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:
- Takes an image and predictions as input
- Identifies bounding box coordinates for each detected object
- Calculates the four corner positions (top-left, top-right, bottom-left, bottom-right) of each bounding box
- Applies color styling based on the selected color palette, with colors assigned by class, index, or track ID
- Draws corner markers (typically L-shaped lines or corner indicators) at each corner position using Supervision's BoxCornerAnnotator
- Applies the specified thickness and corner length to control the appearance of the corner markers
- 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:
SAM 3,Image Preprocessing,Time in Zone,Image Slicer,Anthropic Claude,Dynamic Crop,Mask Area Measurement,BoT-SORT Tracker,Bounding Box Visualization,Object Detection Model,Mask Edge Snap,Path Deviation,Absolute Static Crop,SIFT Comparison,Stitch Images,Stitch OCR Detections,OpenAI,Instance Segmentation Model,Email Notification,Stability AI Inpainting,Frame Delay,Distance Measurement,EasyOCR,Llama 3.2 Vision,Track Class Lock,Florence-2 Model,Gaze Detection,Roboflow Custom Metadata,Dynamic Zone,Auto Rotate on Edges,YOLO-World Model,Byte Tracker,Detections Transformation,Keypoint Detection Model,Stability AI Outpainting,Model Comparison Visualization,Slack Notification,Detections Classes Replacement,Line Counter Visualization,Camera Calibration,Byte Tracker,PLC Reader,Single-Label Classification Model,Clip Comparison,VLM As Detector,CogVLM,SORT Tracker,Camera Focus,Corner Visualization,Ellipse Visualization,PP-OCR,Morphological Transformation,Detections List Roll-Up,Anthropic Claude,Roboflow Visual Search,Color Visualization,Instance Segmentation Model,OpenAI,Triangle Visualization,Time in Zone,Detection Event Log,Detections Stabilizer,Object Detection Model,Image Contours,SAM 3,Image Threshold,SAM 3,Detections Merge,Current Time,Roboflow Visual Search Classifier,QR Code Generator,OpenAI-Compatible LLM,Florence-2 Model,Polygon Zone Visualization,Stitch OCR Detections,Roboflow Asset Library Attributes,Path Deviation,GeoTag Detection,Microsoft SQL Server Sink,Moondream2,VLM As Classifier,Camera Focus,Image Convert Grayscale,Label Visualization,Detection Offset,Stability AI Image Generation,Llama 3.2 Vision,VLM As Detector,Instance Segmentation Model,Line Counter,MQTT Writer,Roboflow Dataset Upload,Local File Sink,Identify Outliers,VLM As Classifier,Bounding Rectangle,Event Writer,Google Gemini,Depth Estimation,Seg Preview,Byte Tracker,Google Gemini,OpenAI,Trace Visualization,Twilio SMS Notification,Pixel Color Count,SAM 3 Interactive,PLC EthernetIP,Detections Filter,LMM For Classification,Object Detection Model,Velocity,Webhook Sink,Halo Visualization,Buffer,Mask Visualization,Template Matching,Pixelate Visualization,Twilio SMS/MMS Notification,MoonshotAI Kimi,Dot Visualization,Multi-Label Classification Model,Image Stack,OPC UA Writer Sink,Google Gemini,OC-SORT Tracker,Keypoint Visualization,Dimension Collapse,LMM,Detections Combine,Image Slicer,PTZ Tracking (ONVIF),Time in Zone,OCR Model,Circle Visualization,Contrast Enhancement,Relative Static Crop,SAM2 Video Tracker,ByteTrack Tracker,Morphological Transformation,Per-Class Confidence Filter,Email Notification,Halo Visualization,Clip Comparison,Cosmos 3,Polygon Visualization,Qwen-VL,PLC Writer,Google Gemma,Crop Visualization,Qwen 3.5 API,Model Monitoring Inference Aggregator,Keypoint Detection Model,Size Measurement,Icon Visualization,Heatmap Visualization,Motion Detection,Google Gemma API,Detections Consensus,Instance Segmentation Model,CSV Formatter,Image Blur,Segment Anything 2 Model,Background Color Visualization,Grid Visualization,Detections Stitch,SAM3 Video Tracker,Blur Visualization,GLM-OCR,Anthropic Claude,Reference Path Visualization,Classification Label Visualization,Google Vision OCR,Perspective Correction,Background Subtraction,Polygon Visualization,Contrast Equalization,SIFT,Qwen 3.6 API,Text Display,JSON Parser,MoonshotAI Kimi,OpenRouter,Qwen3.5-VL,Roboflow Vision Events,Identify Changes,Keypoint Detection Model,SIFT Comparison,OpenAI,PLC ModbusTCP,Overlap Filter,S3 Sink,Line Counter,Roboflow Dataset Upload - outputs:
SAM 3,Image Preprocessing,Single-Label Classification Model,Anthropic Claude,Image Slicer,CLIP Embedding Model,Dynamic Crop,BoT-SORT Tracker,Bounding Box Visualization,Mask Edge Snap,Object Detection Model,QR Code Detection,Absolute Static Crop,SIFT Comparison,Stitch Images,OpenAI,Instance Segmentation Model,Email Notification,Stability AI Inpainting,Frame Delay,EasyOCR,Llama 3.2 Vision,Track Class Lock,Florence-2 Model,Gaze Detection,Auto Rotate on Edges,YOLO-World Model,Dominant Color,Keypoint Detection Model,Stability AI Outpainting,Model Comparison Visualization,Line Counter Visualization,Camera Calibration,Single-Label Classification Model,Clip Comparison,VLM As Detector,CogVLM,SORT Tracker,Corner Visualization,PP-OCR,Camera Focus,Ellipse Visualization,Morphological Transformation,Anthropic Claude,Roboflow Visual Search,Instance Segmentation Model,Color Visualization,OpenAI,Time in Zone,Triangle Visualization,Detections Stabilizer,Object Detection Model,Image Contours,SAM 3,Image Threshold,SAM 3,Barcode Detection,Roboflow Visual Search Classifier,Qwen2.5-VL,Florence-2 Model,Semantic Segmentation Model,SmolVLM2,Polygon Zone Visualization,GeoTag Detection,Moondream2,VLM As Classifier,Camera Focus,Image Convert Grayscale,Label Visualization,Llama 3.2 Vision,Stability AI Image Generation,VLM As Detector,Perception Encoder Embedding Model,Instance Segmentation Model,Roboflow Dataset Upload,VLM As Classifier,Google Gemini,Event Writer,Semantic Segmentation Model,Depth Estimation,Seg Preview,Byte Tracker,Google Gemini,OpenAI,Trace Visualization,Pixel Color Count,SAM 3 Interactive,LMM For Classification,Object Detection Model,Halo Visualization,Buffer,Mask Visualization,Template Matching,Twilio SMS/MMS Notification,Pixelate Visualization,MoonshotAI Kimi,Dot Visualization,Multi-Label Classification Model,Image Stack,Google Gemini,OC-SORT Tracker,Keypoint Visualization,LMM,Image Slicer,OCR Model,Circle Visualization,Contrast Enhancement,Relative Static Crop,SAM2 Video Tracker,ByteTrack Tracker,Morphological Transformation,Halo Visualization,Clip Comparison,Cosmos 3,Polygon Visualization,Qwen-VL,Google Gemma,Crop Visualization,Qwen 3.5 API,Qwen3-VL,Qwen3.5,Keypoint Detection Model,Single-Label Classification Model,Icon Visualization,Heatmap Visualization,Motion Detection,Multi-Label Classification Model,Google Gemma API,Instance Segmentation Model,SAM3 Video Tracker,Image Blur,Background Color Visualization,Detections Stitch,Segment Anything 2 Model,Blur Visualization,GLM-OCR,Anthropic Claude,Reference Path Visualization,Classification Label Visualization,Google Vision OCR,Background Subtraction,Perspective Correction,Polygon Visualization,Contrast Equalization,SIFT,Qwen 3.6 API,Text Display,MoonshotAI Kimi,OpenRouter,Qwen3.5-VL,Roboflow Vision Events,OpenAI,Keypoint Detection Model,Multi-Label Classification Model,Roboflow Dataset Upload
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[instance_segmentation_prediction,keypoint_detection_prediction,object_detection_prediction,rle_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
}