Reference Path Visualization¶
Class: ReferencePathVisualizationBlockV1
Draw a static reference path on an image to visualize an expected or ideal route, displaying a predefined polyline path that can be compared against actual object trajectories for path deviation analysis and route compliance monitoring.
How This Block Works¶
This block takes an image and reference path coordinates (a list of points defining a path) and draws a static polyline path representing an expected route or ideal trajectory. The block:
- Takes an image and reference path coordinates (a list of points: [(x1, y1), (x2, y2), (x3, y3), ...]) as input
- Converts the coordinate list into a polyline path connecting the points in sequence
- Draws the reference path as a polyline using the specified color and thickness
- Returns an annotated image with the reference path overlaid on the original image
The block visualizes a static, predefined reference path that represents where objects should ideally move or what route they should follow. Unlike Trace Visualization (which draws dynamic paths based on actual tracked object movement), Reference Path Visualization draws a fixed path that remains constant. This reference path serves as a baseline for comparison, allowing you to visualize the expected route alongside actual object trajectories. The path is drawn as a continuous line connecting all the specified points, creating a visual guide for route compliance, path deviation analysis, or navigation workflows. This block is commonly used with Path Deviation analytics blocks to visually display the reference path that actual object trajectories will be compared against.
Common Use Cases¶
- Path Deviation Visualization: Visualize a reference path alongside actual object trajectories to compare expected routes against actual movement for path deviation detection, route compliance monitoring, or navigation validation workflows
- Route Planning and Navigation: Display predefined routes, navigation paths, or expected travel routes that objects should follow for route planning, navigation systems, or waypoint visualization applications
- Compliance and Safety Monitoring: Visualize expected paths for safety monitoring, compliance workflows, or route validation where objects need to follow specific paths (e.g., vehicles on designated lanes, robots on expected routes)
- Industrial and Logistics Applications: Display reference paths for conveyor systems, automated guided vehicles (AGVs), or manufacturing workflows where objects must follow predefined routes for process control or quality assurance
- Security and Access Control: Visualize expected movement paths for security monitoring, access control, or surveillance workflows where deviations from expected routes need to be identified
- Training and Documentation: Display reference paths in training materials, documentation, or demonstrations to show expected object behavior, routes, or movement patterns for educational or reference purposes
Connecting to Other Blocks¶
The annotated image from this block can be connected to:
- Path Deviation analytics blocks to compare tracked object trajectories against the visualized reference path for deviation analysis
- Other visualization blocks (e.g., Trace Visualization, Bounding Box Visualization, Label Visualization) to combine reference path visualization with actual object tracking visualizations for comprehensive path comparison
- Tracking blocks (e.g., Byte Tracker) where the reference path can serve as a visual baseline for comparing actual tracked object trajectories
- Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save images with reference paths for documentation, reporting, or analysis
- Webhook blocks to send visualized results with reference paths 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 reference paths as visual evidence in alerts or reports
- Video output blocks to create annotated video streams or recordings with reference paths for live monitoring, path visualization, or post-processing analysis
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/reference_path_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.. | ✅ |
reference_path |
List[Any] |
Reference path coordinates in the format [(x1, y1), (x2, y2), (x3, y3), ...] defining the expected or ideal route. The path is drawn as a polyline connecting these points in sequence, creating a continuous line representing the reference trajectory. Typically connected from Path Deviation analytics blocks or defined manually as an expected route. Must contain at least two points to form a valid path.. | ✅ |
color |
str |
Color of the reference path. Can be specified as a color name (e.g., 'WHITE', 'GREEN', 'BLUE'), hex color code (e.g., '#5bb573', '#FFFFFF'), or RGB format (e.g., 'rgb(91, 181, 115)'). The reference path is drawn in this color with the specified thickness.. | ✅ |
thickness |
int |
Thickness of the reference path line in pixels. Controls how thick the reference path appears. Higher values create thicker, more visible paths, while lower values create thinner, more subtle paths. Must be greater than or equal to zero. Typical values range from 1 to 5 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 Reference Path Visualization in version v1.
- inputs:
Florence-2 Model,Trace Visualization,Roboflow Dataset Upload,Classification Label Visualization,Stitch Images,Line Counter,Image Slicer,Ellipse Visualization,Clip Comparison,Line Counter,Distance Measurement,Crop Visualization,Grid Visualization,Morphological Transformation,Triangle Visualization,Reference Path Visualization,Roboflow Dataset Upload,Twilio SMS/MMS Notification,Google Gemini,LMM,Stitch OCR Detections,Dimension Collapse,Image Slicer,Local File Sink,VLM As Classifier,Icon Visualization,QR Code Generator,Stability AI Outpainting,OpenAI,Florence-2 Model,Google Vision OCR,Camera Focus,Pixel Color Count,Pixelate Visualization,Model Comparison Visualization,Template Matching,Image Preprocessing,Background Color Visualization,Twilio SMS Notification,Color Visualization,Clip Comparison,Polygon Zone Visualization,OpenAI,Halo Visualization,Background Subtraction,Keypoint Detection Model,Keypoint Visualization,Instance Segmentation Model,Contrast Equalization,EasyOCR,Image Blur,Polygon Visualization,Anthropic Claude,SIFT,Google Gemini,LMM For Classification,Webhook Sink,Perspective Correction,Object Detection Model,Circle Visualization,Blur Visualization,Dot Visualization,Camera Calibration,Heatmap Visualization,Image Threshold,Multi-Label Classification Model,Relative Static Crop,Google Gemini,Text Display,Email Notification,Detection Event Log,OpenAI,Single-Label Classification Model,Anthropic Claude,Depth Estimation,VLM As Detector,Mask Visualization,CSV Formatter,Stability AI Image Generation,Dynamic Zone,Size Measurement,Halo Visualization,Absolute Static Crop,OCR Model,Label Visualization,Detections Consensus,Stability AI Inpainting,Motion Detection,Anthropic Claude,Corner Visualization,Image Convert Grayscale,Roboflow Custom Metadata,Stitch OCR Detections,SIFT Comparison,Polygon Visualization,CogVLM,SIFT Comparison,Detections List Roll-Up,VLM As Detector,Line Counter Visualization,Bounding Box Visualization,VLM As Classifier,JSON Parser,Camera Focus,Identify Outliers,PTZ Tracking (ONVIF),Email Notification,Slack Notification,Llama 3.2 Vision,Identify Changes,Dynamic Crop,Image Contours,Model Monitoring Inference Aggregator,Buffer,OpenAI - outputs:
Florence-2 Model,Roboflow Dataset Upload,Trace Visualization,Image Contours,Seg Preview,Segment Anything 2 Model,Classification Label Visualization,Stitch Images,Single-Label Classification Model,Qwen3-VL,Clip Comparison,Ellipse Visualization,Image Slicer,Byte Tracker,SAM 3,Detections Stabilizer,Crop Visualization,Triangle Visualization,Morphological Transformation,Roboflow Dataset Upload,LMM,Twilio SMS/MMS Notification,Multi-Label Classification Model,Reference Path Visualization,SmolVLM2,Google Gemini,Image Slicer,Barcode Detection,VLM As Classifier,Icon Visualization,Stability AI Outpainting,OpenAI,Moondream2,Keypoint Detection Model,Florence-2 Model,Google Vision OCR,Pixel Color Count,Camera Focus,Pixelate Visualization,Model Comparison Visualization,Object Detection Model,Gaze Detection,Template Matching,Image Preprocessing,Background Color Visualization,Clip Comparison,Color Visualization,Polygon Zone Visualization,OpenAI,Background Subtraction,Halo Visualization,Keypoint Detection Model,Keypoint Visualization,Perception Encoder Embedding Model,Instance Segmentation Model,Contrast Equalization,EasyOCR,Image Blur,Anthropic Claude,Polygon Visualization,SIFT,Google Gemini,Perspective Correction,Object Detection Model,Circle Visualization,Blur Visualization,Dominant Color,Dot Visualization,YOLO-World Model,Multi-Label Classification Model,Heatmap Visualization,Image Threshold,Camera Calibration,Relative Static Crop,Google Gemini,Text Display,Email Notification,OpenAI,Instance Segmentation Model,Qwen2.5-VL,Single-Label Classification Model,Anthropic Claude,Depth Estimation,VLM As Detector,Mask Visualization,Stability AI Image Generation,Buffer,Halo Visualization,Absolute Static Crop,Detections Stitch,OCR Model,Label Visualization,Stability AI Inpainting,Motion Detection,Anthropic Claude,Corner Visualization,Image Convert Grayscale,QR Code Detection,SIFT Comparison,Polygon Visualization,CogVLM,SAM 3,VLM As Detector,Line Counter Visualization,Bounding Box Visualization,CLIP Embedding Model,Llama 3.2 Vision,Camera Focus,SAM 3,VLM As Classifier,Dynamic Crop,Time in Zone,LMM For Classification,OpenAI
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Reference Path 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..reference_path(list_of_values): Reference path coordinates in the format [(x1, y1), (x2, y2), (x3, y3), ...] defining the expected or ideal route. The path is drawn as a polyline connecting these points in sequence, creating a continuous line representing the reference trajectory. Typically connected from Path Deviation analytics blocks or defined manually as an expected route. Must contain at least two points to form a valid path..color(string): Color of the reference path. Can be specified as a color name (e.g., 'WHITE', 'GREEN', 'BLUE'), hex color code (e.g., '#5bb573', '#FFFFFF'), or RGB format (e.g., 'rgb(91, 181, 115)'). The reference path is drawn in this color with the specified thickness..thickness(integer): Thickness of the reference path line in pixels. Controls how thick the reference path appears. Higher values create thicker, more visible paths, while lower values create thinner, more subtle paths. Must be greater than or equal to zero. Typical values range from 1 to 5 pixels..
-
output
image(image): Image in workflows.
Example JSON definition of step Reference Path Visualization in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/reference_path_visualization@v1",
"image": "$inputs.image",
"copy_image": true,
"reference_path": "$inputs.expected_path",
"color": "WHITE",
"thickness": 2
}