Polygon Zone Visualization¶
Class: PolygonZoneVisualizationBlockV1
Source: inference.core.workflows.core_steps.visualizations.polygon_zone.v1.PolygonZoneVisualizationBlockV1
Draw polygon zones on an image to visualize monitoring areas, displaying colored polygon overlays for zone-based detection and counting workflows that track objects within irregular, custom-defined regions.
How This Block Works¶
This block takes an image and polygon zone coordinates (a list of points defining a polygon shape) and draws a filled polygon overlay to visualize the monitoring zone. The block:
- Takes an image and polygon zone coordinates (a list of points: [(x1, y1), (x2, y2), (x3, y3), ...]) as input
- Creates a filled polygon mask from the zone coordinates using the specified color
- Overlays the filled polygon onto the image with the specified opacity, creating a semi-transparent zone visualization
- Returns an annotated image with the polygon zone overlay on the original image
The block visualizes polygon zones used to define irregular monitoring areas for detection, counting, or tracking workflows. The polygon is drawn as a filled shape between the specified points, creating a closed region that can represent any custom area shape (unlike rectangular bounding boxes). This allows for flexible zone definitions that match real-world boundaries, such as specific floor areas, irregular regions of interest, or complex monitoring zones. The zone overlay is semi-transparent, allowing the underlying image details to remain visible while clearly indicating the monitoring area. Note: This block should typically be placed before other visualization blocks in the workflow, as the polygon zone provides a background reference layer for object detection visualizations.
Common Use Cases¶
- Zone Detection Visualization: Visualize polygon zones for object detection or counting workflows where objects are tracked within irregular, custom-defined areas, displaying the monitoring boundaries clearly
- Area-Based Monitoring: Display polygon zones for area-based monitoring applications such as occupancy tracking, people counting in specific regions, or object presence detection within defined spaces
- Custom Region Visualization: Visualize custom monitoring regions that don't fit rectangular boundaries, such as irregular floor areas, complex room layouts, or specific zones within larger spaces
- Security and Surveillance: Display polygon zones for security monitoring, access control, or surveillance workflows where specific areas need to be visually marked and monitored
- Retail and Business Analytics: Visualize polygon zones for foot traffic analysis, customer movement tracking, or space utilization monitoring in retail, hospitality, or business intelligence applications
- Real-Time Zone Monitoring: Create visual overlays for real-time monitoring dashboards, live video feeds, or monitoring interfaces where polygon zones need to be clearly visible to indicate monitored areas
Connecting to Other Blocks¶
The annotated image from this block can be connected to:
- Zone detection or counting blocks to receive polygon zone coordinates that are visualized
- Other visualization blocks (e.g., Bounding Box Visualization, Label Visualization, Polygon Visualization) to add object detection annotations on top of the polygon zone visualization
- Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save images with polygon zone visualizations for documentation, reporting, or analysis
- Webhook blocks to send visualized results with polygon zones to external systems, APIs, or web applications for display in dashboards or monitoring tools
- Notification blocks (e.g., Email Notification, Slack Notification) to send annotated images with polygon zones as visual evidence in alerts or reports
- Video output blocks to create annotated video streams or recordings with polygon zone visualizations for live monitoring, zone visualization, or post-processing analysis
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/polygon_zone_visualization@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
copy_image |
bool |
Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations.. | ✅ |
zone |
List[Any] |
Polygon zone coordinates in the format [[(x1, y1), (x2, y2), (x3, y3), ...], ...] defining one or more polygon shapes. Each zone must consist of more than 2 points to form a valid polygon. The polygon is drawn as a filled shape connecting these points in order, creating a closed region. Typically connected from zone detection or counting blocks that define monitoring areas.. | ✅ |
color |
str |
Color of the polygon zone overlay. Can be specified as a color name (e.g., 'WHITE', 'RED'), hex color code (e.g., '#5bb573', '#FFFFFF'), or RGB format (e.g., 'rgb(255, 255, 255)'). The polygon is filled with this color and overlaid with the specified opacity.. | ✅ |
opacity |
float |
Opacity of the polygon zone overlay, ranging from 0.0 (fully transparent) to 1.0 (fully opaque). Controls how transparent the polygon zone appears over the image. Lower values create more transparent zones that blend with the background, while higher values create more opaque, visible zones. Typical values range from 0.2 to 0.5 for balanced visibility where both the zone and underlying image are visible.. | ✅ |
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 Polygon Zone Visualization in version v1.
- inputs:
Email Notification,Contrast Equalization,PTZ Tracking (ONVIF),Instance Segmentation Model,Google Vision OCR,Grid Visualization,S3 Sink,Stability AI Image Generation,Model Comparison Visualization,Identify Changes,Absolute Static Crop,Keypoint Visualization,SIFT,Trace Visualization,Roboflow Dataset Upload,Twilio SMS/MMS Notification,QR Code Generator,Buffer,Model Monitoring Inference Aggregator,GLM-OCR,Reference Path Visualization,Halo Visualization,OCR Model,SIFT Comparison,VLM As Classifier,VLM As Detector,Image Preprocessing,Crop Visualization,OpenAI,Identify Outliers,Label Visualization,Classification Label Visualization,Pixelate Visualization,Local File Sink,Twilio SMS Notification,Email Notification,OpenAI,Qwen3.5-VL,Stitch OCR Detections,Corner Visualization,Stitch Images,Background Subtraction,Stitch OCR Detections,LMM For Classification,EasyOCR,Morphological Transformation,CSV Formatter,OpenAI,Clip Comparison,Image Threshold,Background Color Visualization,Anthropic Claude,Google Gemini,Camera Calibration,Halo Visualization,Stability AI Outpainting,Roboflow Custom Metadata,CogVLM,OpenAI,Single-Label Classification Model,Ellipse Visualization,Dynamic Zone,VLM As Classifier,Heatmap Visualization,Image Convert Grayscale,Detections Consensus,Triangle Visualization,Image Blur,Depth Estimation,Size Measurement,Dimension Collapse,Color Visualization,SIFT Comparison,Camera Focus,Text Display,Anthropic Claude,Dot Visualization,Image Slicer,Keypoint Detection Model,Polygon Visualization,Florence-2 Model,Motion Detection,Circle Visualization,Blur Visualization,Multi-Label Classification Model,Google Gemini,LMM,Slack Notification,Icon Visualization,Detections List Roll-Up,Camera Focus,Stability AI Inpainting,Polygon Visualization,Webhook Sink,Polygon Zone Visualization,Perspective Correction,Florence-2 Model,Anthropic Claude,Mask Visualization,Google Gemini,Image Contours,Dynamic Crop,Roboflow Dataset Upload,Clip Comparison,Llama 3.2 Vision,JSON Parser,VLM As Detector,Object Detection Model,Image Slicer,Line Counter Visualization,Relative Static Crop,Bounding Box Visualization - outputs:
Dominant Color,Email Notification,Instance Segmentation Model,ByteTrack Tracker,Google Vision OCR,Contrast Equalization,Stability AI Image Generation,Model Comparison Visualization,Absolute Static Crop,Keypoint Visualization,Trace Visualization,SIFT,Roboflow Dataset Upload,Twilio SMS/MMS Notification,CLIP Embedding Model,Buffer,SAM 3,GLM-OCR,Reference Path Visualization,Halo Visualization,OCR Model,SIFT Comparison,VLM As Classifier,Time in Zone,Detections Stabilizer,VLM As Detector,Image Preprocessing,SORT Tracker,Perception Encoder Embedding Model,Crop Visualization,OpenAI,OpenAI,Label Visualization,Pixelate Visualization,Classification Label Visualization,Qwen3.5-VL,Corner Visualization,Stitch Images,Background Subtraction,LMM For Classification,EasyOCR,Morphological Transformation,Qwen2.5-VL,SAM 3,OpenAI,Clip Comparison,Single-Label Classification Model,Background Color Visualization,Anthropic Claude,Image Threshold,Google Gemini,Camera Calibration,Stability AI Outpainting,Halo Visualization,CogVLM,OpenAI,Single-Label Classification Model,Ellipse Visualization,Detections Stitch,VLM As Classifier,Heatmap Visualization,Image Convert Grayscale,Triangle Visualization,Semantic Segmentation Model,Image Blur,Depth Estimation,Barcode Detection,Color Visualization,Camera Focus,Text Display,Anthropic Claude,Dot Visualization,Image Slicer,SmolVLM2,SAM 3,Template Matching,Keypoint Detection Model,Polygon Visualization,Florence-2 Model,Motion Detection,Circle Visualization,Blur Visualization,Qwen3-VL,Multi-Label Classification Model,Google Gemini,LMM,Icon Visualization,Camera Focus,Stability AI Inpainting,Polygon Visualization,Polygon Zone Visualization,Florence-2 Model,Gaze Detection,Perspective Correction,Anthropic Claude,Instance Segmentation Model,Mask Visualization,Moondream2,QR Code Detection,Google Gemini,Image Contours,Clip Comparison,YOLO-World Model,Dynamic Crop,Roboflow Dataset Upload,Llama 3.2 Vision,Seg Preview,Keypoint Detection Model,Object Detection Model,Pixel Color Count,VLM As Detector,Object Detection Model,Image Slicer,Byte Tracker,Line Counter Visualization,Relative Static Crop,Multi-Label Classification Model,OC-SORT Tracker,Bounding Box Visualization,Segment Anything 2 Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Polygon Zone Visualization in version v1 has.
Bindings
-
input
image(image): The image to visualize on..copy_image(boolean): Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..zone(list_of_values): Polygon zone coordinates in the format [[(x1, y1), (x2, y2), (x3, y3), ...], ...] defining one or more polygon shapes. Each zone must consist of more than 2 points to form a valid polygon. The polygon is drawn as a filled shape connecting these points in order, creating a closed region. Typically connected from zone detection or counting blocks that define monitoring areas..color(string): Color of the polygon zone overlay. Can be specified as a color name (e.g., 'WHITE', 'RED'), hex color code (e.g., '#5bb573', '#FFFFFF'), or RGB format (e.g., 'rgb(255, 255, 255)'). The polygon is filled with this color and overlaid with the specified opacity..opacity(float_zero_to_one): Opacity of the polygon zone overlay, ranging from 0.0 (fully transparent) to 1.0 (fully opaque). Controls how transparent the polygon zone appears over the image. Lower values create more transparent zones that blend with the background, while higher values create more opaque, visible zones. Typical values range from 0.2 to 0.5 for balanced visibility where both the zone and underlying image are visible..
-
output
image(image): Image in workflows.
Example JSON definition of step Polygon Zone Visualization in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/polygon_zone_visualization@v1",
"image": "$inputs.image",
"copy_image": true,
"zone": "$inputs.zones",
"color": "WHITE",
"opacity": 0.3
}