Corner Visualization

Class: CornerVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.corner.v1.CornerVisualizationBlockV1

Draw corner markers at the four corners of detected object bounding boxes, providing a minimal, clean visualization style that marks object locations without full bounding box outlines.

How This Block Works

This block takes an image and detection predictions and draws corner markers at the four corners of each detected object's bounding box. The block:

1. Takes an image and predictions as input
2. Identifies bounding box coordinates for each detected object
3. Calculates the four corner positions (top-left, top-right, bottom-left, bottom-right) of each bounding box
4. Applies color styling based on the selected color palette, with colors assigned by class, index, or track ID
5. Draws corner markers (typically L-shaped lines or corner indicators) at each corner position using Supervision's BoxCornerAnnotator
6. Applies the specified thickness and corner length to control the appearance of the corner markers
7. Returns an annotated image with corner markers overlaid on the original image

The block draws minimal corner markers instead of full bounding boxes, creating a clean, unobtrusive visualization style. This approach marks object locations clearly while maintaining a minimal aesthetic that doesn't overwhelm the image with full rectangular outlines. The corner markers can be customized with different thickness and length values, and colors can be assigned based on object class, index, or tracking ID, making it easy to distinguish between different objects or object types.

Common Use Cases

• Minimal Object Marking: Mark detected objects with corner indicators instead of full bounding boxes for a clean, unobtrusive visualization style that preserves image clarity while still indicating object locations
• Aesthetic Visualization Design: Create visually minimal annotations for presentations, dashboards, or user interfaces where full bounding boxes would be too visually intrusive but corner markers provide sufficient location indication
• Dense Scene Visualization: Use corner markers when working with many detected objects in dense scenes where full bounding boxes would overlap excessively and create visual clutter
• Design-Oriented Applications: Apply corner markers in design workflows, artistic visualizations, or creative applications where a minimal, modern aesthetic is preferred over traditional bounding box outlines
• Subtle Object Highlighting: Mark object locations subtly without drawing attention away from the main image content, useful for background annotations or when object location indication is needed without visual prominence
• UI and Dashboard Integration: Integrate corner markers into user interfaces, dashboards, or interactive applications where minimal visual indicators are preferred for better user experience and reduced visual noise

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 corner markers with additional annotations for comprehensive visualization
• Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save annotated images with corner markers for documentation, reporting, or analysis
• Webhook blocks to send visualized results with corner markers 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 corner markers as visual evidence in alerts or reports
• Video output blocks to create annotated video streams or recordings with corner markers for live monitoring, tracking visualization, or post-processing analysis

Type identifier

Use the following identifier in step "type" field: roboflow_core/corner_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 corner marker lines in pixels. Higher values create thicker, more visible corner markers..	✅
corner_length	int	Length of each corner marker line segment in pixels. This controls how long the corner indicators extend from each corner point. Higher values create longer, more prominent corner markers..	✅

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 Corner Visualization in version v1.

• inputs: Clip Comparison, Morphological Transformation, Motion Detection, Email Notification, Detections Stitch, Anthropic Claude, Detections Merge, Pixel Color Count, Keypoint Detection Model, Reference Path Visualization, Stitch OCR Detections, Camera Focus, Stability AI Image Generation, Stitch Images, Stability AI Outpainting, Time in Zone, Bounding Rectangle, Roboflow Dataset Upload, Depth Estimation, Detections Transformation, CogVLM, Identify Outliers, JSON Parser, Local File Sink, SAM 3, Dynamic Crop, Time in Zone, Moondream2, Dot Visualization, Triangle Visualization, Crop Visualization, PTZ Tracking (ONVIF).md), Twilio SMS Notification, Perspective Correction, Twilio SMS/MMS Notification, EasyOCR, Dimension Collapse, Pixelate Visualization, Detections Consensus, OpenAI, Roboflow Dataset Upload, Buffer, Object Detection Model, Single-Label Classification Model, SIFT Comparison, Contrast Equalization, Byte Tracker, Halo Visualization, Model Comparison Visualization, Slack Notification, Byte Tracker, Dynamic Zone, Image Contours, Background Color Visualization, Image Blur, Mask Visualization, Google Vision OCR, Color Visualization, Corner Visualization, Path Deviation, Clip Comparison, Template Matching, Line Counter Visualization, Ellipse Visualization, Icon Visualization, Velocity, Image Slicer, Detections Stabilizer, Absolute Static Crop, Stability AI Inpainting, SAM 3, Distance Measurement, Relative Static Crop, SIFT, CSV Formatter, Detections Filter, Blur Visualization, Instance Segmentation Model, Florence-2 Model, Google Gemini, LMM, Instance Segmentation Model, Polygon Zone Visualization, Keypoint Visualization, Roboflow Custom Metadata, Camera Focus, Multi-Label Classification Model, Detection Offset, Image Threshold, LMM For Classification, Anthropic Claude, Email Notification, Gaze Detection, Overlap Filter, Image Slicer, OpenAI, Detection Event Log, YOLO-World Model, Google Gemini, Image Preprocessing, VLM as Detector, Florence-2 Model, Image Convert Grayscale, Time in Zone, Byte Tracker, OCR Model, Seg Preview, Path Deviation, SAM 3, Detections List Roll-Up, Grid Visualization, Google Gemini, Object Detection Model, Line Counter, Trace Visualization, QR Code Generator, Camera Calibration, Webhook Sink, VLM as Detector, Background Subtraction, Bounding Box Visualization, Label Visualization, OpenAI, Circle Visualization, VLM as Classifier, Size Measurement, Llama 3.2 Vision, Classification Label Visualization, Detections Combine, Segment Anything 2 Model, OpenAI, Detections Classes Replacement, Model Monitoring Inference Aggregator, Line Counter, VLM as Classifier, Polygon Visualization, SIFT Comparison, Keypoint Detection Model, Identify Changes, Text Display
• outputs: Instance Segmentation Model, Clip Comparison, Florence-2 Model, Morphological Transformation, Google Gemini, LMM, Instance Segmentation Model, Motion Detection, Email Notification, Detections Stitch, Polygon Zone Visualization, Keypoint Visualization, Camera Focus, Anthropic Claude, Multi-Label Classification Model, Pixel Color Count, Image Threshold, LMM For Classification, Keypoint Detection Model, Anthropic Claude, Gaze Detection, Reference Path Visualization, Camera Focus, Stability AI Image Generation, Stitch Images, Stability AI Outpainting, Image Slicer, SmolVLM2, OpenAI, Roboflow Dataset Upload, Depth Estimation, YOLO-World Model, Google Gemini, CogVLM, Image Preprocessing, VLM as Detector, Florence-2 Model, Image Convert Grayscale, SAM 3, Byte Tracker, Dynamic Crop, Time in Zone, Perception Encoder Embedding Model, Moondream2, Triangle Visualization, Dot Visualization, OCR Model, Seg Preview, Crop Visualization, Twilio SMS/MMS Notification, Perspective Correction, EasyOCR, SAM 3, Google Gemini, Object Detection Model, Text Display, Trace Visualization, Pixelate Visualization, OpenAI, CLIP Embedding Model, Camera Calibration, Roboflow Dataset Upload, Buffer, Barcode Detection, Object Detection Model, Single-Label Classification Model, QR Code Detection, VLM as Detector, Background Subtraction, Bounding Box Visualization, Contrast Equalization, Model Comparison Visualization, Halo Visualization, Label Visualization, OpenAI, Circle Visualization, Qwen2.5-VL, Image Contours, Image Blur, Background Color Visualization, Mask Visualization, Dominant Color, VLM as Classifier, Google Vision OCR, Llama 3.2 Vision, Color Visualization, Corner Visualization, Classification Label Visualization, Single-Label Classification Model, OpenAI, Segment Anything 2 Model, Clip Comparison, Template Matching, Line Counter Visualization, Icon Visualization, Ellipse Visualization, Image Slicer, Detections Stabilizer, Absolute Static Crop, VLM as Classifier, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Qwen3-VL, SAM 3, Keypoint Detection Model, Relative Static Crop, SIFT, Blur Visualization, Multi-Label Classification Model

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Corner 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[rle_instance_segmentation_prediction, object_detection_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 corner marker lines in pixels. Higher values create thicker, more visible corner markers..
  • corner_length (integer): Length of each corner marker line segment in pixels. This controls how long the corner indicators extend from each corner point. Higher values create longer, more prominent corner markers..

• output

  • image (image): Image in workflows.

Example JSON definition of step Corner Visualization in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/corner_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": 4,
    "corner_length": 15
}