boofcv.examples.geometry

Class ExampleImageStitching

java.lang.Object

boofcv.examples.geometry.ExampleImageStitching

public class ExampleImageStitching
extends java.lang.Object

Exampling showing how to combines two images together by finding the best fit image transform with point features.

Algorithm Steps:

1. Detect feature locations
2. Compute feature descriptors
3. Associate features together
4. Use robust fitting to find transform
5. Render combined image

Constructor Summary

Constructors

Constructor and Description
ExampleImageStitching()

Method Summary

Modifier and Type	Method and Description
static <T extends ImageGray,FD extends TupleDesc> Homography2D_F64	computeTransform(T imageA, T imageB, DetectDescribePoint<T,FD> detDesc, AssociateDescription<FD> associate, ModelMatcher<Homography2D_F64,AssociatedPair> modelMatcher) Using abstracted code, find a transform which minimizes the difference between corresponding features in both images.
static void	main(java.lang.String[] args)
static void	renderStitching(java.awt.image.BufferedImage imageA, java.awt.image.BufferedImage imageB, Homography2D_F64 fromAtoB) Renders and displays the stitched together images
static <T extends ImageGray> void	stitch(java.awt.image.BufferedImage imageA, java.awt.image.BufferedImage imageB, java.lang.Class<T> imageType) Given two input images create and display an image where the two have been overlayed on top of each other.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ExampleImageStitching

public ExampleImageStitching()

Method Detail

computeTransform

public static <T extends ImageGray,FD extends TupleDesc> Homography2D_F64 computeTransform(T imageA,
                                                                                           T imageB,
                                                                                           DetectDescribePoint<T,FD> detDesc,
                                                                                           AssociateDescription<FD> associate,
                                                                                           ModelMatcher<Homography2D_F64,AssociatedPair> modelMatcher)

Using abstracted code, find a transform which minimizes the difference between corresponding features in both images. This code is completely model independent and is the core algorithms.

stitch

public static <T extends ImageGray> void stitch(java.awt.image.BufferedImage imageA,
                                                java.awt.image.BufferedImage imageB,
                                                java.lang.Class<T> imageType)

Given two input images create and display an image where the two have been overlayed on top of each other.

renderStitching

public static void renderStitching(java.awt.image.BufferedImage imageA,
                                   java.awt.image.BufferedImage imageB,
                                   Homography2D_F64 fromAtoB)

Renders and displays the stitched together images

main

public static void main(java.lang.String[] args)