Corner Visualization

Class: CornerVisualizationBlockV1

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

The CornerVisualization block draws the corners of detected objects in an image using Supervision's sv.BoxCornerAnnotator.

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 lines in pixels..	✅
corner_length	int	Length of the corner lines in pixels..	✅

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: Bounding Rectangle, Image Contours, Line Counter Visualization, Keypoint Detection Model, Florence-2 Model, Instance Segmentation Model, Roboflow Dataset Upload, Gaze Detection, Webhook Sink, Camera Calibration, Time in Zone, Image Slicer, LMM, Model Comparison Visualization, Perspective Correction, Dynamic Crop, JSON Parser, LMM For Classification, Roboflow Dataset Upload, Dynamic Zone, SIFT, CogVLM, Relative Static Crop, Dot Visualization, Grid Visualization, Detections Consensus, Detections Classes Replacement, SIFT Comparison, Slack Notification, CSV Formatter, Color Visualization, Keypoint Visualization, Mask Visualization, Byte Tracker, Object Detection Model, Single-Label Classification Model, OCR Model, Clip Comparison, Buffer, Anthropic Claude, Blur Visualization, Segment Anything 2 Model, Path Deviation, Multi-Label Classification Model, Florence-2 Model, YOLO-World Model, Absolute Static Crop, Pixelate Visualization, Corner Visualization, Detections Transformation, Local File Sink, VLM as Detector, Time in Zone, Image Threshold, Twilio SMS Notification, Path Deviation, Label Visualization, OpenAI, Polygon Visualization, Pixel Color Count, VLM as Classifier, Byte Tracker, Background Color Visualization, Roboflow Custom Metadata, Stitch Images, Distance Measurement, Dimension Collapse, Identify Changes, Classification Label Visualization, Stability AI Inpainting, Camera Focus, Circle Visualization, Line Counter, VLM as Classifier, Stability AI Image Generation, VLM as Detector, Stitch OCR Detections, Google Vision OCR, Detections Merge, Clip Comparison, Bounding Box Visualization, Ellipse Visualization, Instance Segmentation Model, Keypoint Detection Model, Reference Path Visualization, Triangle Visualization, Byte Tracker, Template Matching, Image Convert Grayscale, Line Counter, Size Measurement, Model Monitoring Inference Aggregator, Object Detection Model, Image Preprocessing, Image Blur, Email Notification, Google Gemini, Llama 3.2 Vision, Crop Visualization, Image Slicer, Detection Offset, Trace Visualization, Detections Filter, Halo Visualization, Detections Stabilizer, Identify Outliers, Polygon Zone Visualization, SIFT Comparison, Detections Stitch, Velocity, OpenAI
• outputs: Image Contours, Line Counter Visualization, Keypoint Detection Model, Florence-2 Model, Instance Segmentation Model, Roboflow Dataset Upload, Gaze Detection, Time in Zone, Camera Calibration, Image Slicer, LMM, Model Comparison Visualization, Dominant Color, Dynamic Crop, Perspective Correction, LMM For Classification, Roboflow Dataset Upload, Multi-Label Classification Model, SIFT, CogVLM, Dot Visualization, Relative Static Crop, Qwen2.5-VL, SIFT Comparison, Color Visualization, Object Detection Model, Clip Comparison, OCR Model, Keypoint Visualization, Buffer, Single-Label Classification Model, Mask Visualization, Anthropic Claude, Blur Visualization, Multi-Label Classification Model, Segment Anything 2 Model, Florence-2 Model, YOLO-World Model, Absolute Static Crop, Pixelate Visualization, Corner Visualization, VLM as Detector, Image Threshold, Label Visualization, Pixel Color Count, Polygon Visualization, OpenAI, VLM as Classifier, SmolVLM2, Background Color Visualization, Stitch Images, Classification Label Visualization, Stability AI Inpainting, Camera Focus, Circle Visualization, VLM as Classifier, QR Code Detection, Stability AI Image Generation, VLM as Detector, Google Vision OCR, Clip Comparison, Bounding Box Visualization, Ellipse Visualization, Instance Segmentation Model, Keypoint Detection Model, Byte Tracker, Reference Path Visualization, Template Matching, Triangle Visualization, Image Convert Grayscale, Barcode Detection, Object Detection Model, Image Preprocessing, Image Blur, Google Gemini, Llama 3.2 Vision, Crop Visualization, Image Slicer, Single-Label Classification Model, Trace Visualization, Halo Visualization, Detections Stabilizer, Detections Stitch, Polygon Zone Visualization, CLIP Embedding Model, OpenAI

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[keypoint_detection_prediction, instance_segmentation_prediction, object_detection_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 lines in pixels..
  • corner_length (integer): Length of the corner lines in pixels..

• 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
}