Ellipse Visualization¶
Class: EllipseVisualizationBlockV1
Source: inference.core.workflows.core_steps.visualizations.ellipse.v1.EllipseVisualizationBlockV1
Draw elliptical outlines around detected objects, providing oval-shaped annotations that can be customized to full ellipses or partial arcs, offering more flexible geometry than circular visualizations.
How This Block Works¶
This block takes an image and detection predictions and draws elliptical (oval-shaped) outlines around each detected object. The block:
- Takes an image and predictions as input
- Identifies bounding box coordinates for each detected object
- Calculates the center point and dimensions (width and height) for each detection based on its bounding box
- Applies color styling based on the selected color palette, with colors assigned by class, index, or track ID
- Draws elliptical outlines around each detected object using Supervision's EllipseAnnotator
- Applies the specified thickness to control the line width of the elliptical outlines
- Uses start and end angle parameters to draw either full ellipses or partial elliptical arcs
- Returns an annotated image with elliptical outlines overlaid on the original image
The block draws ellipses that are typically fitted to each detection's bounding box, creating oval-shaped outlines that adapt to the object's aspect ratio (unlike circles which are always round). Ellipses provide more flexible geometry than circles, as they can represent both round and elongated objects more accurately. The start and end angle parameters allow you to draw full ellipses (360 degrees) or partial arcs, providing additional visual style options. Unlike circle visualization (which always draws complete circles), ellipse visualization can draw partial arcs, creating distinctive visual markers while still clearly indicating object locations.
Common Use Cases¶
- Oval and Elongated Object Highlighting: Highlight detected objects with elliptical outlines when objects are oval-shaped or elongated (e.g., vehicles, elongated products, elliptical objects) where ellipses provide a better fit than circular or rectangular shapes
- Flexible Geometric Visualization: Use elliptical shapes as a more geometrically flexible alternative to circles or bounding boxes, adapting to object aspect ratios for more accurate visual representation
- Partial Arc Annotations: Draw partial elliptical arcs (using start and end angles) to create distinctive, stylized visual markers that indicate object locations with a unique visual style
- Aesthetic Visualization Alternatives: Create visually distinct annotations compared to standard bounding boxes or circles for design purposes, artistic visualizations, or when elliptical shapes better match design aesthetics
- Object Shape Adaptation: Use ellipses when objects have non-square aspect ratios where circular outlines would be less accurate, providing better visual fit for rectangular or elongated objects
- Design and UI Applications: Integrate elliptical outlines into user interfaces, dashboards, or interactive applications where oval shapes provide a softer, more organic visual style than angular rectangles
Connecting to Other Blocks¶
The annotated image from this block can be connected to:
- Other visualization blocks (e.g., Label Visualization, Dot Visualization, Bounding Box Visualization) to combine elliptical outlines with additional annotations for comprehensive visualization
- Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save annotated images with elliptical outlines for documentation, reporting, or analysis
- Webhook blocks to send visualized results with elliptical outlines 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 elliptical outlines as visual evidence in alerts or reports
- Video output blocks to create annotated video streams or recordings with elliptical outlines for live monitoring, tracking visualization, or post-processing analysis
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/ellipse_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.. | ✅ |
color_palette |
str |
Select a color palette for the visualised elements.. | ✅ |
palette_size |
int |
Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes.. | ✅ |
custom_colors |
List[str] |
Define a list of custom colors for bounding boxes in HEX format.. | ✅ |
color_axis |
str |
Choose how bounding box colors are assigned.. | ✅ |
thickness |
int |
Thickness of the ellipse outline in pixels. Higher values create thicker, more visible elliptical outlines.. | ✅ |
start_angle |
int |
Starting angle for drawing the ellipse arc in degrees. Used together with end_angle to control whether a full ellipse (360 degrees) or partial arc is drawn. Angles are measured from the positive x-axis (0 degrees = right, 90 degrees = down, 180 degrees = left, 270 degrees = up).. | ✅ |
end_angle |
int |
Ending angle for drawing the ellipse arc in degrees. Used together with start_angle to control whether a full ellipse (360 degrees) or partial arc is drawn. To draw a full ellipse, set end_angle = start_angle + 360 (or equivalent). Angles are measured from the positive x-axis (0 degrees = right, 90 degrees = down, 180 degrees = left, 270 degrees = up).. | ✅ |
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 Ellipse Visualization in version v1.
- inputs:
Roboflow Dataset Upload,Line Counter Visualization,Mask Edge Snap,OCR Model,Image Slicer,Gaze Detection,Instance Segmentation Model,Distance Measurement,Color Visualization,Bounding Rectangle,Ellipse Visualization,Polygon Visualization,ByteTrack Tracker,Relative Static Crop,Byte Tracker,Detections Consensus,Detections Classes Replacement,Webhook Sink,Trace Visualization,Object Detection Model,Camera Focus,Stitch OCR Detections,Qwen 3.5 API,OpenAI,Buffer,SAM 3,Size Measurement,Image Threshold,Heatmap Visualization,SORT Tracker,Florence-2 Model,Halo Visualization,Detections Transformation,Path Deviation,GLM-OCR,Dot Visualization,S3 Sink,Path Deviation,Twilio SMS Notification,Seg Preview,Model Monitoring Inference Aggregator,Google Gemini,Roboflow Dataset Upload,Dynamic Zone,Clip Comparison,VLM As Classifier,Pixelate Visualization,Line Counter,Twilio SMS/MMS Notification,Polygon Zone Visualization,Motion Detection,Blur Visualization,Background Subtraction,Text Display,CSV Formatter,Stability AI Image Generation,Detections Merge,Perspective Correction,Overlap Filter,Anthropic Claude,Bounding Box Visualization,Velocity,Depth Estimation,Line Counter,Stability AI Inpainting,Polygon Visualization,SIFT,Roboflow Vision Events,VLM As Detector,Google Gemini,Label Visualization,Grid Visualization,Qwen3.5-VL,Contrast Equalization,Per-Class Confidence Filter,Triangle Visualization,Halo Visualization,Circle Visualization,Segment Anything 2 Model,Mask Visualization,OpenAI,MoonshotAI Kimi,Llama 3.2 Vision,Email Notification,Slack Notification,Detections Stitch,Detections Stabilizer,Object Detection Model,Stability AI Outpainting,Email Notification,Google Gemma API,Google Vision OCR,Identify Outliers,Image Preprocessing,Google Gemini,EasyOCR,Detections Combine,Object Detection Model,SAM2 Video Tracker,Detection Event Log,Byte Tracker,OpenAI,Anthropic Claude,Time in Zone,Model Comparison Visualization,Roboflow Custom Metadata,YOLO-World Model,Detection Offset,Instance Segmentation Model,Single-Label Classification Model,VLM As Classifier,Detections List Roll-Up,Template Matching,Mask Area Measurement,Stitch Images,Qwen 3.6 API,SIFT Comparison,Morphological Transformation,Instance Segmentation Model,CogVLM,Crop Visualization,Camera Calibration,Florence-2 Model,Time in Zone,OC-SORT Tracker,SAM 3,Icon Visualization,Local File Sink,Detections Filter,Image Contours,JSON Parser,Keypoint Detection Model,Time in Zone,Reference Path Visualization,Dimension Collapse,Anthropic Claude,Clip Comparison,VLM As Detector,LMM,Pixel Color Count,Identify Changes,Classification Label Visualization,Image Slicer,Absolute Static Crop,Image Blur,Byte Tracker,Multi-Label Classification Model,Image Convert Grayscale,SAM 3,OpenAI,Corner Visualization,Dynamic Crop,Moondream2,Keypoint Visualization,Keypoint Detection Model,QR Code Generator,Camera Focus,LMM For Classification,Morphological Transformation,Keypoint Detection Model,Contrast Enhancement,Background Color Visualization,PTZ Tracking (ONVIF),Stitch OCR Detections,SIFT Comparison - outputs:
Roboflow Dataset Upload,Line Counter Visualization,Mask Edge Snap,OCR Model,Image Slicer,Gaze Detection,Qwen2.5-VL,Instance Segmentation Model,Color Visualization,Multi-Label Classification Model,Ellipse Visualization,Polygon Visualization,ByteTrack Tracker,Single-Label Classification Model,Relative Static Crop,Barcode Detection,Trace Visualization,Object Detection Model,Qwen 3.5 API,Camera Focus,OpenAI,Buffer,SAM 3,Image Threshold,Heatmap Visualization,SORT Tracker,Florence-2 Model,Halo Visualization,GLM-OCR,Dot Visualization,Semantic Segmentation Model,Seg Preview,Google Gemini,Roboflow Dataset Upload,Clip Comparison,VLM As Classifier,Pixelate Visualization,Twilio SMS/MMS Notification,Polygon Zone Visualization,Motion Detection,Blur Visualization,Background Subtraction,Text Display,Stability AI Image Generation,Perspective Correction,Anthropic Claude,Bounding Box Visualization,Depth Estimation,Stability AI Inpainting,Polygon Visualization,SmolVLM2,SIFT,Roboflow Vision Events,VLM As Detector,Google Gemini,Label Visualization,Qwen3.5-VL,Contrast Equalization,Triangle Visualization,Halo Visualization,Circle Visualization,Segment Anything 2 Model,Mask Visualization,Dominant Color,OpenAI,MoonshotAI Kimi,Llama 3.2 Vision,Email Notification,CLIP Embedding Model,Detections Stabilizer,Detections Stitch,Object Detection Model,Stability AI Outpainting,Google Gemma API,Google Vision OCR,Google Gemini,Image Preprocessing,EasyOCR,Object Detection Model,OpenAI,SAM2 Video Tracker,Byte Tracker,Anthropic Claude,Qwen3-VL,Model Comparison Visualization,YOLO-World Model,Instance Segmentation Model,Perception Encoder Embedding Model,Semantic Segmentation Model,Single-Label Classification Model,VLM As Classifier,Template Matching,Stitch Images,Qwen 3.6 API,SIFT Comparison,Morphological Transformation,Instance Segmentation Model,CogVLM,Crop Visualization,Florence-2 Model,Camera Calibration,Multi-Label Classification Model,Time in Zone,OC-SORT Tracker,SAM 3,QR Code Detection,Icon Visualization,Image Contours,Keypoint Detection Model,Reference Path Visualization,Anthropic Claude,Clip Comparison,VLM As Detector,LMM,Pixel Color Count,Multi-Label Classification Model,Image Slicer,Absolute Static Crop,Classification Label Visualization,Image Blur,Image Convert Grayscale,SAM 3,Single-Label Classification Model,OpenAI,Corner Visualization,Dynamic Crop,Keypoint Detection Model,Moondream2,Keypoint Visualization,Camera Focus,LMM For Classification,Morphological Transformation,Keypoint Detection Model,Contrast Enhancement,Background Color Visualization
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Ellipse 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..predictions(Union[object_detection_prediction,rle_instance_segmentation_prediction,keypoint_detection_prediction,instance_segmentation_prediction]): Model predictions to visualize..color_palette(string): Select a color palette for the visualised elements..palette_size(integer): Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes..custom_colors(list_of_values): Define a list of custom colors for bounding boxes in HEX format..color_axis(string): Choose how bounding box colors are assigned..thickness(integer): Thickness of the ellipse outline in pixels. Higher values create thicker, more visible elliptical outlines..start_angle(integer): Starting angle for drawing the ellipse arc in degrees. Used together with end_angle to control whether a full ellipse (360 degrees) or partial arc is drawn. Angles are measured from the positive x-axis (0 degrees = right, 90 degrees = down, 180 degrees = left, 270 degrees = up)..end_angle(integer): Ending angle for drawing the ellipse arc in degrees. Used together with start_angle to control whether a full ellipse (360 degrees) or partial arc is drawn. To draw a full ellipse, set end_angle = start_angle + 360 (or equivalent). Angles are measured from the positive x-axis (0 degrees = right, 90 degrees = down, 180 degrees = left, 270 degrees = up)..
-
output
image(image): Image in workflows.
Example JSON definition of step Ellipse Visualization in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/ellipse_visualization@v1",
"image": "$inputs.image",
"copy_image": true,
"predictions": "$steps.object_detection_model.predictions",
"color_palette": "DEFAULT",
"palette_size": 10,
"custom_colors": [
"#FF0000",
"#00FF00",
"#0000FF"
],
"color_axis": "CLASS",
"thickness": 2,
"start_angle": -45,
"end_angle": 235
}