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:
- Takes an image and predictions as input.
- Accumulates heat based on the position of detections.
- 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.
Runtime compatibility¶
-
soft— runtimehosted_serverless,dedicated_deployment; executionremote; inputvideo - Heatmap accumulation and stationary-object filtering keep per-video tracking state in process memory. With remote step execution on stateless or multi-replica HTTP runtimes, successive frames may be served by different worker processes, so heat history resets or splits across workers. Use local step execution in an InferencePipeline for stable cross-frame visualizations.
-
soft— inputimage - Block depends on temporal context from video or repeated-frame workflows. With a still image/photo, there is no meaningful history to track, compare, aggregate, or visualize, so the block provides little or no benefit.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Heatmap Visualization in version v1.
- inputs:
Detections Filter,Absolute Static Crop,VLM As Classifier,Qwen-VL,Gaze Detection,Triangle Visualization,Byte Tracker,EasyOCR,Model Comparison Visualization,Detection Event Log,Stitch OCR Detections,Track Class Lock,YOLO-World Model,OC-SORT Tracker,Llama 3.2 Vision,Heatmap Visualization,Stitch Images,Keypoint Visualization,Webhook Sink,Anthropic Claude,Detections Stabilizer,Google Gemini,GLM-OCR,QR Code Generator,Instance Segmentation Model,VLM As Detector,MoonshotAI Kimi,SAM2 Video Tracker,Multi-Label Classification Model,Twilio SMS/MMS Notification,Line Counter,Distance Measurement,Ellipse Visualization,Keypoint Detection Model,Pixelate Visualization,Detections Transformation,Corner Visualization,Template Matching,Bounding Rectangle,Llama 3.2 Vision,JSON Parser,Qwen 3.5 API,Velocity,Per-Class Confidence Filter,LMM,Roboflow Visual Search,OpenAI-Compatible LLM,Morphological Transformation,Color Visualization,Roboflow Dataset Upload,Morphological Transformation,Camera Calibration,Motion Detection,Detection Offset,Google Vision OCR,Clip Comparison,Bounding Box Visualization,OpenAI,Halo Visualization,SAM3 Video Tracker,Object Detection Model,Identify Changes,Detections Combine,Contrast Equalization,CSV Formatter,Mask Area Measurement,Detections Classes Replacement,Instance Segmentation Model,Model Monitoring Inference Aggregator,MQTT Writer,PLC Reader,Image Threshold,Blur Visualization,Line Counter Visualization,Google Gemini,Background Color Visualization,Microsoft SQL Server Sink,Single-Label Classification Model,Background Subtraction,Identify Outliers,Object Detection Model,Twilio SMS Notification,OPC UA Writer Sink,Polygon Zone Visualization,Path Deviation,Instance Segmentation Model,SAM 3,Google Gemma API,Keypoint Detection Model,Reference Path Visualization,Image Stack,SAM 3 Interactive,Stability AI Inpainting,Crop Visualization,Anthropic Claude,Image Convert Grayscale,Dynamic Zone,Camera Focus,Image Slicer,Overlap Filter,Florence-2 Model,Polygon Visualization,Time in Zone,MoonshotAI Kimi,Dynamic Crop,Qwen 3.6 API,Event Writer,Perspective Correction,Segment Anything 2 Model,Line Counter,Polygon Visualization,OCR Model,Roboflow Visual Search Classifier,Circle Visualization,Slack Notification,CogVLM,Contrast Enhancement,Grid Visualization,Mask Edge Snap,Time in Zone,Byte Tracker,Local File Sink,LMM For Classification,Florence-2 Model,OpenAI,Roboflow Custom Metadata,SORT Tracker,Qwen3.5-VL,Image Blur,Label Visualization,ByteTrack Tracker,Seg Preview,Path Deviation,Object Detection Model,Anthropic Claude,Cosine Similarity,Pixel Color Count,Roboflow Vision Events,Image Preprocessing,Trace Visualization,Email Notification,SIFT Comparison,Stability AI Outpainting,Detections Consensus,PTZ Tracking (ONVIF),Dot Visualization,Keypoint Detection Model,Roboflow Asset Library Attributes,Current Time,Halo Visualization,SAM 3,Classification Label Visualization,Mask Visualization,Image Contours,Camera Focus,OpenRouter,Moondream2,S3 Sink,Stability AI Image Generation,VLM As Detector,Google Gemma,Relative Static Crop,Roboflow Dataset Upload,OpenAI,Image Slicer,Detections Merge,Stitch OCR Detections,Google Gemini,BoT-SORT Tracker,Email Notification,Byte Tracker,SAM 3,Detections Stitch,Text Display,Depth Estimation,Icon Visualization,OpenAI,Time in Zone,SIFT Comparison,SIFT,Instance Segmentation Model,PLC Writer,Detections List Roll-Up,VLM As Classifier - outputs:
Absolute Static Crop,VLM As Classifier,Qwen-VL,Gaze Detection,Triangle Visualization,EasyOCR,Model Comparison Visualization,OC-SORT Tracker,YOLO-World Model,Track Class Lock,Llama 3.2 Vision,Anthropic Claude,Heatmap Visualization,Stitch Images,Keypoint Visualization,Detections Stabilizer,Google Gemini,Dominant Color,MoonshotAI Kimi,GLM-OCR,Instance Segmentation Model,VLM As Detector,SAM2 Video Tracker,Multi-Label Classification Model,Twilio SMS/MMS Notification,Ellipse Visualization,Single-Label Classification Model,SmolVLM2,Keypoint Detection Model,Pixelate Visualization,Corner Visualization,Buffer,Template Matching,Llama 3.2 Vision,Qwen2.5-VL,Qwen 3.5 API,LMM,Semantic Segmentation Model,Roboflow Visual Search,Morphological Transformation,Color Visualization,Roboflow Dataset Upload,Morphological Transformation,Camera Calibration,Motion Detection,Google Vision OCR,Clip Comparison,Bounding Box Visualization,OpenAI,Halo Visualization,SAM3 Video Tracker,Object Detection Model,Contrast Equalization,Instance Segmentation Model,Multi-Label Classification Model,Image Threshold,Blur Visualization,Line Counter Visualization,Google Gemini,Single-Label Classification Model,Background Subtraction,Object Detection Model,Instance Segmentation Model,SAM 3,QR Code Detection,Polygon Zone Visualization,Google Gemma API,Keypoint Detection Model,Image Stack,Reference Path Visualization,SAM 3 Interactive,Qwen3-VL,Stability AI Inpainting,Multi-Label Classification Model,Perception Encoder Embedding Model,Crop Visualization,Anthropic Claude,Image Convert Grayscale,Camera Focus,Image Slicer,Florence-2 Model,Polygon Visualization,MoonshotAI Kimi,Dynamic Crop,Qwen 3.6 API,Event Writer,Perspective Correction,Segment Anything 2 Model,Polygon Visualization,Clip Comparison,OCR Model,Roboflow Visual Search Classifier,Circle Visualization,CogVLM,Contrast Enhancement,Mask Edge Snap,Barcode Detection,Time in Zone,LMM For Classification,Qwen3.5-VL,Florence-2 Model,OpenAI,SORT Tracker,ByteTrack Tracker,Label Visualization,Image Blur,Seg Preview,Object Detection Model,Anthropic Claude,Pixel Color Count,Roboflow Vision Events,Image Preprocessing,Trace Visualization,Email Notification,SIFT Comparison,Stability AI Outpainting,Keypoint Detection Model,Dot Visualization,Halo Visualization,SAM 3,Classification Label Visualization,Mask Visualization,Image Contours,Camera Focus,Single-Label Classification Model,OpenRouter,Moondream2,Stability AI Image Generation,VLM As Detector,Google Gemma,CLIP Embedding Model,Relative Static Crop,Roboflow Dataset Upload,OpenAI,Image Slicer,Google Gemini,BoT-SORT Tracker,Byte Tracker,SAM 3,Detections Stitch,Semantic Segmentation Model,Text Display,Qwen3.5,Depth Estimation,Icon Visualization,OpenAI,GeoTag Detection,SIFT,Instance Segmentation Model,Background Color Visualization,VLM As Classifier
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[rle_instance_segmentation_prediction,instance_segmentation_prediction,keypoint_detection_prediction,object_detection_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
}