Heatmap Visualization

Class: HeatmapVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.heatmap.v1.HeatmapVisualizationBlockV1

Draw heatmaps on an image based on provided detections. Heat accumulates over time and is drawn as a semi-transparent overlay of blurred circles.

How This Block Works

This block takes an image and detection predictions and draws a heatmap. The block:

1. Takes an image and predictions as input.
2. Accumulates heat based on the position of detections.
3. Draws a semi-transparent overlay of blurred circles representing the heat.

Common Use Cases

• Density Analysis: Visualize the density of objects in a scene.
• Traffic Monitoring: Identify high-traffic areas.
• Retail Analytics: Analyze foot traffic in stores.

Type identifier

Use the following identifier in step "type" field: roboflow_core/heatmap_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..	✅
position	str	The position of the heatmap relative to the detection..	✅
opacity	float	Opacity of the overlay mask, between 0 and 1..	✅
radius	int	Radius of the heat circle..	✅
kernel_size	int	Kernel size for blurring the heatmap..	✅
top_hue	int	Hue at the top of the heatmap. Defaults to 0 (red)..	✅
low_hue	int	Hue at the bottom of the heatmap. Defaults to 125 (blue)..	✅
ignore_stationary	bool	If True, only moving objects (based on tracker ID) will contribute to the heatmap..	✅
motion_threshold	int	Minimum movement in pixels required to consider an object as moving..	✅

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 Heatmap Visualization in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Heatmap 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, object_detection_prediction, rle_instance_segmentation_prediction, instance_segmentation_prediction]): Model predictions to visualize..
  • metadata (video_metadata): Video metadata containing video_identifier to maintain separate state for different videos..
  • position (string): The position of the heatmap relative to the detection..
  • opacity (float): Opacity of the overlay mask, between 0 and 1..
  • radius (integer): Radius of the heat circle..
  • kernel_size (integer): Kernel size for blurring the heatmap..
  • top_hue (integer): Hue at the top of the heatmap. Defaults to 0 (red)..
  • low_hue (integer): Hue at the bottom of the heatmap. Defaults to 125 (blue)..
  • ignore_stationary (boolean): If True, only moving objects (based on tracker ID) will contribute to the heatmap..
  • motion_threshold (integer): Minimum movement in pixels required to consider an object as moving..

• output

  • image (image): Image in workflows.

Example JSON definition of step Heatmap Visualization in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/heatmap_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.object_detection_model.predictions",
    "metadata": "$inputs.video_metadata",
    "position": "BOTTOM_CENTER",
    "opacity": 0.2,
    "radius": 40,
    "kernel_size": 25,
    "top_hue": 0,
    "low_hue": 125,
    "ignore_stationary": true,
    "motion_threshold": 25
}