boofcv.examples.sfm
Class ExamplePnP
- java.lang.Object
-
- boofcv.examples.sfm.ExamplePnP
-
public class ExamplePnP extends java.lang.ObjectThe Perspective-n-Point problem or PnP for short, is a problem where there are N observations of points with known 3D coordinates. The output is the pose of the camera observing the points. The minimal solution requires 3-points but produces multiple solutions. BoofCV provide several solutions to the PnP problem and the example below demonstrates how to use them.
-
-
Constructor Summary
Constructors Constructor and Description ExamplePnP()
-
Method Summary
All Methods Static Methods Instance Methods Concrete Methods Modifier and Type Method and Description voidaddOutliers(java.util.List<Point2D3D> observations, int total)Adds some really bad observations to the mixjava.util.List<Point2D3D>createObservations(Se3_F64 worldToCamera, int total)Generates synthetic observations randomly in front of the cameraSe3_F64estimateNoOutliers(java.util.List<Point2D3D> observations)Assumes all observations actually match the correct/real 3D pointSe3_F64estimateOutliers(java.util.List<Point2D3D> observations)Uses robust techniques to remove outliersstatic voidmain(java.lang.String[] args)
-
-
-
Method Detail
-
main
public static void main(java.lang.String[] args)
-
estimateNoOutliers
public Se3_F64 estimateNoOutliers(java.util.List<Point2D3D> observations)
Assumes all observations actually match the correct/real 3D point
-
estimateOutliers
public Se3_F64 estimateOutliers(java.util.List<Point2D3D> observations)
Uses robust techniques to remove outliers
-
createObservations
public java.util.List<Point2D3D> createObservations(Se3_F64 worldToCamera, int total)
Generates synthetic observations randomly in front of the camera
-
addOutliers
public void addOutliers(java.util.List<Point2D3D> observations, int total)
Adds some really bad observations to the mix
-
-
DataMelt 3.0 © DataMelt by jWork.ORG