对极几何
下面这段代码是 OpenCV-Python-Tutorial-中文版.pdf （P254）中的实现，
当前系列所有demo下载地址：
https://github.com/GaoRenBao/OpenCv4-Demo
https://gitee.com/fuckgrb/OpenCv4-Demo
不同编程语言对应的OpenCv版本以及开发环境信息如下：
语言 | OpenCv版本 | IDE |
C# | OpenCvSharp4.4.8.0.20230708 | Visual Studio 2022 |
C++ | OpenCv-4.5.5-vc14_vc15 | Visual Studio 2022 |
Python | OpenCv-Python (4.6.0.66) | PyCharm Community Edition 2022.1.3 |
博主这里没找到官方测试用的原图，博主自己拍了两张测试。
测试效果如下：
C#版本代码如下：
C++版本代码如下：
#include <opencv2/opencv.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/features2d.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <iostream>
using namespace cv;
using namespace std;
int main()
{
Mat img1 = cv::imread("../images/myleft.jpg", 0);
Mat img2 = cv::imread("../images/myright.jpg", 0);
Ptr<SIFT> sift = SIFT::create();
Mat des1, des2;
vector<KeyPoint> kp1, kp2;
sift->detectAndCompute(img1, cv::Mat(), kp1, des1);
sift->detectAndCompute(img2, cv::Mat(), kp2, des2);
Ptr<flann::IndexParams> index_params = makePtr<flann::KDTreeIndexParams>(5);
index_params->setAlgorithm(0);
Ptr<flann::SearchParams> search_params = makePtr<flann::SearchParams>(50);
FlannBasedMatcher flann = FlannBasedMatcher(index_params, search_params);
vector<vector<DMatch>> matches;
flann.knnMatch(des1, des2, matches, 2);
vector<Point2f> pts1;
vector<Point2f> pts2;
for (int i = 0; i < matches.size(); i++)
{
if (matches[i][0].distance < 0.7 * matches[i][1].distance)
{
pts2.push_back(kp2[matches[i][0].trainIdx].pt);
pts1.push_back(kp1[matches[i][0].queryIdx].pt);
}
}
// 匹配点列表，用它来计算【基础矩阵】
Mat mask;
cv::Mat F = cv::findFundamentalMat(pts1, pts2, mask, FM_LMEDS);
std::vector<cv::Vec<float, 3>> epilines1, epilines2;
cv::computeCorrespondEpilines(pts1, 2, F, epilines1);
cv::computeCorrespondEpilines(pts2, 1, F, epilines2);
cv::RNG& rng = theRNG();
for (int i = 0; i < pts1.size(); i++)
{
Scalar color = Scalar(rng(256), rng(256), rng(256));
line(img1, Point(0, -epilines1[i][2] / epilines1[i][1]),
Point(img1.cols, -(epilines1[i][2] + epilines1[i][0] * img1.cols) / epilines1[i][1]), color);
}
for (int i = 0; i < pts2.size(); i++)
{
Scalar color = Scalar(rng(256), rng(256), rng(256));
line(img2, Point(0, -epilines2[i][2] / epilines2[i][1]),
Point(img2.cols, -(epilines2[i][2] + epilines2[i][0] * img2.cols) / epilines2[i][1]), color);
}
cv::imshow("img1", img1);
cv::imshow("img2", img2);
cv::waitKey(0);
}
Python版本代码如下：
参考资料：
https://docs.opencv.org/4.5.5/da/de9/tutorial_py_epipolar_geometry.html
https://blog.csdn.net/zhoujinwang/article/details/128349114
import cv2
import numpy as np
from matplotlib import pyplot as plt
# 找到极线
def drawlines(img1, img2, lines, pts1, pts2):
''' img1 - image on which we draw the epilines for the points in img2
lines - corresponding epilines '''
r, c = img1.shape
img1 = cv2.cvtColor(img1, cv2.COLOR_GRAY2BGR)
img2 = cv2.cvtColor(img2, cv2.COLOR_GRAY2BGR)
for r, pt1, pt2 in zip(lines, pts1, pts2):
color = tuple(np.random.randint(0, 255, 3).tolist())
x0, y0 = map(int, [0, -r[2] / r[1]])
x1, y1 = map(int, [c, -(r[2] + r[0] * c) / r[1]])
img1 = cv2.line(img1, (x0, y0), (x1, y1), color, 1)
img1 = cv2.circle(img1, tuple(pt1), 5, color, -1)
img2 = cv2.circle(img2, tuple(pt2), 5, color, -1)
return img1, img2
img1 = cv2.imread('../images/myleft.jpg', 0) # queryimage # left image
img2 = cv2.imread('../images/myright.jpg', 0) # trainimage # right image
sift = cv2.SIFT_create()
# sift = cv2.xfeatures2d.SIFT_create()
# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1, None)
kp2, des2 = sift.detectAndCompute(img2, None)
# FLANN parameters
FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1, des2, k=2)
pts1 = []
pts2 = []
# ratio test as per Lowe's paper
for i, (m, n) in enumerate(matches):
if m.distance < 0.7 * n.distance:
pts2.append(kp2[m.trainIdx].pt)
pts1.append(kp1[m.queryIdx].pt)
# 匹配点列表，用它来计算【基础矩阵】
pts1 = np.int32(pts1)
pts2 = np.int32(pts2)
F, mask = cv2.findFundamentalMat(pts1, pts2, cv2.FM_LMEDS)
# We select only inlier points
pts1 = pts1[mask.ravel() == 1]
pts2 = pts2[mask.ravel() == 1]
# 从两幅图像中计算并绘制极线
# Find epilines corresponding to points in right image (second image) and
# drawing its lines on left image
lines1 = cv2.computeCorrespondEpilines(pts2.reshape(-1, 1, 2), 2, F)
lines1 = lines1.reshape(-1, 3)
img5, img6 = drawlines(img1, img2, lines1, pts1, pts2)
# Find epilines corresponding to points in left image (first image) and
# drawing its lines on right image
lines2 = cv2.computeCorrespondEpilines(pts1.reshape(-1, 1, 2), 1, F)
lines2 = lines2.reshape(-1, 3)
img3, img4 = drawlines(img2, img1, lines2, pts2, pts1)
plt.subplot(121), plt.imshow(img5)
plt.subplot(122), plt.imshow(img3)
plt.show()
# 从上图可以看出所有的极线都汇聚以图像外的一点 这个点就是极点。
# 为了得到更好的结果 我们应 使用分辨率比较高的图像和 non-planar 点
