Example Calibrate Planar Fisheye - Revision history

Peter at 02:04, 10 September 2023

2023-09-10T02:04:53Z

← Older revision		Revision as of 02:04, 10 September 2023
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.41/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v1.1.0/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 69:		Line 69:
	// Need to tell it the image shape and the layout once		// Need to tell it the image shape and the layout once
	if (usedImages.isEmpty())		if (usedImages.isEmpty())
	calibrator.initialize(image.getWidth(), image.getHeight(), detector.getLayout());		calibrator.initialize(image.getWidth(), image.getHeight(), List.of(detector.getLayout()));
	calibrator.addImage(detector.getDetectedPoints().copy());		calibrator.addImage(detector.getDetectedPoints().copy());
	usedImages.add(n);		usedImages.add(n);

Peter at 20:19, 2 September 2022

2022-09-02T20:19:00Z

← Older revision		Revision as of 20:19, 2 September 2022
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.40/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.41/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 49:		Line 49:

	// Declare and setup the calibration algorithm		// Declare and setup the calibration algorithm
	var ~~calibrationAlg~~ = new CalibrateMonoPlanar(~~detector.getLayout()~~);		var calibrator = new CalibrateMonoPlanar();

	// Specify the camera model to use. Here are a few examples.		// Specify the camera model to use. Here are a few examples.
	//		//
	~~calibrationAlg~~.configureUniversalOmni( /zeroSkew/ true, /radial/ 2, /tangential/ false);		calibrator.configureUniversalOmni( /zeroSkew/ true, /radial/ 2, /tangential/ false);
	// it's also possible to fix the mirror offset parameter		// it's also possible to fix the mirror offset parameter
	// 0 = pinhole camera. 1 = fisheye		// 0 = pinhole camera. 1 = fisheye
Line 60:		Line 60:
	// calibrationAlg.configureKannalaBrandt( /zeroSkew/ true, /symmetric/ 5, /asymmetric/ 0);		// calibrationAlg.configureKannalaBrandt( /zeroSkew/ true, /symmetric/ 5, /asymmetric/ 0);

			var usedImages = new ArrayList<String>();
	for (String n : images) {		for (String n : images) {
	BufferedImage input = UtilImageIO.loadImage(n);		BufferedImage input = UtilImageIO.loadImage(n);
Line 66:		Line 67:
	GrayF32 image = ConvertBufferedImage.convertFrom(input, (GrayF32)null);		GrayF32 image = ConvertBufferedImage.convertFrom(input, (GrayF32)null);
	if (detector.process(image)) {		if (detector.process(image)) {
	~~calibrationAlg~~.addImage(detector.getDetectedPoints().copy());		// Need to tell it the image shape and the layout once
			if (usedImages.isEmpty())
			calibrator.initialize(image.getWidth(), image.getHeight(), detector.getLayout());
			calibrator.addImage(detector.getDetectedPoints().copy());
			usedImages.add(n);
	} else {		} else {
	System.err.println("Failed to detect target in " + n);		System.err.println("Failed to detect target in " + n);
Line 72:		Line 77:
	}		}
	// process and compute intrinsic parameters		// process and compute intrinsic parameters
	CameraModel intrinsic = ~~calibrationAlg~~.process();		CameraModel intrinsic = calibrator.process();

	// save results to a file and print out		// save results to a file and print out
	CalibrationIO.save(intrinsic, "fisheye.yaml");		CalibrationIO.save(intrinsic, "fisheye.yaml");

	~~calibrationAlg~~.~~printStatistics~~(~~System~~.~~out~~);		System.out.println(calibrator.computeQualityText(usedImages));
	System.out.println();		System.out.println();
	System.out.println("--- Intrinsic Parameters ---");		System.out.println("--- Intrinsic Parameters ---");

Peter at 20:21, 17 January 2022

2022-01-17T20:21:58Z

← Older revision		Revision as of 20:21, 17 January 2022
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.39/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.40/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 36:		Line 36:
	public static void main( String[] args ) {		public static void main( String[] args ) {
	DetectSingleFiducialCalibration detector;		DetectSingleFiducialCalibration detector;
	~~List<String> images;~~

	// Circle based calibration targets are not recommended because the sever lens distortion will change		// Circle based calibration targets are not recommended because the sever lens distortion will change
Line 47:		Line 46:
	// Chessboard Example		// Chessboard Example
	detector = FactoryFiducialCalibration.chessboardX(null, new ConfigGridDimen(/rows/7, /cols/5, /size/30));		detector = FactoryFiducialCalibration.chessboardX(null, new ConfigGridDimen(/rows/7, /cols/5, /size/30));
	images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/chessboard"));		List<String> images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/chessboard"));

	// Declare and setup the calibration algorithm		// Declare and setup the calibration algorithm
Line 63:		Line 62:
	for (String n : images) {		for (String n : images) {
	BufferedImage input = UtilImageIO.loadImage(n);		BufferedImage input = UtilImageIO.loadImage(n);
	if (input != null) {		if (input == null)
	GrayF32 image = ConvertBufferedImage.convertFrom(input, (GrayF32)null);		continue;
	if (detector.process(image)) {		GrayF32 image = ConvertBufferedImage.convertFrom(input, (GrayF32)null);
	calibrationAlg.addImage(detector.getDetectedPoints().copy());		if (detector.process(image)) {
	} else {		calibrationAlg.addImage(detector.getDetectedPoints().copy());
	System.err.println("Failed to detect target in " + n);		} else {
	}		System.err.println("Failed to detect target in " + n);
	}		}
	}		}

Peter at 02:58, 9 October 2021

2021-10-09T02:58:55Z

← Older revision		Revision as of 02:58, 9 October 2021
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.38/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.39/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 30:		Line 30:
	* see at a distance and cover more of the fisheye's camera large FOV.		* see at a distance and cover more of the fisheye's camera large FOV.
	*		*
			* @author Peter Abeles
	* @see CalibrateMonoPlanar		* @see CalibrateMonoPlanar
	*
	* @author Peter Abeles
	*/		*/
	public class ExampleCalibrateFisheye {		public class ExampleCalibrateFisheye {
	public static void main( String[] args ) {		public static void main( String[] args ) {
	~~DetectorFiducialCalibration~~ detector;		DetectSingleFiducialCalibration detector;
	List<String> images;		List<String> images;

	// Circle based calibration targets ~~not~~ not recommended because the sever lens distortion will change		// Circle based calibration targets are not recommended because the sever lens distortion will change
	// the apparent location of tangent points.		// the apparent location of tangent points.

	// Square Grid example		// Square Grid example
	// detector = FactoryFiducialCalibration.squareGrid(null, new ConfigGridDimen(4, 3, 30, 30));		// detector = FactoryFiducialCalibration.squareGrid(null, new ConfigGridDimen(/rows/ 4, /cols/ 3, /size/ 30, /space/ 30));
	// images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/square_grid"));		// images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/square_grid"));

	// Chessboard Example		// Chessboard Example
	detector = FactoryFiducialCalibration.chessboardX(null,new ConfigGridDimen(7, 5, 30));		detector = FactoryFiducialCalibration.chessboardX(null, new ConfigGridDimen(/rows/7, /cols/5, /size/30));
	images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/chessboard"));		images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/chessboard"));

	// Declare and setup the calibration algorithm		// Declare and setup the calibration algorithm
	~~CalibrateMonoPlanar~~ calibrationAlg = new CalibrateMonoPlanar(detector.getLayout());		var calibrationAlg = new CalibrateMonoPlanar(detector.getLayout());

	~~// tell it type type of target and which parameters to estimate~~
	~~calibrationAlg.configureUniversalOmni( true, 2, false~~);

			// Specify the camera model to use. Here are a few examples.
			//
			calibrationAlg.configureUniversalOmni( /zeroSkew/ true, /radial/ 2, /tangential/ false);
	// it's also possible to fix the mirror offset parameter		// it's also possible to fix the mirror offset parameter
	// 0 = pinhole camera. 1 = fisheye		// 0 = pinhole camera. 1 = fisheye
	// calibrationAlg.configureUniversalOmni( true, 2, false,1.0);		// calibrationAlg.configureUniversalOmni( /zeroSkew/ true, /radial/ 2, /tangential/ false, /offset/ 1.0);
			// Another popular model is Kannala-Brandt. Most people just use the symmetric terms.
			// calibrationAlg.configureKannalaBrandt( /zeroSkew/ true, /symmetric/ 5, /asymmetric/ 0);

	for( String n : images ) {		for (String n : images) {
	BufferedImage input = UtilImageIO.loadImage(n);		BufferedImage input = UtilImageIO.loadImage(n);
	if( input != null ) {		if (input != null) {
	GrayF32 image = ConvertBufferedImage.convertFrom(input,(GrayF32)null);		GrayF32 image = ConvertBufferedImage.convertFrom(input, (GrayF32)null);
	if( detector.process(image)) {		if (detector.process(image)) {
	calibrationAlg.addImage(detector.getDetectedPoints().copy());		calibrationAlg.addImage(detector.getDetectedPoints().copy());
	} else {		} else {
Line 72:		Line 73:
	}		}
	// process and compute intrinsic parameters		// process and compute intrinsic parameters
	~~CameraUniversalOmni~~ intrinsic = calibrationAlg.process();		CameraModel intrinsic = calibrationAlg.process();

	// save results to a file and print out		// save results to a file and print out

Peter at 17:01, 12 July 2021

2021-07-12T17:01:37Z

← Older revision		Revision as of 17:01, 12 July 2021
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.37/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.38/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 77:		Line 77:
	CalibrationIO.save(intrinsic, "fisheye.yaml");		CalibrationIO.save(intrinsic, "fisheye.yaml");

	calibrationAlg.printStatistics();		calibrationAlg.printStatistics(System.out);
	System.out.println();		System.out.println();
	System.out.println("--- Intrinsic Parameters ---");		System.out.println("--- Intrinsic Parameters ---");

Peter at 19:42, 21 December 2020

2020-12-21T19:42:56Z

← Older revision		Revision as of 19:42, 21 December 2020
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.35/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.37/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 35:		Line 35:
	*/		*/
	public class ExampleCalibrateFisheye {		public class ExampleCalibrateFisheye {
	public static void main( String ~~args~~[] ) {		public static void main( String[] args ) {
	DetectorFiducialCalibration detector;		DetectorFiducialCalibration detector;
	List<String> images;		List<String> images;

Peter at 00:55, 24 December 2019

2019-12-24T00:55:28Z

← Older revision		Revision as of 00:55, 24 December 2019
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.29/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.35/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 43:		Line 43:

	// Square Grid example		// Square Grid example
	// detector = FactoryFiducialCalibration.squareGrid(new ~~ConfigSquareGrid~~(4, 3, 30, 30));		// detector = FactoryFiducialCalibration.squareGrid(null, new ConfigGridDimen(4, 3, 30, 30));
	// images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/square_grid"));		// images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/square_grid"));

	// Chessboard Example		// Chessboard Example
	detector = FactoryFiducialCalibration.~~chessboard~~(new ~~ConfigChessboard~~(7, 5, 30));		detector = FactoryFiducialCalibration.chessboardX(null,new ConfigGridDimen(7, 5, 30));
	images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/chessboard"));		images = UtilIO.listAll(UtilIO.pathExample("calibration/fisheye/chessboard"));

Peter at 02:55, 19 March 2018

2018-03-19T02:55:14Z

← Older revision		Revision as of 02:55, 19 March 2018
Line 7:		Line 7:
	This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.		This example demonstrates how to compute the intrinsic camera parameters for a fisheye camera lens. Fisheye lenses exhibit significantly more distortion than regular lenses with a more narrow field of view. Its not unusual for a fisheye lens to have a FOV of 185 degrees. The calibration process is very similar to regular cameras. A planar calibration target is shown at different angles across the entire field of view. The main difference is the camera model.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.28/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.29/examples/src/main/java/boofcv/examples/calibration/ExampleCalibrateFisheye.java ExampleCalibrateFisheye.java]

	Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]		Calibration Tutorial: [[Tutorial_Camera_Calibration\|Wikipage]]
Line 51:		Line 51:

	// Declare and setup the calibration algorithm		// Declare and setup the calibration algorithm
	CalibrateMonoPlanar calibrationAlg = new CalibrateMonoPlanar(detector);		CalibrateMonoPlanar calibrationAlg = new CalibrateMonoPlanar(detector.getLayout());

	// tell it type type of target and which parameters to estimate		// tell it type type of target and which parameters to estimate
Line 64:		Line 64:
	if( input != null ) {		if( input != null ) {
	GrayF32 image = ConvertBufferedImage.convertFrom(input,(GrayF32)null);		GrayF32 image = ConvertBufferedImage.convertFrom(input,(GrayF32)null);
	if( !calibrationAlg.addImage(~~image~~) )		if( detector.process(image)) {
	System.err.println("Failed to detect target in "+n);		calibrationAlg.addImage(detector.getDetectedPoints().copy());
			} else {
			System.err.println("Failed to detect target in " + n);
			}
	}		}
	}		}
Line 81:		Line 84:
	}		}
	}		}

	</syntaxhighlight>		</syntaxhighlight>

Peter at 01:01, 21 January 2018

2018-01-21T01:01:35Z

← Older revision		Revision as of 01:01, 21 January 2018
Line 1:		Line 1:
	<center>		<center>
	<gallery heights=400 widths=~~610~~ >		<gallery heights=400 widths=400 >
	Image:Calib_fisheye_chessboard.jpg\|Detected Calibration Target in a Fisheye Camera.		Image:Calib_fisheye_chessboard.jpg\|Detected Calibration Target in a Fisheye Camera.
	</gallery>		</gallery>

Peter at 00:11, 21 January 2018

2018-01-21T00:11:49Z

← Older revision		Revision as of 00:11, 21 January 2018
Line 15:		Line 15:
	* Fisheye Lens distortion		* Fisheye Lens distortion
	* Intrinsic parameters		* Intrinsic parameters

			Relevant Videos:
			* [https://youtu.be/TGg-xgTyaU8?t=69 YouTube Video]

	Related Examples:		Related Examples: