Keypoint Visualization¶
Class: KeypointVisualizationBlockV1
Source: inference.core.workflows.core_steps.visualizations.keypoint.v1.KeypointVisualizationBlockV1
The KeypointVisualization block uses a detections from an
keypoint detection model to draw keypoints on objects using
sv.VertexAnnotator.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/keypoint_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.. | ✅ |
annotator_type |
str |
Type of annotator to be used for keypoint visualization.. | ❌ |
color |
str |
Color of the keypoint.. | ✅ |
text_color |
str |
Text color of the keypoint.. | ✅ |
text_scale |
float |
Scale of the text.. | ✅ |
text_thickness |
int |
Thickness of the text characters.. | ✅ |
text_padding |
int |
Padding around the text in pixels.. | ✅ |
thickness |
int |
Thickness of the outline in pixels.. | ✅ |
radius |
int |
Radius of the keypoint 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 Keypoint Visualization in version v1.
- inputs:
Mask Visualization,Twilio SMS Notification,Relative Static Crop,Image Preprocessing,Dot Visualization,Reference Path Visualization,Grid Visualization,Clip Comparison,SIFT Comparison,Blur Visualization,Image Threshold,OpenAI,Single-Label Classification Model,Stitch OCR Detections,Detection Offset,Background Color Visualization,Bounding Box Visualization,Identify Outliers,Image Slicer,Pixel Color Count,Stability AI Image Generation,Camera Focus,Anthropic Claude,SIFT,Keypoint Detection Model,Detections Consensus,Pixelate Visualization,Google Vision OCR,Circle Visualization,Florence-2 Model,Webhook Sink,VLM as Detector,OpenAI,Absolute Static Crop,CSV Formatter,VLM as Classifier,Image Slicer,Detections Classes Replacement,Local File Sink,CogVLM,Line Counter Visualization,VLM as Classifier,Identify Changes,Gaze Detection,Llama 3.2 Vision,Instance Segmentation Model,Classification Label Visualization,Color Visualization,Trace Visualization,Slack Notification,Model Monitoring Inference Aggregator,Object Detection Model,Line Counter,Polygon Visualization,Line Counter,OCR Model,Template Matching,Stitch Images,Roboflow Custom Metadata,Corner Visualization,Dynamic Crop,SIFT Comparison,Image Contours,Crop Visualization,Image Convert Grayscale,Stability AI Inpainting,Perspective Correction,Detections Filter,Florence-2 Model,Keypoint Visualization,JSON Parser,Cosine Similarity,Google Gemini,Triangle Visualization,Label Visualization,Email Notification,Keypoint Detection Model,LMM,VLM as Detector,Model Comparison Visualization,Roboflow Dataset Upload,Detections Transformation,Roboflow Dataset Upload,Halo Visualization,Multi-Label Classification Model,Distance Measurement,Ellipse Visualization,LMM For Classification,Polygon Zone Visualization,Image Blur - outputs:
Mask Visualization,Relative Static Crop,Image Preprocessing,Dot Visualization,Reference Path Visualization,Clip Comparison,Blur Visualization,Image Threshold,OpenAI,Single-Label Classification Model,Background Color Visualization,Bounding Box Visualization,Image Slicer,Pixel Color Count,Stability AI Image Generation,Camera Focus,Multi-Label Classification Model,Object Detection Model,Anthropic Claude,SIFT,Keypoint Detection Model,Pixelate Visualization,Google Vision OCR,Buffer,Dominant Color,Circle Visualization,Florence-2 Model,QR Code Detection,Qwen2.5-VL,OpenAI,VLM as Detector,Absolute Static Crop,Segment Anything 2 Model,VLM as Classifier,Image Slicer,Byte Tracker,CogVLM,Line Counter Visualization,VLM as Classifier,Gaze Detection,Llama 3.2 Vision,Instance Segmentation Model,Classification Label Visualization,Color Visualization,Trace Visualization,Object Detection Model,Instance Segmentation Model,Polygon Visualization,Time in Zone,Single-Label Classification Model,OCR Model,Template Matching,Clip Comparison,Stitch Images,Corner Visualization,Dynamic Crop,SIFT Comparison,Image Contours,Crop Visualization,Image Convert Grayscale,Stability AI Inpainting,CLIP Embedding Model,Perspective Correction,Florence-2 Model,Keypoint Visualization,Google Gemini,Triangle Visualization,Label Visualization,Keypoint Detection Model,YOLO-World Model,LMM,VLM as Detector,Model Comparison Visualization,Roboflow Dataset Upload,Roboflow Dataset Upload,Multi-Label Classification Model,Halo Visualization,Barcode Detection,Detections Stitch,Ellipse Visualization,LMM For Classification,Polygon Zone Visualization,Detections Stabilizer,Image Blur
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Keypoint 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(keypoint_detection_prediction): Predictions.color(string): Color of the keypoint..text_color(string): Text color of the keypoint..text_scale(float): Scale of the text..text_thickness(integer): Thickness of the text characters..text_padding(integer): Padding around the text in pixels..thickness(integer): Thickness of the outline in pixels..radius(integer): Radius of the keypoint in pixels..
-
output
image(image): Image in workflows.
Example JSON definition of step Keypoint Visualization in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/keypoint_visualization@v1",
"image": "$inputs.image",
"copy_image": true,
"predictions": "$steps.keypoint_detection_model.predictions",
"annotator_type": "<block_does_not_provide_example>",
"color": "#A351FB",
"text_color": "black",
"text_scale": 0.5,
"text_thickness": 1,
"text_padding": 10,
"thickness": 2,
"radius": 10
}