Dataset Upload, SAM 3, Detections Filter, Detections Classes Replacement, SIFT Comparison, Distance Measurement, Detections Consensus, SAM 3, Path Deviation, SAM 3, Line Counter, SIFT Comparison, Motion Detection, Roboflow Custom Metadata, Twilio SMS Notification, VLM as Classifier, Perspective Correction, Clip Comparison, Dynamic Zone, VLM as Detector, Seg Preview, VLM as Classifier, Detections Transformation, Segment Anything 2 Model, PTZ Tracking (ONVIF).md), Roboflow Dataset Upload, Detections Stabilizer, Local File Sink, Slack Notification, Path Deviation, Detections Combine, Detection Offset, Model Monitoring Inference Aggregator, Identify Changes, Gaze Detection, Time in Zone
• outputs: Blur Visualization, Line Counter Visualization, Detections Stitch, Velocity, Instance Segmentation Model, Line Counter, Time in Zone, Multi-Label Classification Model, Instance Segmentation Model, Dynamic Crop, Multi-Label Classification Model, Circle Visualization, Webhook Sink, Mask Visualization, Google Gemini, Ellipse Visualization, Single-Label Classification Model, Email Notification, Anthropic Claude, Color Visualization, Keypoint Detection Model, Detections Classes Replacement, Detections Consensus, Llama 3.2 Vision, SAM 3, OpenAI, SAM 3, OpenAI, Line Counter, Florence-2 Model, Trace Visualization, Roboflow Custom Metadata, Twilio SMS Notification, Perspective Correction, Dynamic Zone, VLM as Detector, Grid Visualization, Google Gemini, Detections Transformation, Polygon Zone Visualization, Reference Path Visualization, PTZ Tracking (ONVIF).md), Roboflow Dataset Upload, Stability AI Inpainting, Bounding Box Visualization, Corner Visualization, Polygon Visualization, Detections Merge, Slack Notification, Path Deviation, Detections Combine, Triangle Visualization, Model Monitoring Inference Aggregator, Pixelate Visualization, Icon Visualization, Time in Zone, Overlap Filter, Classification Label Visualization, Background Color Visualization, Keypoint Visualization, Size Measurement, Dot Visualization, Object Detection Model, Email Notification, Crop Visualization, Time in Zone, Object Detection Model, VLM as Detector, LMM For Classification, Florence-2 Model, Template Matching, Bounding Rectangle, Keypoint Detection Model, Single-Label Classification Model, Roboflow Dataset Upload, YOLO-World Model, SAM 3, Halo Visualization, Detections Filter, Model Comparison Visualization, SIFT Comparison, Distance Measurement, Path Deviation, Motion Detection, Byte Tracker, VLM as Classifier, Clip Comparison, Clip Comparison, Cache Set, Seg Preview, VLM as Classifier, Segment Anything 2 Model, Byte Tracker, Buffer, Byte Tracker, Detections Stabilizer, OpenAI, Detection Offset, Anthropic Claude, Label Visualization, Gaze Detection

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Dynamic Zone in version v1 has.

Bindings

• input

  • predictions (instance_segmentation_prediction): .
  • required_number_of_vertices (integer): Keep simplifying polygon until number of vertices matches this number.
  • scale_ratio (float): Expand resulting polygon along imaginary line from centroid to edge by this ratio.
  • apply_least_squares (boolean): Apply least squares algorithm to fit resulting polygon edges to base contour.
  • midpoint_fraction (float_zero_to_one): Fraction of vertices to keep in the middle of each edge before fitting least squares line. This parameter is useful when vertices of convex polygon are not aligned with edge that would be otherwise fitted to points closer to the center of each edge..

• output

  • zones (list_of_values): List of values of any type.
  • predictions (instance_segmentation_prediction): Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object.
  • simplification_converged (boolean): Boolean flag.

Example JSON definition of step Dynamic Zone in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/dynamic_zone@v1",
    "predictions": "$segmentation.predictions",
    "required_number_of_vertices": 4,
    "scale_ratio": 1.05,
    "apply_least_squares": true,
    "midpoint_fraction": 0.9
}