Distance Measurement

Class: DistanceMeasurementBlockV1

Source: inference.core.workflows.core_steps.classical_cv.distance_measurement.v1.DistanceMeasurementBlockV1

Calculate the distance between two bounding boxes on a 2D plane, leveraging a perpendicular camera view and either a reference object or a pixel-to-unit scaling ratio for precise measurements.

Type identifier

Use the following identifier in step "type" field: roboflow_core/distance_measurement@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
object_1_class_name	str	The class name of the first object..	❌
object_2_class_name	str	The class name of the second object..	❌
reference_axis	str	The axis along which the distance will be measured..	❌
calibration_method	str	Select how to calibrate the measurement of distance between objects..	❌
reference_object_class_name	str	The class name of the reference object..	✅
reference_width	float	Width of the reference object in centimeters.	✅
reference_height	float	Height of the reference object in centimeters.	✅
pixel_ratio	float	The pixel-to-centimeter ratio of the input image, i.e. 1 centimeter = 100 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 Distance Measurement in version v1.

• inputs: Local File Sink, Byte Tracker, Webhook Sink, LMM For Classification, Time in Zone, VLM as Classifier, OpenAI, Cosine Similarity, Detections Stitch, Time in Zone, Velocity, Perspective Correction, CSV Formatter, Object Detection Model, Detections Transformation, LMM, Byte Tracker, Overlap Filter, PTZ Tracking (ONVIF).md), Florence-2 Model, Florence-2 Model, OpenAI, Roboflow Custom Metadata, Object Detection Model, Multi-Label Classification Model, Detections Combine, Detection Offset, CogVLM, Dynamic Zone, EasyOCR, Byte Tracker, Model Monitoring Inference Aggregator, Gaze Detection, Line Counter, Anthropic Claude, Time in Zone, Stitch OCR Detections, VLM as Detector, Path Deviation, OpenAI, Slack Notification, Google Vision OCR, Keypoint Detection Model, Twilio SMS Notification, Identify Changes, Camera Focus, Roboflow Dataset Upload, Email Notification, Detections Filter, YOLO-World Model, Instance Segmentation Model, Clip Comparison, Template Matching, Detections Classes Replacement, Bounding Rectangle, OCR Model, Detections Stabilizer, Llama 3.2 Vision, Instance Segmentation Model, VLM as Detector, Google Gemini, Dynamic Crop, Roboflow Dataset Upload, Detections Merge, Path Deviation, Single-Label Classification Model, Detections Consensus, Moondream2, Segment Anything 2 Model
• outputs: Byte Tracker, Identify Outliers, Dot Visualization, Morphological Transformation, Blur Visualization, Perspective Correction, Corner Visualization, Pixel Color Count, PTZ Tracking (ONVIF).md), Grid Visualization, Image Threshold, Halo Visualization, Keypoint Detection Model, Detection Offset, Byte Tracker, Line Counter Visualization, Stitch OCR Detections, Stability AI Outpainting, Twilio SMS Notification, Keypoint Detection Model, Identify Changes, Email Notification, Instance Segmentation Model, Image Slicer, Keypoint Visualization, Detections Stabilizer, Bounding Box Visualization, Instance Segmentation Model, Reference Path Visualization, Mask Visualization, Image Preprocessing, Webhook Sink, Image Slicer, QR Code Generator, SIFT Comparison, Dominant Color, Trace Visualization, Object Detection Model, Byte Tracker, Crop Visualization, SIFT Comparison, Object Detection Model, Pixelate Visualization, Dynamic Zone, Anthropic Claude, Polygon Visualization, Image Contours, Slack Notification, Triangle Visualization, Classification Label Visualization, Detections Classes Replacement, Circle Visualization, Image Blur, Label Visualization, Absolute Static Crop, Stability AI Inpainting, Icon Visualization, Ellipse Visualization, Color Visualization, Detections Consensus, Stitch Images

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Distance Measurement in version v1 has.

Bindings

• input

  • predictions (Union[object_detection_prediction, instance_segmentation_prediction]): The output of a detection model describing the bounding boxes that will be used to measure the objects..
  • reference_object_class_name (string): The class name of the reference object..
  • reference_width (float): Width of the reference object in centimeters.
  • reference_height (float): Height of the reference object in centimeters.
  • pixel_ratio (float): The pixel-to-centimeter ratio of the input image, i.e. 1 centimeter = 100 pixels..

• output

  • distance_cm (integer): Integer value.
  • distance_pixel (integer): Integer value.

Example JSON definition of step Distance Measurement in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/distance_measurement@v1",
    "predictions": "$steps.model.predictions",
    "object_1_class_name": "car",
    "object_2_class_name": "person",
    "reference_axis": "vertical",
    "calibration_method": "<block_does_not_provide_example>",
    "reference_object_class_name": "reference-object",
    "reference_width": 2.5,
    "reference_height": 2.5,
    "pixel_ratio": 100
}