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

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
}