Example Stereo Disparity - Revision history

Peter at 01:03, 3 September 2022

2022-09-03T01:03:15Z

← Older revision		Revision as of 01:03, 3 September 2022
Line 19:		Line 19:
	* [[Example_Rectification_Calibrated\| Rectifying Calibrated Cameras]]		* [[Example_Rectification_Calibrated\| Rectifying Calibrated Cameras]]
	* [[Example_Stereo_Single_Camera\| Stereo from Single Camera Example]]		* [[Example_Stereo_Single_Camera\| Stereo from Single Camera Example]]
			* [[Example_Stereo_Mesh\| Disparity to Mesh]]
			* [[Example_Stereo_Disparity_3D\| Disparity to Point Cloud]]

	Related Videos		Related Videos

Peter at 00:52, 3 September 2022

2022-09-03T00:52:33Z

← Older revision		Revision as of 00:52, 3 September 2022
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

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

	Concepts:		Concepts:
Line 92:		Line 92:
	config.maxPerPixelError = 35;		config.maxPerPixelError = 35;
	config.validateRtoL = 1;		config.validateRtoL = 1;
	config.texture = 0.2;		config.texture = 0.05;
	StereoDisparity<GrayU8, GrayF32> disparityAlg =		StereoDisparity<GrayU8, GrayF32> disparityAlg =
	FactoryStereoDisparity.blockMatchBest5(config, GrayU8.class, GrayF32.class);		FactoryStereoDisparity.blockMatchBest5(config, GrayU8.class, GrayF32.class);

Peter at 00:33, 18 January 2022

2022-01-18T00:33:33Z

← Older revision		Revision as of 00:33, 18 January 2022
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.38/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.40/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]

	Concepts:		Concepts:
Line 57:		Line 57:
	// A slower but more accuracy algorithm is selected		// A slower but more accuracy algorithm is selected
	// All of these parameters should be turned		// All of these parameters should be turned
	~~ConfigDisparityBMBest5~~ config = new ConfigDisparityBMBest5();		var config = new ConfigDisparityBMBest5();
	config.errorType = DisparityError.CENSUS;		config.errorType = DisparityError.CENSUS;
	config.disparityMin = disparityMin;		config.disparityMin = disparityMin;
Line 84:		Line 84:
	// A slower but more accuracy algorithm is selected		// A slower but more accuracy algorithm is selected
	// All of these parameters should be turned		// All of these parameters should be turned
	~~ConfigDisparityBMBest5~~ config = new ConfigDisparityBMBest5();		var config = new ConfigDisparityBMBest5();
	config.errorType = DisparityError.CENSUS;		config.errorType = DisparityError.CENSUS;
	config.disparityMin = disparityMin;		config.disparityMin = disparityMin;
Line 128:		Line 128:

	// undistorted and rectify images		// undistorted and rectify images
	~~FMatrixRMaj~~ rect1_F32 = new FMatrixRMaj(3, 3);		var rect1_F32 = new FMatrixRMaj(3, 3);
	~~FMatrixRMaj~~ rect2_F32 = new FMatrixRMaj(3, 3);		var rect2_F32 = new FMatrixRMaj(3, 3);
	ConvertMatrixData.convert(rect1, rect1_F32);		ConvertMatrixData.convert(rect1, rect1_F32);
	ConvertMatrixData.convert(rect2, rect2_F32);		ConvertMatrixData.convert(rect2, rect2_F32);
Line 171:		Line 171:
	BufferedImage visualized = VisualizeImageData.disparity(disparity, null, disparityRange, 0);		BufferedImage visualized = VisualizeImageData.disparity(disparity, null, disparityRange, 0);

	~~ListDisplayPanel~~ gui = new ListDisplayPanel();		var gui = new ListDisplayPanel();
	gui.addImage(rectLeft, "Rectified");		gui.addImage(rectLeft, "Rectified");
	gui.addImage(visualized, "Disparity");		gui.addImage(visualized, "Disparity");

Peter at 20:12, 12 July 2021

2021-07-12T20:12:47Z

← Older revision		Revision as of 20:12, 12 July 2021
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

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

	Concepts:		Concepts:

Peter at 02:49, 22 December 2020

2020-12-22T02:49:47Z

Show changes

Peter at 04:51, 22 June 2020

2020-06-22T04:51:30Z

← Older revision		Revision as of 04:51, 22 June 2020
Line 19:		Line 19:
	* [[Example_Rectification_Calibrated\| Rectifying Calibrated Cameras]]		* [[Example_Rectification_Calibrated\| Rectifying Calibrated Cameras]]
	* [[Example_Stereo_Single_Camera\| Stereo from Single Camera Example]]		* [[Example_Stereo_Single_Camera\| Stereo from Single Camera Example]]

			Related Videos
			* [https://www.youtube.com/watch?v=8pn9Ebw90uk&t=672s Stereo Update 2020]

	= Example Code =		= Example Code =

Peter at 05:33, 18 May 2020

2020-05-18T05:33:52Z

← Older revision		Revision as of 05:33, 18 May 2020
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.35/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.36/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]

	Concepts:		Concepts:
Line 18:		Line 18:
	Related Examples:		Related Examples:
	* [[Example_Rectification_Calibrated\| Rectifying Calibrated Cameras]]		* [[Example_Rectification_Calibrated\| Rectifying Calibrated Cameras]]
	* [[Example_Rectification_Uncalibrated\| Rectifying Uncalibrated Cameras]]
	* [[Example_Stereo_Single_Camera\| Stereo from Single Camera Example]]		* [[Example_Stereo_Single_Camera\| Stereo from Single Camera Example]]

Line 126:		Line 125:

	// Adjust the rectification to make the view area more useful		// Adjust the rectification to make the view area more useful
	RectifyImageOps.allInsideLeft(param.left~~, null~~, rect1, rect2, rectK, null);		RectifyImageOps.allInsideLeft(param.left, rect1, rect2, rectK, null);

	// undistorted and rectify images		// undistorted and rectify images

Peter at 01:05, 24 December 2019

2019-12-24T01:05:55Z

← Older revision		Revision as of 01:05, 24 December 2019
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.33/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.35/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]

	Concepts:		Concepts:
Line 47:		Line 47:
	* @param regionSize Radius of region being matched		* @param regionSize Radius of region being matched
	* @param minDisparity Minimum disparity that is considered		* @param minDisparity Minimum disparity that is considered
	* @param ~~maxDisparity Maximum~~ disparity ~~that is~~ considered		* @param rangeDisparity Number of disparity values considered.
	* @return Disparity image		* @return Disparity image
	*/		*/
	public static GrayU8 denseDisparity(GrayU8 rectLeft , GrayU8 rectRight ,		public static GrayU8 denseDisparity(GrayU8 rectLeft , GrayU8 rectRight ,
	int regionSize,		int regionSize,
	int minDisparity , int ~~maxDisparity~~ )		int minDisparity , int rangeDisparity )
	{		{
	// A slower but more accuracy algorithm is selected		// A slower but more accuracy algorithm is selected
	// All of these parameters should be turned		// All of these parameters should be turned
	StereoDisparity<GrayU8,GrayU8> disparityAlg =		ConfigDisparityBMBest5 config = new ConfigDisparityBMBest5();
	FactoryStereoDisparity.~~regionWta~~(~~DisparityAlgorithms.RECT_FIVE~~,		config.errorType = DisparityError.CENSUS;
	~~minDisparity, maxDisparity, regionSize, regionSize, 25, 1, 0~~.2, GrayU8.class);		config.disparityMin = minDisparity;
			config.disparityRange = rangeDisparity;
			config.subpixel = false;
			config.regionRadiusX = config.regionRadiusY = regionSize;
			config.maxPerPixelError = 35;
			config.validateRtoL = 1;
			config.texture = 0.2;
			StereoDisparity<GrayU8, GrayU8> disparityAlg =
			FactoryStereoDisparity.blockMatchBest5(config, GrayU8.class, GrayU8.class);

	// process and return the results		// process and return the results
Line 72:		Line 80:
	public static GrayF32 denseDisparitySubpixel(GrayU8 rectLeft , GrayU8 rectRight ,		public static GrayF32 denseDisparitySubpixel(GrayU8 rectLeft , GrayU8 rectRight ,
	int regionSize ,		int regionSize ,
	int minDisparity , int ~~maxDisparity~~ )		int minDisparity , int rangeDisparity )
	{		{
	// A slower but more accuracy algorithm is selected		// A slower but more accuracy algorithm is selected
	// All of these parameters should be turned		// All of these parameters should be turned
	StereoDisparity<GrayU8,GrayF32> disparityAlg =		ConfigDisparityBMBest5 config = new ConfigDisparityBMBest5();
	FactoryStereoDisparity.~~regionSubpixelWta~~(~~DisparityAlgorithms.RECT_FIVE~~,		config.errorType = DisparityError.CENSUS;
	~~minDisparity, maxDisparity, regionSize, regionSize, 25, 1, 0~~.2, ~~GrayU8~~.class);		config.disparityMin = minDisparity;
			config.disparityRange = rangeDisparity;
			config.subpixel = true;
			config.regionRadiusX = config.regionRadiusY = regionSize;
			config.maxPerPixelError = 35;
			config.validateRtoL = 1;
			config.texture = 0.2;
			StereoDisparity<GrayU8, GrayF32> disparityAlg =
			FactoryStereoDisparity.blockMatchBest5(config, GrayU8.class, GrayF32.class);

	// process and return the results		// process and return the results
Line 110:		Line 126:

	// Adjust the rectification to make the view area more useful		// Adjust the rectification to make the view area more useful
	RectifyImageOps.allInsideLeft(param.left, rect1, rect2, rectK);		RectifyImageOps.allInsideLeft(param.left, null, rect1, rect2, rectK, null);

	// undistorted and rectify images		// undistorted and rectify images
Line 153:		Line 169:

	// show results		// show results
	BufferedImage visualized = VisualizeImageData.disparity(disparity, null~~,10~~,60,0);		BufferedImage visualized = VisualizeImageData.disparity(disparity, null,60,0);

	ListDisplayPanel gui = new ListDisplayPanel();		ListDisplayPanel gui = new ListDisplayPanel();

Peter at 15:04, 15 March 2019

2019-03-15T15:04:56Z

← Older revision		Revision as of 15:04, 15 March 2019
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.31/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.33/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]

	Concepts:		Concepts:

Peter at 03:11, 17 October 2018

2018-10-17T03:11:00Z

← Older revision		Revision as of 03:11, 17 October 2018
Line 9:		Line 9:
	For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.		For visualization purposes the disparity is encoded using a color histogram. Hotter colors indicate closer objects while cooler objects indicate objects that are farther away. Cameras must be accurate calibrated or else an error of a few pixels will drastically degrade performance. A common preprocessing step is to run a Laplacian of Gaussian edge detector across the image to provide invariance to lighting conditions. This was not done below because the cameras have their gain synchronized.

	Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.27/examples/src/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]		Example File: [https://github.com/lessthanoptimal/BoofCV/blob/v0.31/examples/src/main/java/boofcv/examples/stereo/ExampleStereoDisparity.java ExampleStereoDisparity.java]

	Concepts:		Concepts:
Line 98:		Line 98:

	// original camera calibration matrices		// original camera calibration matrices
	DMatrixRMaj K1 = PerspectiveOps.~~calibrationMatrix~~(param.getLeft(), (DMatrixRMaj)null);		DMatrixRMaj K1 = PerspectiveOps.pinholeToMatrix(param.getLeft(), (DMatrixRMaj)null);
	DMatrixRMaj K2 = PerspectiveOps.~~calibrationMatrix~~(param.getRight(), (DMatrixRMaj)null);		DMatrixRMaj K2 = PerspectiveOps.pinholeToMatrix(param.getRight(), (DMatrixRMaj)null);

	rectifyAlg.process(K1,new Se3_F64(),K2,leftToRight);		rectifyAlg.process(K1,new Se3_F64(),K2,leftToRight);