Angular point detection in OpenCV sub-pixel

Sub-pixel angular point detection target

In this tutorial we will cover the following:

• Use the OPENCV function Cornersubpix to find a more precise corner position (not a position of the integer type, but a more precise floating-point type position).

Theoretical code

The code for this tutorial is shown below. The source code can also be downloaded from this link

#include "opencv2/highgui/highgui.hpp"#include "opencv2/imgproc/imgproc.hpp"#include <iostream>#include <stdio.h>#include <stdlib.h>UsingNamespaceCv;UsingNamespaceStd;Global variablesMatSrc,Src_gray;IntMaxcorners=10;IntMaxtrackbar=25;RNGRng(12345);Char*Source_window="Image";Function HeadervoidGoodfeaturestotrack_demo(Int,void*);/** @function Main */IntMain(Intargc,Char**Argv){Load source image and convert it to graySrc=Imread(Argv[1],1);Cvtcolor(Src,Src_gray,Cv_bgr2gray);Create WindowNamedwindow(Source_window,Cv_window_autosize);Create Trackbar to set the number of cornersCreatetrackbar("Max Corners:",Source_window,&Maxcorners,Maxtrackbar,Goodfeaturestotrack_demo);Imshow(Source_window,Src);Goodfeaturestotrack_demo(0,0);Waitkey(0);Return(0);}/*** @function Goodfeaturestotrack_demo.cpp* @brief Apply Shi-tomasi Corner Detector*/voidGoodfeaturestotrack_demo(Int,void*){If(Maxcorners<1){Maxcorners=1;}Parameters for Shi-tomasi algorithmVector<point2f>Corners;DoubleQualitylevel=0.01;DoubleMindistance=10;IntBlockSize=3;boolUseharrisdetector=False;DoubleK=0.04;Copy the source imageMatCopy;Copy=Src.Clone();Apply Corner DetectionGoodfeaturestotrack(Src_gray,Corners,Maxcorners,Qualitylevel,Mindistance,Mat(),BlockSize,Useharrisdetector,K);Draw Corners Detectedcout<<"* * Number of corners detected:"<<Corners.Size()<<Endl;IntR=4;For(IntI=0;I<Corners.Size();I++){Circle(Copy,Corners[I],R,Scalar(Rng.Uniform(0,255),Rng.Uniform(0,255),Rng.Uniform(0,255)),-1,8,0);}Show You gotNamedwindow(Source_window,Cv_window_autosize);Imshow(Source_window,Copy);Set the neeed parameters to find the refined cornersSizeWinsize=Size(5,5);SizeZerozone=Size(-1,-1);TermcriteriaCriteria=Termcriteria(Cv_termcrit_eps+Cv_termcrit_iter,40,0.001);Calculate the refined corner locationsCornersubpix(Src_gray,Corners,Winsize,Zerozone,Criteria);Write them downFor(IntI=0;I<corners. Size (); i++ ) {cout< < "--refined Corner [" <<i<< "] (" <<corners[i . x<< "," <<corners< Span class= "p" >[i]. Y<<<<endl }}             

Interpreting the results

Sub-pixel Corner detection results:

Translators

Shuai Zheng, <[email protected], http://www.cbsr.ia.ac.cn/users/szheng/

from:http://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/features2d/trackingmotion/corner_subpixeles/ Corner_subpixeles.html#corner-subpixeles

Angular point detection in OpenCV sub-pixel