我是这个领域的新手，正在尝试将2D图像建模为简单的3D场景，但我没有有关相机的任何信息。我知道有三种选择：
我有两张图片，我知道我的相机模型（内参）是从一个XML文件中加载的，例如
loadXMLFromFile()=>stereoRectify()=>reprojectImageTo3D()我没有这些内容，但我可以校准我的相机 =>
stereoCalibrate()=>stereoRectify()=>reprojectImageTo3D()我无法校准相机（这是我的情况，因为我没有拍摄这2张图像的相机），所以我需要在两张图像上找到一对关键点，例如使用SURF、SIFT检测器(实际上还可以使用任何blob检测器)，然后计算这些关键点的描述符，然后将左图和右图的关键点进行匹配，然后从它们中找到基本矩阵。处理过程更加复杂，如下所示：
- 检测关键点（SURF、SIFT）=>
- 提取描述符（SURF、SIFT）=>
- 比较和匹配描述符（BruteForce、Flann）=>
- 从这些匹配对中找出基本矩阵(
findFundamentalMat()) => stereoRectifyUncalibrated()=>reprojectImageTo3D()
1）这样做对吗？
2）如果可以，我对最后一步
stereoRectifyUncalibrated() => reprojectImageTo3D() 有疑问。 reprojectImageTo3D() 函数的签名如下：void reprojectImageTo3D(InputArray disparity, OutputArray _3dImage, InputArray Q, bool handleMissingValues=false, int depth=-1 )
cv::reprojectImageTo3D(imgDisparity8U, xyz, Q, true) (in my code)
参数：
disparity– 输入单通道8位无符号、16位有符号、32位有符号或32位浮点视差图像。_3dImage– 输出与disparity大小相同的三通道浮点图像。_3dImage（x，y）的每个元素都包含从视差图计算的点（x，y）的3D坐标。Q– 4x4透视变换矩阵，可使用stereoRectify()获得。handleMissingValues– 表示函数是否应处理缺失值（即未计算视差的点）。如果handleMissingValues=true，则对应于异常值（请参见StereoBM :: operator()）的最小视差像素被转换为具有非常大Z值的3D点（当前设置为10000）。ddepth– 可选输出数组深度。如果它是-1，则输出图像将具有CV_32F深度。ddepth也可以设置为CV_16S、CV_32S或CV_32F。
我该如何获得 Q 矩阵？是否可以通过 F、H1 和 H2 或其他方式获得 Q 矩阵？
3) 是否有其他方法可以获得 xyz 坐标而无需校准相机？
我的代码如下：
#include <opencv2/core/core.hpp>
#include <opencv2/calib3d/calib3d.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/contrib/contrib.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <stdio.h>
#include <iostream>
#include <vector>
#include <conio.h>
#include <opencv/cv.h>
#include <opencv/cxcore.h>
#include <opencv/cvaux.h>
using namespace cv;
using namespace std;
int main(int argc, char *argv[]){
// Read the images
Mat imgLeft = imread( argv[1], CV_LOAD_IMAGE_GRAYSCALE );
Mat imgRight = imread( argv[2], CV_LOAD_IMAGE_GRAYSCALE );
// check
if (!imgLeft.data || !imgRight.data)
return 0;
// 1] find pair keypoints on both images (SURF, SIFT):::::::::::::::::::::::::::::
// vector of keypoints
std::vector<cv::KeyPoint> keypointsLeft;
std::vector<cv::KeyPoint> keypointsRight;
// Construct the SURF feature detector object
cv::SiftFeatureDetector sift(
0.01, // feature threshold
10); // threshold to reduce
// sensitivity to lines
// Detect the SURF features
// Detection of the SIFT features
sift.detect(imgLeft,keypointsLeft);
sift.detect(imgRight,keypointsRight);
std::cout << "Number of SURF points (1): " << keypointsLeft.size() << std::endl;
std::cout << "Number of SURF points (2): " << keypointsRight.size() << std::endl;
// 2] compute descriptors of these keypoints (SURF,SIFT) ::::::::::::::::::::::::::
// Construction of the SURF descriptor extractor
cv::SurfDescriptorExtractor surfDesc;
// Extraction of the SURF descriptors
cv::Mat descriptorsLeft, descriptorsRight;
surfDesc.compute(imgLeft,keypointsLeft,descriptorsLeft);
surfDesc.compute(imgRight,keypointsRight,descriptorsRight);
std::cout << "descriptor matrix size: " << descriptorsLeft.rows << " by " << descriptorsLeft.cols << std::endl;
// 3] matching keypoints from image right and image left according to their descriptors (BruteForce, Flann based approaches)
// Construction of the matcher
cv::BruteForceMatcher<cv::L2<float> > matcher;
// Match the two image descriptors
std::vector<cv::DMatch> matches;
matcher.match(descriptorsLeft,descriptorsRight, matches);
std::cout << "Number of matched points: " << matches.size() << std::endl;
// 4] find the fundamental mat ::::::::::::::::::::::::::::::::::::::::::::::::::::
// Convert 1 vector of keypoints into
// 2 vectors of Point2f for compute F matrix
// with cv::findFundamentalMat() function
std::vector<int> pointIndexesLeft;
std::vector<int> pointIndexesRight;
for (std::vector<cv::DMatch>::const_iterator it= matches.begin(); it!= matches.end(); ++it) {
// Get the indexes of the selected matched keypoints
pointIndexesLeft.push_back(it->queryIdx);
pointIndexesRight.push_back(it->trainIdx);
}
// Convert keypoints into Point2f
std::vector<cv::Point2f> selPointsLeft, selPointsRight;
cv::KeyPoint::convert(keypointsLeft,selPointsLeft,pointIndexesLeft);
cv::KeyPoint::convert(keypointsRight,selPointsRight,pointIndexesRight);
/* check by drawing the points
std::vector<cv::Point2f>::const_iterator it= selPointsLeft.begin();
while (it!=selPointsLeft.end()) {
// draw a circle at each corner location
cv::circle(imgLeft,*it,3,cv::Scalar(255,255,255),2);
++it;
}
it= selPointsRight.begin();
while (it!=selPointsRight.end()) {
// draw a circle at each corner location
cv::circle(imgRight,*it,3,cv::Scalar(255,255,255),2);
++it;
} */
// Compute F matrix from n>=8 matches
cv::Mat fundemental= cv::findFundamentalMat(
cv::Mat(selPointsLeft), // points in first image
cv::Mat(selPointsRight), // points in second image
CV_FM_RANSAC); // 8-point method
std::cout << "F-Matrix size= " << fundemental.rows << "," << fundemental.cols << std::endl;
/* draw the left points corresponding epipolar lines in right image
std::vector<cv::Vec3f> linesLeft;
cv::computeCorrespondEpilines(
cv::Mat(selPointsLeft), // image points
1, // in image 1 (can also be 2)
fundemental, // F matrix
linesLeft); // vector of epipolar lines
// for all epipolar lines
for (vector<cv::Vec3f>::const_iterator it= linesLeft.begin(); it!=linesLeft.end(); ++it) {
// draw the epipolar line between first and last column
cv::line(imgRight,cv::Point(0,-(*it)[2]/(*it)[1]),cv::Point(imgRight.cols,-((*it)[2]+(*it)[0]*imgRight.cols)/(*it)[1]),cv::Scalar(255,255,255));
}
// draw the left points corresponding epipolar lines in left image
std::vector<cv::Vec3f> linesRight;
cv::computeCorrespondEpilines(cv::Mat(selPointsRight),2,fundemental,linesRight);
for (vector<cv::Vec3f>::const_iterator it= linesRight.begin(); it!=linesRight.end(); ++it) {
// draw the epipolar line between first and last column
cv::line(imgLeft,cv::Point(0,-(*it)[2]/(*it)[1]), cv::Point(imgLeft.cols,-((*it)[2]+(*it)[0]*imgLeft.cols)/(*it)[1]), cv::Scalar(255,255,255));
}
// Display the images with points and epipolar lines
cv::namedWindow("Right Image Epilines");
cv::imshow("Right Image Epilines",imgRight);
cv::namedWindow("Left Image Epilines");
cv::imshow("Left Image Epilines",imgLeft);
*/
// 5] stereoRectifyUncalibrated()::::::::::::::::::::::::::::::::::::::::::::::::::
//H1, H2 – The output rectification homography matrices for the first and for the second images.
cv::Mat H1(4,4, imgRight.type());
cv::Mat H2(4,4, imgRight.type());
cv::stereoRectifyUncalibrated(selPointsRight, selPointsLeft, fundemental, imgRight.size(), H1, H2);
// create the image in which we will save our disparities
Mat imgDisparity16S = Mat( imgLeft.rows, imgLeft.cols, CV_16S );
Mat imgDisparity8U = Mat( imgLeft.rows, imgLeft.cols, CV_8UC1 );
// Call the constructor for StereoBM
int ndisparities = 16*5; // < Range of disparity >
int SADWindowSize = 5; // < Size of the block window > Must be odd. Is the
// size of averaging window used to match pixel
// blocks(larger values mean better robustness to
// noise, but yield blurry disparity maps)
StereoBM sbm( StereoBM::BASIC_PRESET,
ndisparities,
SADWindowSize );
// Calculate the disparity image
sbm( imgLeft, imgRight, imgDisparity16S, CV_16S );
// Check its extreme values
double minVal; double maxVal;
minMaxLoc( imgDisparity16S, &minVal, &maxVal );
printf("Min disp: %f Max value: %f \n", minVal, maxVal);
// Display it as a CV_8UC1 image
imgDisparity16S.convertTo( imgDisparity8U, CV_8UC1, 255/(maxVal - minVal));
namedWindow( "windowDisparity", CV_WINDOW_NORMAL );
imshow( "windowDisparity", imgDisparity8U );
// 6] reprojectImageTo3D() :::::::::::::::::::::::::::::::::::::::::::::::::::::
//Mat xyz;
//cv::reprojectImageTo3D(imgDisparity8U, xyz, Q, true);
//How can I get the Q matrix? Is possibile to obtain the Q matrix with
//F, H1 and H2 or in another way?
//Is there another way for obtain the xyz coordinates?
cv::waitKey();
return 0;
}