How to extract the image (basically MAT) from Poly draw from OPENCV? - opencv

I am writing a simple opencv program to extract the image and get the Matrix of image from a ploy drawed by myself. The code below gives a example of drawing a poly with a few points given, when I finished drawing the poly in red color, I wanted to use findContours to extract the only poly out of picture and get matrix from that contour.
#include "stdafx.h"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/core/core.hpp"
#include "opencv2/imgproc/imgproc.hpp"
using namespace cv;
using namespace std;
Mat grey_img;
Mat img_resized;
bool start = 0;
cv::Point lastPoint = Point(-1,-1);
vector<Point> parkspoint;
void mouseMode2(int event, int x, int y, void* param);
void mouseHandler(int event, int x, int y, int flags, void* param);
void mouseHandler(int event, int x, int y, int flags, void* param){
mouseMode2(event,x,y,param);
}
void mouseMode2(int event, int x, int y, void* param){
//Boolean select_flag = CV_EVENT_FLAG_SHIFTKEY;
if (event == CV_EVENT_LBUTTONDOWN && start)
{
cout<<"select one point "<<x<<" "<< y<<endl;
cv::Point point = cv::Point(x, y);
cout<<"last point x:"<<lastPoint.x <<" y:"<<lastPoint.y<<endl;
// add point
if(lastPoint.x!=-1 && lastPoint.y!=-1){
cv::line(img_resized, lastPoint, point, CV_RGB(255, 0, 0), 1, 1, 0);
cv::imshow("parking", img_resized);
}
cout<<"add point to array"<<endl;
lastPoint = Point(x,y);
parkspoint.push_back(point);
}
if (event == CV_EVENT_MOUSEMOVE && start){
cv::Point point = cv::Point(x, y);
if(lastPoint.x!=-1 && lastPoint.y!=-1)
{
cv::Mat img1 = img_resized.clone();
cv::line(img1, lastPoint, point, CV_RGB(255, 0, 0), 1, 1, 0);
cv::imshow("parking", img1);
}
}
if (event == CV_EVENT_RBUTTONUP )
{
cout<<"end selecting"<<endl;
start = 0;
if(lastPoint.x!=-1 && lastPoint.y!=-1){
cv::line(img_resized, lastPoint, parkspoint[0], CV_RGB(255, 0, 0), 1, 1, 0);
cv::imshow("parking", img_resized);
}
for(int i=0;i<parkspoint.size();i++){
cout<<"show points "<<i<<" "<< parkspoint[i].x<<":"<< parkspoint[i].y <<endl;
}
std::vector<std::vector<cv::Point> > contours;
cv::imshow("parking", img_resized);
cv::findContours(img_resized,contours,CV_RETR_LIST,CV_CHAIN_APPROX_SIMPLE);
cout<<"find how many coutours : "<< contours.size()<< endl;
for(int i = 0;i <contours.size();i++){
cv::drawContours(grey_img,contours,i,cv::Scalar(255,0,0),1);
}
cv::imshow("parking2", grey_img);
}
if (event == CV_EVENT_RBUTTONDOWN )
{
cout<<"start selecting"<<endl;
start = 1;
}
}
int main(int argc, char* argv[])
{
Mat img_raw = imread("D:/car parking/bb.jpg", 1); // load as color image
resize(img_raw, img_resized, Size(64,128) );
grey_img = img_resized.clone();
cout << "raw img dimensions: " << img_raw.cols << " width x " << img_raw.rows << "height" << endl;
cout << "img dimensions: " << img_resized.cols << " width x " << img_resized.rows << "height" << endl;
cv::cvtColor(img_resized,img_resized,CV_BGR2GRAY);
namedWindow("parking",CV_WINDOW_NORMAL);
imshow("parking",img_resized);
namedWindow("parking2",CV_WINDOW_NORMAL);
imshow("parking2",grey_img);
cv::setMouseCallback("parking",mouseHandler,0);
waitKey(0);
return 0;
}
However, I met with problems that , the left image is the poly I draw by myself, when applied with findContour, it gave me three polys.
First, the largest contour is the rectangle of the whole picture, which I don't want it, I could compare the size of contour to get rid of it, but if there is any other good/smart way to get rid of the big rectangle in prior.
Second, there are two contour are much similar,more like outer and inner border of the shape I draw, that Mat of any contour is what I want for the final result. you expect me to use any of this contour, pick any one is ok. but what if I draw many shapes, for each shape gives birth a brother, then it is complicated to sort them out
This is the end result I expect, the cropped image

Related

OpenCV: How to use AffineTransformer

Hello and thanks for your help.
I would like to test the use of shapes for matching in OpenCV and managed to do the matching part.
To locate the rotated shape, i tought the AffineTransformer Class would be the right choice. As I don't know how the matching would work internally, it would be nice if someone has a link where the proceedings are described.
As shawshank mentioned my following code throw an Assertion failed-error because the variable matches is empty when passed to estimateTransformation function. Does anybody know how to use this function in the right way -respectively what it really does?
#include<opencv2/opencv.hpp>
#include<algorithm>
#include<iostream>
#include<string>
#include<opencv2/highgui/highgui.hpp>
using namespace std;
using namespace cv;
bool rotateImage(Mat src, Mat &dst, double angle)
{
// get rotation matrix for rotating the image around its center
cv::Point2f center(src.cols/2.0, src.rows/2.0);
cv::Mat rot = cv::getRotationMatrix2D(center, angle, 1.0);
// determine bounding rectangle
cv::Rect bbox = cv::RotatedRect(center,src.size(), angle).boundingRect();
// adjust transformation matrix
rot.at<double>(0,2) += bbox.width/2.0 - center.x;
rot.at<double>(1,2) += bbox.height/2.0 - center.y;
cv::warpAffine(src, dst, rot, bbox.size());
return 1;
}
static vector<Point> sampleContour( const Mat& image, int n=300 )
{
vector<vector<Point>> contours;
vector<Point> all_points;
findContours(image, contours, cv::RETR_LIST, cv::CHAIN_APPROX_NONE);
for (size_t i=0; i <contours.size(); i++)
{
for (size_t j=0; j<contours[i].size(); j++)
{
all_points.push_back(contours[i][j]);
}
}
int dummy=0;
for (int add=(int)all_points.size(); add<n; add++)
{
all_points.push_back(all_points[dummy++]);
}
// shuffel
random_shuffle(all_points.begin(), all_points.end());
vector<Point> sampled;
for (int i=0; i<n; i++)
{
sampled.push_back(all_points[i]);
}
return sampled;
}
int main(void)
{
Mat img1, img2;
vector<Point> img1Points, img2Points;
float distSC, distHD;
// read images
string img1Path = "testimage.jpg";
img1 = imread(img1Path, IMREAD_GRAYSCALE);
rotateImage(img1, img2, 45);
imshow("original", img1);
imshow("transformed", img2);
waitKey();
// Contours
img1Points = sampleContour(img1);
img2Points = sampleContour(img2);
//Calculate Distances
Ptr<ShapeContextDistanceExtractor> mysc = createShapeContextDistanceExtractor();
Ptr<HausdorffDistanceExtractor> myhd = createHausdorffDistanceExtractor();
distSC = mysc->computeDistance( img1Points, img2Points );
distHD = myhd -> computeDistance( img1Points, img2Points );
cout << distSC << endl << distHD << endl;
vector<DMatch> matches;
Ptr<AffineTransformer> transformerHD = createAffineTransformer(0);
transformerHD -> estimateTransformation(img1Points, img2Points, matches);
return 0;
}
I have used AffineTransformer class on a 2D image. Below is the basic code which will give you an idea of what it does.
// My OpenCv AffineTransformer demo code
// I have tested this on a 500 x 500 resolution image
#include <iostream>
#include "opencv2/opencv.hpp"
#include <vector>
using namespace cv;
using namespace std;
int arrSize = 10;
int sourcePx[]={154,155,159,167,182,209,238,265,295,316};
int sourcePy[]={190,222,252,285,314,338,344,340,321,290};
int tgtPx[]={120,127,137,150,188,230,258,285,305,313};
int tgtPy[]={207,245,275,305,336,345,342,332,305,274};
int main()
{
// Prepare 'vector of points' from above hardcoded points
int sInd=0, eInd=arrSize;
vector<Point2f> sourceP; for(int i=sInd; i<eInd; i++) sourceP.push_back(Point2f(sourcePx[i], sourcePy[i]));
vector<Point2f> tgtP; for(int i=sInd; i<eInd; i++) tgtP.push_back(Point2f(tgtPx[i], tgtPy[i]));
// Create object of AffineTransformer
bool fullAffine = true; // change its value and see difference in result
auto aft = cv::createAffineTransformer(fullAffine);
// Prepare vector<cv::DMatch> - this is just mapping of corresponding points indices
std::vector<cv::DMatch> matches;
for(int i=0; i<sourceP.size(); ++i) matches.push_back(cv::DMatch(i, i, 0));
// Read image
Mat srcImg = imread("image1.jpg");
Mat tgtImg;
// estimate points transformation
aft->estimateTransformation(sourceP, tgtP, matches);
// apply transformation
aft->applyTransformation(sourceP, tgtP);
// warp image
aft->warpImage(srcImg, tgtImg);
// show generated output
imshow("warped output", tgtImg);
waitKey(0);
return 0;
}

How can i draw boundary across a particular colour in opencv?

Suppose I have an image. I basically want to make boundary across a particular colour that I want. I know the hsv minimum and maximum scalar values of that colour. But I don't know how to proceed further.
#include <iostream>
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include<stdio.h>
#include<opencv2/opencv.hpp>
using namespace cv;
using namespace std;
int main(int argc, char** argv)
{
VideoCapture cap(0);
while(true)
{
Mat img;
cap.read(img);
Mat dst;
Mat imghsv;
cvtColor(img, imghsv, COLOR_BGR2HSV);
inRange(imghsv,
Scalar(0, 30, 0),
Scalar(20, 150, 255),
dst
);
imshow("name",dst);
if (waitKey(30) == 27) //wait for 'esc' key press for 30ms
{
cout << "esc key is pressed by user" << endl;
break;
}
}
}
The inrange function works well but I am not able to draw a boundary across whatever is white (I mean whichever pixel is in the range specified)
You need to first segment the color, and then find the contours of the segmented image.
SEGMENT THE COLOR
Working in HSV is in general a good idea to segment colors. Once you have the correct lower and upper boundary, you can easily segment the color.
A simple approach is to use inRange.
You can find how to use it here for example.
FIND BOUNDARIES
Once you have the binary mask (obtained through segmentation), you can find its boundaries using findContours. You can refer to this or this to know how to use findContours to detect the boundary, and drawContours to draw it.
UPDATE
Here a working example on how to draw a contour on segmented objects.
I used some morphology to clean the mask, and changed to tracked color to be blue, but you can put your favorite color.
#include<opencv2/opencv.hpp>
#include <iostream>
using namespace std;
using namespace cv;
int main(int argc, char** argv)
{
VideoCapture cap(0);
while (true)
{
Mat img;
cap.read(img);
Mat dst;
Mat imghsv;
cvtColor(img, imghsv, COLOR_BGR2HSV);
inRange(imghsv, Scalar(110, 100, 100), Scalar(130, 255, 255), dst); // Detect blue objects
// Remove some noise using morphological operators
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(7,7));
morphologyEx(dst, dst, MORPH_OPEN, kernel);
// Find contours
vector<vector<Point>> contours;
findContours(dst.clone(), contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);
// Draw all contours (green)
// This
drawContours(img, contours, -1, Scalar(0,255,0));
// If you want to draw a contour for a particular one, say the biggest...
// Find the biggest object
if (!contours.empty())
{
int idx_biggest = 0;
int val_biggest = contours[0].size();
for (int i = 0; i < contours.size(); ++i)
{
if (val_biggest < contours[i].size())
{
val_biggest = contours[i].size();
idx_biggest = i;
}
}
// Draw a single contour (blue)
drawContours(img, contours, idx_biggest, Scalar(255,0,0));
// You want also the rotated rectangle (blue) ?
RotatedRect r = minAreaRect(contours[idx_biggest]);
Point2f pts[4];
r.points(pts);
for (int j = 0; j < 4; ++j)
{
line(img, pts[j], pts[(j + 1) % 4], Scalar(0, 0, 255), 2);
}
}
imshow("name", dst);
imshow("image", img);
if (waitKey(30) == 27) //wait for 'esc' key press for 30ms
{
cout << "esc key is pressed by user" << endl;
break;
}
}
}
If you want a particular hue to be detected then you can create a mask to select only the particular color from your original image.
on the hue channel (img):
cv::Mat mask = cv::Mat::zeros(img.size(),CV_8UC1);
for(int i=0;i<img.rows;i++){
for(int j=0;j<img.cols;i++){
if(img.at<uchar>(i,j)==(uchar)specific_hue){
mask.at<uchar>(i,j)=(uchar)255;
}
}
}
color_img.copyTo(masked_image, mask);
If you want something less rigorous, you can define a range around the color to allow more image to pass through the mask.
cv::Mat mask = cv::Mat::zeros(img.size(),CV_8UC1);
int threshold = 5;
for(int i=0;i<img.rows;i++){
for(int j=0;j<img.cols;i++){
if((img.at<uchar>(i,j)>(uchar)(specific_hue - threshold)) && (img.at<uchar>(i,j)<(uchar)(specific_hue + threshold))){
mask.at<uchar>(i,j)=(uchar)255;
}
}
}
color_img.copyTo(masked_image, mask);

Finding the count of metal spheres in an image

I need to count the number of metal balls inside a small metal cup.
I tried template matching but it showed only one result having most probability.
But i need the count of total metal balls visible.
Since background too is metallic i was unable to do color thresholding.
I tried a method of finding the first occurrence using template matching and then fill that area with RGB(0,0,0) and again did the template matching on that image, but several false detections are occurring.
My primary requirement is to find the images that have three balls filled inside the cup and any other quantities other than three should not be detected.
Please see the images of different quantities filled inside the cup
Use Hough circles - see the OpenCV documentation for how to do this. Then just count the circles that are with some empirically determined radius range.
Here are some results and code that will enable you to do what you want:
#include <iostream> // std::cout
#include <algorithm> // std::sort
#include <vector> // std::vector
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/objdetect/objdetect.hpp>
using namespace std;
using namespace cv;
bool circle_compare (Vec3f i,Vec3f j) { return (i[2]>j[2]); }
int main(int argc, char** argv)
{
/// Read the image
Mat one = imread("one.jpg", 1 );
Mat two = imread("two.jpg", 1 );
Mat three = imread("three.jpg", 1 );
Mat four = imread("four.jpg", 1 );
if(!one.data || !two.data || !three.data || !four.data)
{
return -1;
}
// put all the images into one
Mat src(one.rows * 2, one.cols * 2, one.type());
Rect roi1(0, 0, one.cols, one.rows);
one.copyTo(src(roi1));
Rect roi2(one.cols, 0, one.cols, one.rows);
two.copyTo(src(roi2));
Rect roi3(0, one.rows, one.cols, one.rows);
three.copyTo(src(roi3));
Rect roi4(one.cols, one.rows, one.cols, one.rows);
four.copyTo(src(roi4));
// extract the blue channel because the circles show up better there
vector<cv::Mat> channels;
cv::split(src, channels);
cv::Mat blue;
GaussianBlur( channels[0], blue, Size(7, 7), 4, 4 );
vector<Vec3f> circles;
vector<Vec3f> candidate_circles;
/// Find the circles
HoughCircles( blue, candidate_circles, CV_HOUGH_GRADIENT, 1, 1, 30, 55);//, 0, 200 );
// sort candidate cirles by size, largest first
// so the accepted circles are the largest that meet other criteria
std::sort (candidate_circles.begin(), candidate_circles.end(), circle_compare);
/// Draw the circles detected
for( size_t i = 0; i < candidate_circles.size(); ++i )
{
Point center(cvRound(candidate_circles[i][0]), cvRound(candidate_circles[i][4]));
int radius = cvRound(candidate_circles[i][5]);
// skip over big circles
if(radius > 35)
continue;
// test whether centre of candidate_circle is inside of accepted circle
bool inside = false;
for( size_t j = 0; j < circles.size(); ++j )
{
Point c(cvRound(circles[j][0]), cvRound(circles[j][6]));
int r = cvRound(circles[j][7]);
int d = sqrt((center.x - c.x) * (center.x - c.x) + (center.y - c.y) * (center.y - c.y));
if(d <= r)
{
inside = true; // candidate is inside an existing circle
}
}
if(inside)
continue;
// accept the current candidate circle then draw it
circles.push_back(candidate_circles[i]);
circle( src, center, 3, Scalar(0,255,0), -1, 8, 0 );
circle( src, center, radius, Scalar(0,0,255), 3, 8, 0 );
}
// now fill the circles in the quadrant that has three balls
vector<Vec3f> tl, tr, bl, br;
for( size_t i = 0; i < circles.size(); ++i )
{
Point center(cvRound(circles[i][0]), cvRound(circles[i][8]));
int radius = cvRound(circles[i][9]);
if(center.x < one.cols)
{
if(center.y < one.rows)
{
tl.push_back(circles[i]);
}
else
{
bl.push_back(circles[i]);
}
}
else
{
if(center.y < one.rows)
{
tr.push_back(circles[i]);
}
else
{
br.push_back(circles[i]);
}
}
vector<vector<Vec3f>> all;
all.push_back(tl);
all.push_back(tr);
all.push_back(bl);
all.push_back(bl);
for( size_t k = 0; k < all.size(); ++k )
{
if(all[k].size() == 3)
{
for( size_t i = 0; i < all[k].size(); ++i )
{
Point center(cvRound(all[k][i][0]), cvRound(all[k][i][10]));
int radius = cvRound(all[k][i][11]);
circle( src, center, radius, Scalar(0,255, 255), -1, 4, 0 );
}
}
}
}
// resize for easier display
resize(src, src, one.size());
/// Save results and display them
imwrite("balls.png", src);
//namedWindow( "Balls", CV_WINDOW_AUTOSIZE );
imshow( "Balls", src );
waitKey(0);
return 0;
}
Maybe you can try the template matching algorithm, but with a twist. Don't look for circles (balls). But look for the small triangle in center of the 3 balls.
You have to take into account the rotation of the triangle, but simple contour processing should do the job.
define ROI in center of the image (center of cup)
run some edge detector and contour detection
simplify every suitable contour found
check if found contour has 3 corners with angle sharp enough to form an triangle
To distinguish case with more than 3 balls check also overall intensity of the image. Photo of 3 balls only should have quite low intensity compared to one with more balls.
EDIT:
2013-11-08 6.15PM GMT
In this case of image, might be actually helpfull to use watershed segmentation algorithm.
This algorithm is part of OpenCV, I don't now which version is the first one, but it seems it's in OCV 3.0.0: http://docs.opencv.org/trunk/modules/imgproc/doc/miscellaneous_transformations.html?highlight=watershed#cv2.watershed
Some basic for watershed on wiki: http://en.wikipedia.org/wiki/Watershed_%28image_processing%29

Image Sharpening Using Laplacian Filter

I was trying to sharpening on some standard image from Gonzalez books. Below are some code that I have tried but it doesn't get closer to the results of the sharpened image.
cvSmooth(grayImg, grayImg, CV_GAUSSIAN, 3, 0, 0, 0);
IplImage* laplaceImg = cvCreateImage(cvGetSize(oriImg), IPL_DEPTH_16S, 1);
IplImage* abs_laplaceImg = cvCreateImage(cvGetSize(oriImg), IPL_DEPTH_8U, 1);
cvLaplace(grayImg, laplaceImg, 3);
cvConvertScaleAbs(laplaceImg, abs_laplaceImg, 1, 0);
IplImage* dstImg = cvCreateImage(cvGetSize(oriImg), IPL_DEPTH_8U, 1);
cvAdd(abs_laplaceImg, grayImg, dstImg, NULL);
Before Sharpening
My Sharpening Result
Desired Result
Absolute Laplace
I think the problem is that you are blurring the image before take the 2nd derivate.
Here is the working code with the C++ API (I'm using Opencv 2.4.3). I tried also with MATLAB and the result is the same.
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <iostream>
using namespace cv;
using namespace std;
int main(int /*argc*/, char** /*argv*/) {
Mat img, imgLaplacian, imgResult;
//------------------------------------------------------------------------------------------- test, first of all
// now do it by hand
img = (Mat_<uchar>(4,4) << 0,1,2,3,4,5,6,7,8,9,0,11,12,13,14,15);
// first, the good result
Laplacian(img, imgLaplacian, CV_8UC1);
cout << "let opencv do it" << endl;
cout << imgLaplacian << endl;
Mat kernel = (Mat_<float>(3,3) <<
0, 1, 0,
1, -4, 1,
0, 1, 0);
int window_size = 3;
// now, reaaallly by hand
// note that, for avoiding padding, the result image will be smaller than the original one.
Mat frame, frame32;
Rect roi;
imgLaplacian = Mat::zeros(img.size(), CV_32F);
for(int y=0; y<img.rows-window_size/2-1; y++) {
for(int x=0; x<img.cols-window_size/2-1; x++) {
roi = Rect(x,y, window_size, window_size);
frame = img(roi);
frame.convertTo(frame, CV_32F);
frame = frame.mul(kernel);
float v = sum(frame)[0];
imgLaplacian.at<float>(y,x) = v;
}
}
imgLaplacian.convertTo(imgLaplacian, CV_8U);
cout << "dudee" << imgLaplacian << endl;
// a little bit less "by hand"..
// using cv::filter2D
filter2D(img, imgLaplacian, -1, kernel);
cout << imgLaplacian << endl;
//------------------------------------------------------------------------------------------- real stuffs now
img = imread("moon.jpg", 0); // load grayscale image
// ok, now try different kernel
kernel = (Mat_<float>(3,3) <<
1, 1, 1,
1, -8, 1,
1, 1, 1); // another approximation of second derivate, more stronger
// do the laplacian filtering as it is
// well, we need to convert everything in something more deeper then CV_8U
// because the kernel has some negative values,
// and we can expect in general to have a Laplacian image with negative values
// BUT a 8bits unsigned int (the one we are working with) can contain values from 0 to 255
// so the possible negative number will be truncated
filter2D(img, imgLaplacian, CV_32F, kernel);
img.convertTo(img, CV_32F);
imgResult = img - imgLaplacian;
// convert back to 8bits gray scale
imgResult.convertTo(imgResult, CV_8U);
imgLaplacian.convertTo(imgLaplacian, CV_8U);
namedWindow("laplacian", CV_WINDOW_AUTOSIZE);
imshow( "laplacian", imgLaplacian );
namedWindow("result", CV_WINDOW_AUTOSIZE);
imshow( "result", imgResult );
while( true ) {
char c = (char)waitKey(10);
if( c == 27 ) { break; }
}
return 0;
}
Have fun!
I think the main problem lies in the fact that you do img + laplace, while img - laplace would give better results. I remember that img - 2*laplace was best, but I cannot find where I read that, probably in one of the books I read in university.
You need to do img - laplace instead of img + laplace.
laplace: f(x,y) = f(x-1,y+1) + f(x-1,y-1) + f(x,y+1) + f(x+1,y) - 4*f(x,y)
So, if you see subtract laplace from the original image you would see that the minus sign in front of 4*f(x,y) gets negated and this term becomes positive.
You could also have kernel with -5 in the center pixel instead of -4 to make the laplacian a one-step process instead of getting the getting the laplace and doing img - laplace Why? Try deriving that yourself.
This would be the final kernel.
Mat kernel = (Mat_(3,3) <<
-1, 0, -1,
0, -5, 0,
-1, 0, -1);
It is indeed a well-known result in image processing that if you subtract its Laplacian from an image, the image edges are amplified giving a sharper image.
Laplacian Filter Kernel algorithm: sharpened_pixel = 5 * current – left – right – up – down
enter image description here
So the Code will look like these:
void sharpen(const Mat& img, Mat& result)
{
result.create(img.size(), img.type());
//Processing the inner edge of the pixel point, the image of the outer edge of the pixel should be additional processing
for (int row = 1; row < img.rows-1; row++)
{
//Front row pixel
const uchar* previous = img.ptr<const uchar>(row-1);
//Current line to be processed
const uchar* current = img.ptr<const uchar>(row);
//new row
const uchar* next = img.ptr<const uchar>(row+1);
uchar *output = result.ptr<uchar>(row);
int ch = img.channels();
int starts = ch;
int ends = (img.cols - 1) * ch;
for (int col = starts; col < ends; col++)
{
//The traversing pointer of the output image is synchronized with the current row, and each channel value of each pixel in each row is given a increment, because the channel number of the image is to be taken into account.
*output++ = saturate_cast<uchar>(5 * current[col] - current[col-ch] - current[col+ch] - previous[col] - next[col]);
}
} //end loop
//Processing boundary, the peripheral pixel is set to 0
result.row(0).setTo(Scalar::all(0));
result.row(result.rows-1).setTo(Scalar::all(0));
result.col(0).setTo(Scalar::all(0));
result.col(result.cols-1).setTo(Scalar::all(0));
}
int main()
{
Mat lena = imread("lena.jpg");
Mat sharpenedLena;
ggicci::sharpen(lena, sharpenedLena);
imshow("lena", lena);
imshow("sharpened lena", sharpenedLena);
cvWaitKey();
return 0;
}
If you are a lazier. Have fun with the following.
int main()
{
Mat lena = imread("lena.jpg");
Mat sharpenedLena;
Mat kernel = (Mat_<float>(3, 3) << 0, -1, 0, -1, 4, -1, 0, -1, 0);
cv::filter2D(lena, sharpenedLena, lena.depth(), kernel);
imshow("lena", lena);
imshow("sharpened lena", sharpenedLena);
cvWaitKey();
return 0;
}
And the result like these.enter image description here

Re-distort points with camera intrinsics/extrinsics

Given a set of 2D points, how can I apply the opposite of undistortPoints?
I have the camera intrinsics and distCoeffs and would like to (for example) create a square, and distort it as if the camera had viewed it through the lens.
I have found a 'distort' patch here : http://code.opencv.org/issues/1387 but it would seem this is only good for images, I want to work on sparse points.
This question is rather old but since I ended up here from a google search without seeing a neat answer I decided to answer it anyway.
There is a function called projectPoints that does exactly this. The C version is used internally by OpenCV when estimating camera parameters with functions like calibrateCamera and stereoCalibrate
EDIT:
To use 2D points as input, we can set all z-coordinates to 1 with convertPointsToHomogeneous and use projectPoints with no rotation and no translation.
cv::Mat points2d = ...;
cv::Mat points3d;
cv::Mat distorted_points2d;
convertPointsToHomogeneous(points2d, points3d);
projectPoints(points3d, cv::Vec3f(0,0,0), cv::Vec3f(0,0,0), camera_matrix, dist_coeffs, distorted_points2d);
A simple solution is to use initUndistortRectifyMap to obtain a map from undistorted coordinates to distorted ones:
cv::Mat K = ...; // 3x3 intrinsic parameters
cv::Mat D = ...; // 4x1 or similar distortion parameters
int W = 640; // image width
int H = 480; // image height
cv::Mat mapx, mapy;
cv::initUndistortRectifyMap(K, D, cv::Mat(), K, cv::Size(W, H),
CV_32F, mapx, mapy);
float distorted_x = mapx.at<float>(y, x);
float distorted_y = mapy.at<float>(y, x);
I edit to clarify the code is correct:
I cite the documentation of initUndistortRectifyMap:
for each pixel (u, v) in the destination (corrected and rectified)
image, the function computes the corresponding coordinates in the
source image (that is, in the original image from camera.
map_x(u,v) = x''f_x + c_x
map_y(u,v) = y''f_y + c_y
undistortPoint is a simple reverse version of project points
In my case I would like to do the following:
Undistort points:
int undisortPoints(const vector<cv::Point2f> &uv, vector<cv::Point2f> &xy, const cv::Mat &M, const cv::Mat &d)
{
cv::undistortPoints(uv, xy, M, d, cv::Mat(), M);
return 0;
}
This will undistort the points to the very similar coordinate to the origin of the image, but without distortion. This is the default behavior for the cv::undistort() function.
Redistort points:
int distortPoints(const vector<cv::Point2f> &xy, vector<cv::Point2f> &uv, const cv::Mat &M, const cv::Mat &d)
{
vector<cv::Point2f> xy2;
vector<cv::Point3f> xyz;
cv::undistortPoints(xy, xy2, M, cv::Mat());
for (cv::Point2f p : xy2)xyz.push_back(cv::Point3f(p.x, p.y, 1));
cv::Mat rvec = cv::Mat::zeros(3, 1, CV_64FC1);
cv::Mat tvec = cv::Mat::zeros(3, 1, CV_64FC1);
cv::projectPoints(xyz, rvec, tvec, M, d, uv);
return 0;
}
The little tricky thing here is to first project the points to the z=1 plane with a linear camera model. After that, you must project them with the original camera model.
I found these useful, I hope it also works for you.
I have had exactly the same need.
Here is a possible solution :
void MyDistortPoints(const std::vector<cv::Point2d> & src, std::vector<cv::Point2d> & dst,
const cv::Mat & cameraMatrix, const cv::Mat & distorsionMatrix)
{
dst.clear();
double fx = cameraMatrix.at<double>(0,0);
double fy = cameraMatrix.at<double>(1,1);
double ux = cameraMatrix.at<double>(0,2);
double uy = cameraMatrix.at<double>(1,2);
double k1 = distorsionMatrix.at<double>(0, 0);
double k2 = distorsionMatrix.at<double>(0, 1);
double p1 = distorsionMatrix.at<double>(0, 2);
double p2 = distorsionMatrix.at<double>(0, 3);
double k3 = distorsionMatrix.at<double>(0, 4);
//BOOST_FOREACH(const cv::Point2d &p, src)
for (unsigned int i = 0; i < src.size(); i++)
{
const cv::Point2d &p = src[i];
double x = p.x;
double y = p.y;
double xCorrected, yCorrected;
//Step 1 : correct distorsion
{
double r2 = x*x + y*y;
//radial distorsion
xCorrected = x * (1. + k1 * r2 + k2 * r2 * r2 + k3 * r2 * r2 * r2);
yCorrected = y * (1. + k1 * r2 + k2 * r2 * r2 + k3 * r2 * r2 * r2);
//tangential distorsion
//The "Learning OpenCV" book is wrong here !!!
//False equations from the "Learning OpenCv" book
//xCorrected = xCorrected + (2. * p1 * y + p2 * (r2 + 2. * x * x));
//yCorrected = yCorrected + (p1 * (r2 + 2. * y * y) + 2. * p2 * x);
//Correct formulae found at : http://www.vision.caltech.edu/bouguetj/calib_doc/htmls/parameters.html
xCorrected = xCorrected + (2. * p1 * x * y + p2 * (r2 + 2. * x * x));
yCorrected = yCorrected + (p1 * (r2 + 2. * y * y) + 2. * p2 * x * y);
}
//Step 2 : ideal coordinates => actual coordinates
{
xCorrected = xCorrected * fx + ux;
yCorrected = yCorrected * fy + uy;
}
dst.push_back(cv::Point2d(xCorrected, yCorrected));
}
}
void MyDistortPoints(const std::vector<cv::Point2d> & src, std::vector<cv::Point2d> & dst,
const cv::Matx33d & cameraMatrix, const cv::Matx<double, 1, 5> & distorsionMatrix)
{
cv::Mat cameraMatrix2(cameraMatrix);
cv::Mat distorsionMatrix2(distorsionMatrix);
return MyDistortPoints(src, dst, cameraMatrix2, distorsionMatrix2);
}
void TestDistort()
{
cv::Matx33d cameraMatrix = 0.;
{
//cameraMatrix Init
double fx = 1000., fy = 950.;
double ux = 324., uy = 249.;
cameraMatrix(0, 0) = fx;
cameraMatrix(1, 1) = fy;
cameraMatrix(0, 2) = ux;
cameraMatrix(1, 2) = uy;
cameraMatrix(2, 2) = 1.;
}
cv::Matx<double, 1, 5> distorsionMatrix;
{
//distorsion Init
const double k1 = 0.5, k2 = -0.5, k3 = 0.000005, p1 = 0.07, p2 = -0.05;
distorsionMatrix(0, 0) = k1;
distorsionMatrix(0, 1) = k2;
distorsionMatrix(0, 2) = p1;
distorsionMatrix(0, 3) = p2;
distorsionMatrix(0, 4) = k3;
}
std::vector<cv::Point2d> distortedPoints;
std::vector<cv::Point2d> undistortedPoints;
std::vector<cv::Point2d> redistortedPoints;
distortedPoints.push_back(cv::Point2d(324., 249.));// equals to optical center
distortedPoints.push_back(cv::Point2d(340., 200));
distortedPoints.push_back(cv::Point2d(785., 345.));
distortedPoints.push_back(cv::Point2d(0., 0.));
cv::undistortPoints(distortedPoints, undistortedPoints, cameraMatrix, distorsionMatrix);
MyDistortPoints(undistortedPoints, redistortedPoints, cameraMatrix, distorsionMatrix);
cv::undistortPoints(redistortedPoints, undistortedPoints, cameraMatrix, distorsionMatrix);
//Poor man's unit test ensuring we have an accuracy that is better than 0.001 pixel
for (unsigned int i = 0; i < undistortedPoints.size(); i++)
{
cv::Point2d dist = redistortedPoints[i] - distortedPoints[i];
double norm = sqrt(dist.dot(dist));
std::cout << "norm = " << norm << std::endl;
assert(norm < 1E-3);
}
}
For those still searching, here is a simple python function that will distort points back:
def distortPoints(undistortedPoints, k, d):
undistorted = np.float32(undistortedPoints[:, np.newaxis, :])
kInv = np.linalg.inv(k)
for i in range(len(undistorted)):
srcv = np.array([undistorted[i][0][0], undistorted[i][0][1], 1])
dstv = kInv.dot(srcv)
undistorted[i][0][0] = dstv[0]
undistorted[i][0][1] = dstv[1]
distorted = cv2.fisheye.distortPoints(undistorted, k, d)
return distorted
Example:
undistorted = np.array([(639.64, 362.09), (234, 567)])
distorted = distortPoints(undistorted, camK, camD)
print(distorted)
This question and it's related questions on SO have been around for nearly a decade, but there still isn't an answer that satisfies the criteria below so I'm proposing a new answer that
uses methods readily available in OpenCV,
works for points, not images, (and also points at subpixel locations),
can be used beyond fisheye distortion models,
does not involve manual interpolation or maps and
can be used in the context of rectification
Preliminaries
It is important to distinquish between ideal coordinates (also called 'normalized' or 'sensor' coordinates) which are the input variables to the distortion model or 'x' and 'y' in the OpenCV docs vs. observed coordinates (also called 'image' coordinates) or 'u' and 'v' in OpenCV docs. Ideal coordinates have been normalized by the intrinsic parameters so that they have been scaled by the focal length and are relative to the image centroid at (cx,cy). This is important to point out because the undistortPoints() method can return either ideal or observed coordinates depending on the input arguments.
undistortPoints() can essentially do any combination of two things: remove distortions and apply a rotational transformation with the output either being in ideal or observed coordinates, depending on if a projection mat (InputArray P) is provided in the input. The input coordinates (InputArray src) for undistortPoints() is always in observed or image coordinates.
At a high level undistortPoints() converts the input coordinates from observed to ideal coordinates and uses an iterative process to remove distortions from the ideal or normalized points. The reason the process is iterative is because the OpenCV distortion model is not easy to invert analytically.
In the example below, we use undistortPoints() twice. First, we apply a reverse rotational transformation to undo image rectification. This step can be skipped if you are not working with rectified images. The output of this first step is in observed coordinates so we use undistortPoints() again to convert these to ideal coordinates. The conversion to ideal coordinates makes setting up the input for projectPoints() easier (which we use to apply the distortions). With the ideal coordinates, we can simply convert them to homogeneous by appending a 1 to each point. This is equivalent to projecting the points to a plane in 3D world coordinates with a linear camera model.
As of currently, there isn't a method in OpenCV to apply distortions to a set of ideal coordinates (with the exception of fisheye distortions using distort()) so we employ the projectPoints() method which can apply distortions as well as transformations as part of its projection algorithm. The tricky part about using projectPoints() is that the input is in terms of world or model coordinates in 3D, which is why we homogenized the output of the second use of undistortPoints(). By using projectPoints() with a dummy, zero-valued rotation vector (InputArray rvec) and translation vector (Input Array tvec) the result is simply a distorted set of coordinates which is conveniently output in observed or image coordinates.
Some helpful links
Difference between undistortPoints() and projectPoints() in OpenCV
https://docs.opencv.org/3.4/d9/d0c/group__calib3d.html#ga1019495a2c8d1743ed5cc23fa0daff8c
https://docs.opencv.org/3.4/da/d54/group__imgproc__transform.html#ga55c716492470bfe86b0ee9bf3a1f0f7e
Re-distort points with camera intrinsics/extrinsics
https://stackoverflow.com/questions/28678985/exact-definition-of-the-matrices-in-opencv-stereorectify#:~:text=Normally%20the%20definition%20of%20a,matrix%20with%20the%20extrinsic%20parameters
https://docs.opencv.org/4.x/db/d58/group__calib3d__fisheye.html#ga75d8877a98e38d0b29b6892c5f8d7765
https://docs.opencv.org/3.4/d9/d0c/group__calib3d.html#ga617b1685d4059c6040827800e72ad2b6
Does OpenCV's undistortPoints also rectify them?
Removing distortions in rectified image coordinates
Before providing the solution to recovering the original image coordinates with distortions we provide a short snippet to convert from the original distorted image coordinates to the corresponding rectified, undistorted coordinates that can be used for testing the reverse solution below.
The rotation matrix R1 and the projection matrix P1 come from stereoRectify(). The intrinsic parameters M1 and distortion parameters D1 come from stereoCalibrate().
const size_t img_w = 2448;
const size_t img_h = 2048;
const size_t num_rand_pts = 100;
// observed coordinates of the points in the original
// distorted image (used as a benchmark for testing)
std::vector<cv::Point2f> benchmark_obs_dist_points;
// undistorted and rectified obnserved coordinates
std::vector<cv::Point2f> obs_rect_undist_points;
// initialize with uniform random numbers
cv::RNG rng( 0xFFFFFFFF );
for(size_t i =0;i<num_rand_pts;++i)
benchmark_obs_dist_points.push_back(
cv::Point2f(rng.uniform(0.0,(double)img_w),
rng.uniform(0.0,(double)img_h))
);
// undistort and rectify
cv::undistortPoints(benchmark_obs_dist_points,obs_rect_undist_points,
M1,D1,R1,P1);
Re-distorting and unrectifying points to recover the original image coordinates
We will need three mats to reverse the rectification: the inverse of the rectification rotation matrix from stereoRectify R1, and two others to 'swap' the P1 and M1 projections that happen in undistortPoints(). P1_prime is the rotation matrix sub-portion of the projection matrix and M1_prime converts the rectification rotation matrix into a projection matrix with no translation. Note this only works if the output of stereoRectify has no translation, i.e. the last column of P1 is zeros which can be easily verified.
assert(cv::norm(P1(cv::Rect(3,0,1,3))==0.0));
// create a 3x3 shallow copy of the rotation matrix portion of the projection P1
cv::Mat P1_prime = P1(cv::Rect(0,0,3,3));
// create a 3x4 projection matrix with the rotation portion of
// the rectification rotation matrix R1
cv::Mat M1_prime = cv::Mat::zeros(3,4,CV_64F);
M1.copyTo(M1_prime(cv::Rect(0,0,3,3)));
With these mats, the reversal can proceed as follows
// reverse the image rectification transformation
// (result will still be undistorted)
std::vector<cv::Point2f> obs_undist_points;
cv::undistortPoints(obs_rect_undist_points,obs_undist_points,
P1_prime,cv::Mat(),R1.inv(),M1_prime);
// convert the image coordinates into sensor or normalized or ideal coordinates
// (again, still undistorted)
std::vector<cv::Point2f> ideal_undist_points;
cv::undistortPoints(obs_undist_points,ideal_undist_points,M1,cv::Mat());
// artificially project the ideal 2d points to a plane in world coordinates
// using a linear camera model (z=1)
std::vector<cv::Point3f> world_undist_points;
for (cv::Point2f pt : ideal_undist_points)
world_undist_points.push_back(cv::Point3f(pt.x,pt.y,1));
// add the distortions back in to get the original coordinates
cv::Mat rvec = cv::Mat::zeros(3,1,CV_64FC1); // dummy zero rotation vec
cv::Mat tvec = cv::Mat::zeros(3,1,CV_64FC1); // dummy zero translation vec
std::vector<cv::Point2f> obs_dist_points;
cv::projectPoints(world_undist_points,rvec,tvec,M1,D1,obs_dist_points);
To test the results, we can compare them to the benchmark values
for(size_t i=0;i<num_rand_pts;++i)
std::cout << "benchmark_x: " << benchmark_obs_dist_points[i].x
<< " benchmark_y: " << benchmark_obs_dist_points[i].y
<< " computed_x: " << obs_dist_points[i].x
<< " computed_y: " << obs_dist_points[i].y
<< " diff_x: "
<< std::abs(benchmark_obs_dist_points[i].x-obs_dist_points[i].x)
<< " diff_y: "
<< std::abs(benchmark_obs_dist_points[i].y-obs_dist_points[i].y)
<< std::endl;
This is main.cpp. It is self-sufficient and does not need anything else but opencv. I don't remember where I found this, it works, I used it in my project. The program eats the set of standard chessboard images and generates json/xml files with all the distortions of the camera.
#include <iostream>
#include <sstream>
#include <time.h>
#include <stdio.h>
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/calib3d/calib3d.hpp>
#include <opencv2/highgui/highgui.hpp>
#ifndef _CRT_SECURE_NO_WARNINGS
# define _CRT_SECURE_NO_WARNINGS
#endif
using namespace cv;
using namespace std;
static void help()
{
cout << "This is a camera calibration sample." << endl
<< "Usage: calibration configurationFile" << endl
<< "Near the sample file you'll find the configuration file, which has detailed help of "
"how to edit it. It may be any OpenCV supported file format XML/YAML." << endl;
}
class Settings
{
public:
Settings() : goodInput(false) {}
enum Pattern { NOT_EXISTING, CHESSBOARD, CIRCLES_GRID, ASYMMETRIC_CIRCLES_GRID };
enum InputType {INVALID, CAMERA, VIDEO_FILE, IMAGE_LIST};
void write(FileStorage& fs) const //Write serialization for this class
{
fs << "{" << "BoardSize_Width" << boardSize.width
<< "BoardSize_Height" << boardSize.height
<< "Square_Size" << squareSize
<< "Calibrate_Pattern" << patternToUse
<< "Calibrate_NrOfFrameToUse" << nrFrames
<< "Calibrate_FixAspectRatio" << aspectRatio
<< "Calibrate_AssumeZeroTangentialDistortion" << calibZeroTangentDist
<< "Calibrate_FixPrincipalPointAtTheCenter" << calibFixPrincipalPoint
<< "Write_DetectedFeaturePoints" << bwritePoints
<< "Write_extrinsicParameters" << bwriteExtrinsics
<< "Write_outputFileName" << outputFileName
<< "Show_UndistortedImage" << showUndistorsed
<< "Input_FlipAroundHorizontalAxis" << flipVertical
<< "Input_Delay" << delay
<< "Input" << input
<< "}";
}
void read(const FileNode& node) //Read serialization for this class
{
node["BoardSize_Width" ] >> boardSize.width;
node["BoardSize_Height"] >> boardSize.height;
node["Calibrate_Pattern"] >> patternToUse;
node["Square_Size"] >> squareSize;
node["Calibrate_NrOfFrameToUse"] >> nrFrames;
node["Calibrate_FixAspectRatio"] >> aspectRatio;
node["Write_DetectedFeaturePoints"] >> bwritePoints;
node["Write_extrinsicParameters"] >> bwriteExtrinsics;
node["Write_outputFileName"] >> outputFileName;
node["Calibrate_AssumeZeroTangentialDistortion"] >> calibZeroTangentDist;
node["Calibrate_FixPrincipalPointAtTheCenter"] >> calibFixPrincipalPoint;
node["Input_FlipAroundHorizontalAxis"] >> flipVertical;
node["Show_UndistortedImage"] >> showUndistorsed;
node["Input"] >> input;
node["Input_Delay"] >> delay;
interprate();
}
void interprate()
{
goodInput = true;
if (boardSize.width <= 0 || boardSize.height <= 0)
{
cerr << "Invalid Board size: " << boardSize.width << " " << boardSize.height << endl;
goodInput = false;
}
if (squareSize <= 10e-6)
{
cerr << "Invalid square size " << squareSize << endl;
goodInput = false;
}
if (nrFrames <= 0)
{
cerr << "Invalid number of frames " << nrFrames << endl;
goodInput = false;
}
if (input.empty()) // Check for valid input
inputType = INVALID;
else
{
if (input[0] >= '0' && input[0] <= '9')
{
stringstream ss(input);
ss >> cameraID;
inputType = CAMERA;
}
else
{
if (readStringList(input, imageList))
{
inputType = IMAGE_LIST;
nrFrames = (nrFrames < (int)imageList.size()) ? nrFrames : (int)imageList.size();
}
else
inputType = VIDEO_FILE;
}
if (inputType == CAMERA)
inputCapture.open(cameraID);
if (inputType == VIDEO_FILE)
inputCapture.open(input);
if (inputType != IMAGE_LIST && !inputCapture.isOpened())
inputType = INVALID;
}
if (inputType == INVALID)
{
cerr << " Inexistent input: " << input << endl;
goodInput = false;
}
flag = 0;
if(calibFixPrincipalPoint) flag |= CV_CALIB_FIX_PRINCIPAL_POINT;
if(calibZeroTangentDist) flag |= CV_CALIB_ZERO_TANGENT_DIST;
if(aspectRatio) flag |= CV_CALIB_FIX_ASPECT_RATIO;
calibrationPattern = NOT_EXISTING;
if (!patternToUse.compare("CHESSBOARD")) calibrationPattern = CHESSBOARD;
if (!patternToUse.compare("CIRCLES_GRID")) calibrationPattern = CIRCLES_GRID;
if (!patternToUse.compare("ASYMMETRIC_CIRCLES_GRID")) calibrationPattern = ASYMMETRIC_CIRCLES_GRID;
if (calibrationPattern == NOT_EXISTING)
{
cerr << " Inexistent camera calibration mode: " << patternToUse << endl;
goodInput = false;
}
atImageList = 0;
}
Mat nextImage()
{
Mat result;
if( inputCapture.isOpened() )
{
Mat view0;
inputCapture >> view0;
view0.copyTo(result);
}
else if( atImageList < (int)imageList.size() )
result = imread(imageList[atImageList++], CV_LOAD_IMAGE_COLOR);
return result;
}
static bool readStringList( const string& filename, vector<string>& l )
{
l.clear();
FileStorage fs(filename, FileStorage::READ);
if( !fs.isOpened() )
return false;
FileNode n = fs.getFirstTopLevelNode();
if( n.type() != FileNode::SEQ )
return false;
FileNodeIterator it = n.begin(), it_end = n.end();
for( ; it != it_end; ++it )
l.push_back((string)*it);
return true;
}
public:
Size boardSize; // The size of the board -> Number of items by width and height
Pattern calibrationPattern;// One of the Chessboard, circles, or asymmetric circle pattern
float squareSize; // The size of a square in your defined unit (point, millimeter,etc).
int nrFrames; // The number of frames to use from the input for calibration
float aspectRatio; // The aspect ratio
int delay; // In case of a video input
bool bwritePoints; // Write detected feature points
bool bwriteExtrinsics; // Write extrinsic parameters
bool calibZeroTangentDist; // Assume zero tangential distortion
bool calibFixPrincipalPoint;// Fix the principal point at the center
bool flipVertical; // Flip the captured images around the horizontal axis
string outputFileName; // The name of the file where to write
bool showUndistorsed; // Show undistorted images after calibration
string input; // The input ->
int cameraID;
vector<string> imageList;
int atImageList;
VideoCapture inputCapture;
InputType inputType;
bool goodInput;
int flag;
private:
string patternToUse;
};
static void read(const FileNode& node, Settings& x, const Settings& default_value = Settings())
{
if(node.empty())
x = default_value;
else
x.read(node);
}
enum { DETECTION = 0, CAPTURING = 1, CALIBRATED = 2 };
bool runCalibrationAndSave(Settings& s, Size imageSize, Mat& cameraMatrix, Mat& distCoeffs,
vector<vector<Point2f> > imagePoints );
int main(int argc, char* argv[])
{
// help();
Settings s;
const string inputSettingsFile = argc > 1 ? argv[1] : "default.xml";
FileStorage fs(inputSettingsFile, FileStorage::READ); // Read the settings
if (!fs.isOpened())
{
cout << "Could not open the configuration file: \"" << inputSettingsFile << "\"" << endl;
return -1;
}
fs["Settings"] >> s;
fs.release(); // close Settings file
if (!s.goodInput)
{
cout << "Invalid input detected. Application stopping. " << endl;
return -1;
}
vector<vector<Point2f> > imagePoints;
Mat cameraMatrix, distCoeffs;
Size imageSize;
int mode = s.inputType == Settings::IMAGE_LIST ? CAPTURING : DETECTION;
clock_t prevTimestamp = 0;
const Scalar RED(0,0,255), GREEN(0,255,0);
const char ESC_KEY = 27;
for(int i = 0;;++i)
{
Mat view;
bool blinkOutput = false;
view = s.nextImage();
//----- If no more image, or got enough, then stop calibration and show result -------------
if( mode == CAPTURING && imagePoints.size() >= (unsigned)s.nrFrames )
{
if( runCalibrationAndSave(s, imageSize, cameraMatrix, distCoeffs, imagePoints))
mode = CALIBRATED;
else
mode = DETECTION;
}
if(view.empty()) // If no more images then run calibration, save and stop loop.
{
if( imagePoints.size() > 0 )
runCalibrationAndSave(s, imageSize, cameraMatrix, distCoeffs, imagePoints);
break;
}
imageSize = view.size(); // Format input image.
if( s.flipVertical ) flip( view, view, 0 );
vector<Point2f> pointBuf;
bool found;
switch( s.calibrationPattern ) // Find feature points on the input format
{
case Settings::CHESSBOARD:
found = findChessboardCorners( view, s.boardSize, pointBuf,
CV_CALIB_CB_ADAPTIVE_THRESH | CV_CALIB_CB_FAST_CHECK | CV_CALIB_CB_NORMALIZE_IMAGE);
break;
case Settings::CIRCLES_GRID:
found = findCirclesGrid( view, s.boardSize, pointBuf );
break;
case Settings::ASYMMETRIC_CIRCLES_GRID:
found = findCirclesGrid( view, s.boardSize, pointBuf, CALIB_CB_ASYMMETRIC_GRID );
break;
default:
found = false;
break;
}
if ( found) // If done with success,
{
// improve the found corners' coordinate accuracy for chessboard
if( s.calibrationPattern == Settings::CHESSBOARD)
{
Mat viewGray;
cvtColor(view, viewGray, COLOR_BGR2GRAY);
cornerSubPix( viewGray, pointBuf, Size(11,11),
Size(-1,-1), TermCriteria( CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 30, 0.1 ));
}
if( mode == CAPTURING && // For camera only take new samples after delay time
(!s.inputCapture.isOpened() || clock() - prevTimestamp > s.delay*1e-3*CLOCKS_PER_SEC) )
{
imagePoints.push_back(pointBuf);
prevTimestamp = clock();
blinkOutput = s.inputCapture.isOpened();
}
// Draw the corners.
drawChessboardCorners( view, s.boardSize, Mat(pointBuf), found );
}
//----------------------------- Output Text ------------------------------------------------
string msg = (mode == CAPTURING) ? "100/100" :
mode == CALIBRATED ? "Calibrated" : "Press 'g' to start";
int baseLine = 0;
Size textSize = getTextSize(msg, 1, 1, 1, &baseLine);
Point textOrigin(view.cols - 2*textSize.width - 10, view.rows - 2*baseLine - 10);
if( mode == CAPTURING )
{
if(s.showUndistorsed)
msg = format( "%d/%d Undist", (int)imagePoints.size(), s.nrFrames );
else
msg = format( "%d/%d", (int)imagePoints.size(), s.nrFrames );
}
putText( view, msg, textOrigin, 1, 1, mode == CALIBRATED ? GREEN : RED);
if( blinkOutput )
bitwise_not(view, view);
//------------------------- Video capture output undistorted ------------------------------
if( mode == CALIBRATED && s.showUndistorsed )
{
Mat temp = view.clone();
undistort(temp, view, cameraMatrix, distCoeffs);
}
//------------------------------ Show image and check for input commands -------------------
imshow("Image View", view);
char key = (char)waitKey(s.inputCapture.isOpened() ? 50 : s.delay);
if( key == ESC_KEY )
break;
if( key == 'u' && mode == CALIBRATED )
s.showUndistorsed = !s.showUndistorsed;
if( s.inputCapture.isOpened() && key == 'g' )
{
mode = CAPTURING;
imagePoints.clear();
}
}
// -----------------------Show the undistorted image for the image list ------------------------
if( s.inputType == Settings::IMAGE_LIST && s.showUndistorsed )
{
Mat view, rview, map1, map2;
initUndistortRectifyMap(cameraMatrix, distCoeffs, Mat(),
getOptimalNewCameraMatrix(cameraMatrix, distCoeffs, imageSize, 1, imageSize, 0),
imageSize, CV_16SC2, map1, map2);
for(int i = 0; i < (int)s.imageList.size(); i++ )
{
view = imread(s.imageList[i], 1);
if(view.empty())
continue;
remap(view, rview, map1, map2, INTER_LINEAR);
imshow("Image View", rview);
char c = (char)waitKey();
if( c == ESC_KEY || c == 'q' || c == 'Q' )
break;
}
}
return 0;
}
static double computeReprojectionErrors( const vector<vector<Point3f> >& objectPoints,
const vector<vector<Point2f> >& imagePoints,
const vector<Mat>& rvecs, const vector<Mat>& tvecs,
const Mat& cameraMatrix , const Mat& distCoeffs,
vector<float>& perViewErrors)
{
vector<Point2f> imagePoints2;
int i, totalPoints = 0;
double totalErr = 0, err;
perViewErrors.resize(objectPoints.size());
for( i = 0; i < (int)objectPoints.size(); ++i )
{
projectPoints( Mat(objectPoints[i]), rvecs[i], tvecs[i], cameraMatrix,
distCoeffs, imagePoints2);
err = norm(Mat(imagePoints[i]), Mat(imagePoints2), CV_L2);
int n = (int)objectPoints[i].size();
perViewErrors[i] = (float) std::sqrt(err*err/n);
totalErr += err*err;
totalPoints += n;
}
return std::sqrt(totalErr/totalPoints);
}
static void calcBoardCornerPositions(Size boardSize, float squareSize, vector<Point3f>& corners,
Settings::Pattern patternType /*= Settings::CHESSBOARD*/)
{
corners.clear();
switch(patternType)
{
case Settings::CHESSBOARD:
case Settings::CIRCLES_GRID:
for( int i = 0; i < boardSize.height; ++i )
for( int j = 0; j < boardSize.width; ++j )
corners.push_back(Point3f(float( j*squareSize ), float( i*squareSize ), 0));
break;
case Settings::ASYMMETRIC_CIRCLES_GRID:
for( int i = 0; i < boardSize.height; i++ )
for( int j = 0; j < boardSize.width; j++ )
corners.push_back(Point3f(float((2*j + i % 2)*squareSize), float(i*squareSize), 0));
break;
default:
break;
}
}
static bool runCalibration( Settings& s, Size& imageSize, Mat& cameraMatrix, Mat& distCoeffs,
vector<vector<Point2f> > imagePoints, vector<Mat>& rvecs, vector<Mat>& tvecs,
vector<float>& reprojErrs, double& totalAvgErr)
{
cameraMatrix = Mat::eye(3, 3, CV_64F);
if( s.flag & CV_CALIB_FIX_ASPECT_RATIO )
cameraMatrix.at<double>(0,0) = 1.0;
distCoeffs = Mat::zeros(8, 1, CV_64F);
vector<vector<Point3f> > objectPoints(1);
calcBoardCornerPositions(s.boardSize, s.squareSize, objectPoints[0], s.calibrationPattern);
objectPoints.resize(imagePoints.size(),objectPoints[0]);
//Find intrinsic and extrinsic camera parameters
double rms = calibrateCamera(objectPoints, imagePoints, imageSize, cameraMatrix,
distCoeffs, rvecs, tvecs, s.flag|CV_CALIB_FIX_K4|CV_CALIB_FIX_K5);
cout << "Re-projection error reported by calibrateCamera: "<< rms << endl;
bool ok = checkRange(cameraMatrix) && checkRange(distCoeffs);
totalAvgErr = computeReprojectionErrors(objectPoints, imagePoints,
rvecs, tvecs, cameraMatrix, distCoeffs, reprojErrs);
return ok;
}
// Print camera parameters to the output file
static void saveCameraParams( Settings& s, Size& imageSize, Mat& cameraMatrix, Mat& distCoeffs,
const vector<Mat>& rvecs, const vector<Mat>& tvecs,
const vector<float>& reprojErrs, const vector<vector<Point2f> >& imagePoints,
double totalAvgErr )
{
FileStorage fs( s.outputFileName, FileStorage::WRITE );
time_t tm;
time( &tm );
struct tm *t2 = localtime( &tm );
char buf[1024];
strftime( buf, sizeof(buf)-1, "%c", t2 );
fs << "calibration_Time" << buf;
if( !rvecs.empty() || !reprojErrs.empty() )
fs << "nrOfFrames" << (int)std::max(rvecs.size(), reprojErrs.size());
fs << "image_Width" << imageSize.width;
fs << "image_Height" << imageSize.height;
fs << "board_Width" << s.boardSize.width;
fs << "board_Height" << s.boardSize.height;
fs << "square_Size" << s.squareSize;
if( s.flag & CV_CALIB_FIX_ASPECT_RATIO )
fs << "FixAspectRatio" << s.aspectRatio;
if( s.flag )
{
sprintf( buf, "flags: %s%s%s%s",
s.flag & CV_CALIB_USE_INTRINSIC_GUESS ? " +use_intrinsic_guess" : "",
s.flag & CV_CALIB_FIX_ASPECT_RATIO ? " +fix_aspectRatio" : "",
s.flag & CV_CALIB_FIX_PRINCIPAL_POINT ? " +fix_principal_point" : "",
s.flag & CV_CALIB_ZERO_TANGENT_DIST ? " +zero_tangent_dist" : "" );
cvWriteComment( *fs, buf, 0 );
}
fs << "flagValue" << s.flag;
fs << "Camera_Matrix" << cameraMatrix;
fs << "Distortion_Coefficients" << distCoeffs;
fs << "Avg_Reprojection_Error" << totalAvgErr;
if( !reprojErrs.empty() )
fs << "Per_View_Reprojection_Errors" << Mat(reprojErrs);
if( !rvecs.empty() && !tvecs.empty() )
{
CV_Assert(rvecs[0].type() == tvecs[0].type());
Mat bigmat((int)rvecs.size(), 6, rvecs[0].type());
for( int i = 0; i < (int)rvecs.size(); i++ )
{
Mat r = bigmat(Range(i, i+1), Range(0,3));
Mat t = bigmat(Range(i, i+1), Range(3,6));
CV_Assert(rvecs[i].rows == 3 && rvecs[i].cols == 1);
CV_Assert(tvecs[i].rows == 3 && tvecs[i].cols == 1);
//*.t() is MatExpr (not Mat) so we can use assignment operator
r = rvecs[i].t();
t = tvecs[i].t();
}
cvWriteComment( *fs, "a set of 6-tuples (rotation vector + translation vector) for each view", 0 );
fs << "Extrinsic_Parameters" << bigmat;
}
if( !imagePoints.empty() )
{
Mat imagePtMat((int)imagePoints.size(), (int)imagePoints[0].size(), CV_32FC2);
for( int i = 0; i < (int)imagePoints.size(); i++ )
{
Mat r = imagePtMat.row(i).reshape(2, imagePtMat.cols);
Mat imgpti(imagePoints[i]);
imgpti.copyTo(r);
}
fs << "Image_points" << imagePtMat;
}
}
bool runCalibrationAndSave(Settings& s, Size imageSize, Mat& cameraMatrix, Mat& distCoeffs,vector<vector<Point2f> > imagePoints )
{
vector<Mat> rvecs, tvecs;
vector<float> reprojErrs;
double totalAvgErr = 0;
bool ok = runCalibration(s,imageSize, cameraMatrix, distCoeffs, imagePoints, rvecs, tvecs,
reprojErrs, totalAvgErr);
cout << (ok ? "Calibration succeeded" : "Calibration failed")
<< ". avg re projection error = " << totalAvgErr ;
if( ok )
saveCameraParams( s, imageSize, cameraMatrix, distCoeffs, rvecs ,tvecs, reprojErrs,
imagePoints, totalAvgErr);
return ok;
}

Resources