Camera Calibration

Class: CameraCalibrationBlockV1

Source: inference.core.workflows.core_steps.transformations.camera_calibration.v1.CameraCalibrationBlockV1

This block uses the OpenCV calibrateCamera function to remove lens distortions from an image. Please refer to OpenCV documentation where camera calibration methodology is described: https://docs.opencv.org/4.x/dc/dbb/tutorial_py_calibration.html

This block requires following parameters in order to perform the calibration: Lens focal length along the x-axis and y-axis (fx, fy) Lens optical centers along the x-axis and y-axis (cx, cy) Radial distortion coefficients (k1, k2, k3) Tangential distortion coefficients (p1, p2)

Based on above parameters, camera matrix will be built as follows: [[fx 0 cx][ 0 fy cy] [ 0 0 1 ]]

Distortions coefficient will be passed as 5-tuple (k1, k2, p1, p2, k3)

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
fx	float	Focal length along the x-axis.	✅
fy	float	Focal length along the y-axis.	✅
cx	float	Optical center along the x-axis.	✅
cy	float	Optical center along the y-axis.	✅
k1	float	Radial distortion coefficient k1.	✅
k2	float	Radial distortion coefficient k2.	✅
k3	float	Radial distortion coefficient k3.	✅
p1	float	Distortion coefficient p1.	✅
p2	float	Distortion coefficient p2.	✅

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 Camera Calibration in version v1.

• inputs: Image Convert Grayscale, Camera Focus, Depth Estimation, Perspective Correction, Image Threshold, Polygon Visualization, Camera Calibration, Line Counter Visualization, Pixelate Visualization, Color Visualization, SIFT, Circle Visualization, Dynamic Crop, Dot Visualization, Model Comparison Visualization, Image Slicer, Background Color Visualization, Absolute Static Crop, Mask Visualization, Keypoint Visualization, Crop Visualization, Grid Visualization, Relative Static Crop, Bounding Box Visualization, Stitch Images, Ellipse Visualization, Image Blur, Reference Path Visualization, Label Visualization, SIFT Comparison, Image Preprocessing, Image Slicer, Gaze Detection, Triangle Visualization, Corner Visualization, Classification Label Visualization, Stability AI Inpainting, Image Contours, Blur Visualization, Polygon Zone Visualization, Identify Changes, Trace Visualization, Halo Visualization, Stability AI Image Generation, Cosine Similarity
• outputs: Segment Anything 2 Model, Keypoint Detection Model, Image Convert Grayscale, VLM as Classifier, VLM as Detector, Detections Stitch, Image Threshold, Polygon Visualization, YOLO-World Model, CogVLM, Pixelate Visualization, Time in Zone, SmolVLM2, Circle Visualization, Dynamic Crop, Dot Visualization, Model Comparison Visualization, Background Color Visualization, Absolute Static Crop, Byte Tracker, QR Code Detection, Keypoint Visualization, Single-Label Classification Model, LMM, Template Matching, LMM For Classification, Florence-2 Model, Roboflow Dataset Upload, Clip Comparison, Google Gemini, VLM as Classifier, Label Visualization, Image Slicer, Gaze Detection, Keypoint Detection Model, Triangle Visualization, Anthropic Claude, Florence-2 Model, Corner Visualization, Stability AI Inpainting, Image Contours, Llama 3.2 Vision, OCR Model, Qwen2.5-VL, Instance Segmentation Model, Camera Focus, Depth Estimation, Perspective Correction, Google Vision OCR, Single-Label Classification Model, Detections Stabilizer, Camera Calibration, Line Counter Visualization, Multi-Label Classification Model, VLM as Detector, Object Detection Model, OpenAI, Color Visualization, SIFT, Moondream2, Image Slicer, Barcode Detection, Mask Visualization, Crop Visualization, Clip Comparison, Pixel Color Count, Relative Static Crop, Stitch Images, Instance Segmentation Model, Buffer, Ellipse Visualization, Image Blur, Dominant Color, Halo Visualization, Reference Path Visualization, SIFT Comparison, Multi-Label Classification Model, Image Preprocessing, Roboflow Dataset Upload, OpenAI, Classification Label Visualization, CLIP Embedding Model, Blur Visualization, Polygon Zone Visualization, Object Detection Model, Trace Visualization, Bounding Box Visualization, Stability AI Image Generation

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Camera Calibration in version v1 has.

Bindings

• input

  • image (image): Image to remove distortions from.
  • fx (float): Focal length along the x-axis.
  • fy (float): Focal length along the y-axis.
  • cx (float): Optical center along the x-axis.
  • cy (float): Optical center along the y-axis.
  • k1 (float): Radial distortion coefficient k1.
  • k2 (float): Radial distortion coefficient k2.
  • k3 (float): Radial distortion coefficient k3.
  • p1 (float): Distortion coefficient p1.
  • p2 (float): Distortion coefficient p2.

• output

  • calibrated_image (image): Image in workflows.

Example JSON definition of step Camera Calibration in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/camera-calibration@v1",
    "image": "$inputs.image",
    "fx": 0.123,
    "fy": 0.123,
    "cx": 0.123,
    "cy": 0.123,
    "k1": 0.123,
    "k2": 0.123,
    "k3": 0.123,
    "p1": 0.123,
    "p2": 0.123
}