sift+RANSAC+findHomography
来源:互联网 发布:增值税发票扫描软件 编辑:程序博客网 时间:2024/06/01 19:43
#include <stdio.h>
#include <iostream>
#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/features2d/features2d.hpp"
#include "opencv2/calib3d/calib3d.hpp"
#include "opencv2/nonfree/nonfree.hpp"
using namespace cv;
/** @function main sift特征对尺度缩放、旋转、亮度变化等保持不变性 */
int main(int argc, char** argv)
{
Mat img_object = imread("4.jpg");
Mat img_scene = imread("3.jpg");
if (!img_object.data || !img_scene.data)
{
std::cout << " --(!) Error reading images " << std::endl; return -1;
}
resize(img_object, img_object, cv::Size(img_object.cols / 2, img_object.rows / 2), (0, 0), (0, 0), cv::INTER_LINEAR);
/*
//-- Step 1: Detect the keypoints using SURF Detector
int minHessian = 700;
SurfFeatureDetector detector(minHessian);
std::vector<KeyPoint> keypoints_object, keypoints_scene;
detector.detect(img_object, keypoints_object);
detector.detect(img_scene, keypoints_scene);
//-- Step 2: Calculate descriptors (feature vectors)
SurfDescriptorExtractor extractor;
Mat descriptors_object, descriptors_scene;
extractor.compute(img_object, keypoints_object, descriptors_object);
extractor.compute(img_scene, keypoints_scene, descriptors_scene);
//-- Step 3: Matching descriptor vectors using FLANN matcher
FlannBasedMatcher matcher;
std::vector< DMatch > matches;
matcher.match(descriptors_object, descriptors_scene, matches);
*/
SiftFeatureDetector siftDetector;
vector<KeyPoint>keypoints_object;
vector<KeyPoint>keypoints_scene;
siftDetector.detect(img_object, keypoints_object);
siftDetector.detect(img_scene, keypoints_scene);
SiftDescriptorExtractor descriptor;
Mat descriptors_object;
Mat descriptors_scene;
descriptor.compute(img_object, keypoints_object, descriptors_object);
descriptor.compute(img_scene, keypoints_scene, descriptors_scene);
FlannBasedMatcher matcher;
std::vector< DMatch > matches;
matcher.match(descriptors_object, descriptors_scene, matches);
double max_dist = 0; double min_dist = 10000;
//-- Quick calculation of max and min distances between keypoints
for (int i = 0; i < descriptors_object.rows; i++)
{
double dist = matches[i].distance;
if (dist < min_dist) min_dist = dist;
if (dist > max_dist) max_dist = dist;
}
printf("-- Max dist : %f \n", max_dist);
printf("-- Min dist : %f \n", min_dist);
//-- Draw only "good" matches (i.e. whose distance is less than 3*min_dist )
std::vector< DMatch > good_matches;
if (descriptors_object.rows > 100)
{
for (int i = 0; i < descriptors_object.rows; i++)
{
if (matches[i].distance < (max_dist + min_dist) / 2)
{
good_matches.push_back(matches[i]);
}
}
}
else
{
for (int i = 0; i < descriptors_object.rows; i++)
{
if (matches[i].distance < max_dist)
{
good_matches.push_back(matches[i]);
}
}
}
Mat img_matches;
drawMatches(img_object, keypoints_object, img_scene, keypoints_scene,
good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),
vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
imshow("image", img_matches);
waitKey(0);
//Align all points
vector<KeyPoint> alignedKps1, alignedKps2;
for (size_t i = 0; i < good_matches.size(); i++) {
alignedKps1.push_back(keypoints_object[good_matches[i].queryIdx]);
alignedKps2.push_back(keypoints_scene[good_matches[i].trainIdx]);
}
//Keypoints to points
vector<Point2f> ps1, ps2;
for (unsigned i = 0; i < alignedKps1.size(); i++)
ps1.push_back(alignedKps1[i].pt);
for (unsigned i = 0; i < alignedKps2.size(); i++)
ps2.push_back(alignedKps2[i].pt);
vector<uchar> m_RANSACStatus;
Mat m_Fundamental = findFundamentalMat(ps1, ps2, m_RANSACStatus, CV_FM_RANSAC, 3, 0.99);
for (unsigned int i = good_matches.size() - 1; i > 0; i--) {
if (m_RANSACStatus[i] == 0){
good_matches.erase(good_matches.begin() + i);
printf("%d\n", i);
}
}
Mat img_matches2;
drawMatches(img_object, keypoints_object, img_scene, keypoints_scene,
good_matches, img_matches2, Scalar::all(-1), Scalar::all(-1),
vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
imshow("image2", img_matches2);
waitKey(0);
//-- Localize the object
std::vector<Point2f> obj;
std::vector<Point2f> scene;
for (unsigned int i = 0; i < good_matches.size(); i++)
{
//-- Get the keypoints from the good matches
obj.push_back(keypoints_object[good_matches[i].queryIdx].pt);
scene.push_back(keypoints_scene[good_matches[i].trainIdx].pt);
}
Mat H = findHomography(obj, scene, CV_RANSAC);
//-- Get the corners from the image_1 ( the object to be "detected" )
std::vector<Point2f> obj_corners(4);
obj_corners[0] = cvPoint(0, 0); obj_corners[1] = cvPoint(img_object.cols, 0);
obj_corners[2] = cvPoint(img_object.cols, img_object.rows); obj_corners[3] = cvPoint(0, img_object.rows);
std::vector<Point2f> scene_corners(4);
perspectiveTransform(obj_corners, scene_corners, H);
//-- Draw lines between the corners (the mapped object in the scene - image_2 )
line(img_matches2, scene_corners[0] + Point2f(img_object.cols, 0), scene_corners[1] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
line(img_matches2, scene_corners[1] + Point2f(img_object.cols, 0), scene_corners[2] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
line(img_matches2, scene_corners[2] + Point2f(img_object.cols, 0), scene_corners[3] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
line(img_matches2, scene_corners[3] + Point2f(img_object.cols, 0), scene_corners[0] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
//-- Show detected matches
imshow("Good Matches & Object detection", img_matches2);
waitKey(0);
return 0;
#include <iostream>
#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/features2d/features2d.hpp"
#include "opencv2/calib3d/calib3d.hpp"
#include "opencv2/nonfree/nonfree.hpp"
using namespace cv;
/** @function main sift特征对尺度缩放、旋转、亮度变化等保持不变性 */
int main(int argc, char** argv)
{
Mat img_object = imread("4.jpg");
Mat img_scene = imread("3.jpg");
if (!img_object.data || !img_scene.data)
{
std::cout << " --(!) Error reading images " << std::endl; return -1;
}
resize(img_object, img_object, cv::Size(img_object.cols / 2, img_object.rows / 2), (0, 0), (0, 0), cv::INTER_LINEAR);
/*
//-- Step 1: Detect the keypoints using SURF Detector
int minHessian = 700;
SurfFeatureDetector detector(minHessian);
std::vector<KeyPoint> keypoints_object, keypoints_scene;
detector.detect(img_object, keypoints_object);
detector.detect(img_scene, keypoints_scene);
//-- Step 2: Calculate descriptors (feature vectors)
SurfDescriptorExtractor extractor;
Mat descriptors_object, descriptors_scene;
extractor.compute(img_object, keypoints_object, descriptors_object);
extractor.compute(img_scene, keypoints_scene, descriptors_scene);
//-- Step 3: Matching descriptor vectors using FLANN matcher
FlannBasedMatcher matcher;
std::vector< DMatch > matches;
matcher.match(descriptors_object, descriptors_scene, matches);
*/
SiftFeatureDetector siftDetector;
vector<KeyPoint>keypoints_object;
vector<KeyPoint>keypoints_scene;
siftDetector.detect(img_object, keypoints_object);
siftDetector.detect(img_scene, keypoints_scene);
SiftDescriptorExtractor descriptor;
Mat descriptors_object;
Mat descriptors_scene;
descriptor.compute(img_object, keypoints_object, descriptors_object);
descriptor.compute(img_scene, keypoints_scene, descriptors_scene);
FlannBasedMatcher matcher;
std::vector< DMatch > matches;
matcher.match(descriptors_object, descriptors_scene, matches);
double max_dist = 0; double min_dist = 10000;
//-- Quick calculation of max and min distances between keypoints
for (int i = 0; i < descriptors_object.rows; i++)
{
double dist = matches[i].distance;
if (dist < min_dist) min_dist = dist;
if (dist > max_dist) max_dist = dist;
}
printf("-- Max dist : %f \n", max_dist);
printf("-- Min dist : %f \n", min_dist);
//-- Draw only "good" matches (i.e. whose distance is less than 3*min_dist )
std::vector< DMatch > good_matches;
if (descriptors_object.rows > 100)
{
for (int i = 0; i < descriptors_object.rows; i++)
{
if (matches[i].distance < (max_dist + min_dist) / 2)
{
good_matches.push_back(matches[i]);
}
}
}
else
{
for (int i = 0; i < descriptors_object.rows; i++)
{
if (matches[i].distance < max_dist)
{
good_matches.push_back(matches[i]);
}
}
}
Mat img_matches;
drawMatches(img_object, keypoints_object, img_scene, keypoints_scene,
good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),
vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
imshow("image", img_matches);
waitKey(0);
//Align all points
vector<KeyPoint> alignedKps1, alignedKps2;
for (size_t i = 0; i < good_matches.size(); i++) {
alignedKps1.push_back(keypoints_object[good_matches[i].queryIdx]);
alignedKps2.push_back(keypoints_scene[good_matches[i].trainIdx]);
}
//Keypoints to points
vector<Point2f> ps1, ps2;
for (unsigned i = 0; i < alignedKps1.size(); i++)
ps1.push_back(alignedKps1[i].pt);
for (unsigned i = 0; i < alignedKps2.size(); i++)
ps2.push_back(alignedKps2[i].pt);
vector<uchar> m_RANSACStatus;
Mat m_Fundamental = findFundamentalMat(ps1, ps2, m_RANSACStatus, CV_FM_RANSAC, 3, 0.99);
for (unsigned int i = good_matches.size() - 1; i > 0; i--) {
if (m_RANSACStatus[i] == 0){
good_matches.erase(good_matches.begin() + i);
printf("%d\n", i);
}
}
Mat img_matches2;
drawMatches(img_object, keypoints_object, img_scene, keypoints_scene,
good_matches, img_matches2, Scalar::all(-1), Scalar::all(-1),
vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
imshow("image2", img_matches2);
waitKey(0);
//-- Localize the object
std::vector<Point2f> obj;
std::vector<Point2f> scene;
for (unsigned int i = 0; i < good_matches.size(); i++)
{
//-- Get the keypoints from the good matches
obj.push_back(keypoints_object[good_matches[i].queryIdx].pt);
scene.push_back(keypoints_scene[good_matches[i].trainIdx].pt);
}
Mat H = findHomography(obj, scene, CV_RANSAC);
//-- Get the corners from the image_1 ( the object to be "detected" )
std::vector<Point2f> obj_corners(4);
obj_corners[0] = cvPoint(0, 0); obj_corners[1] = cvPoint(img_object.cols, 0);
obj_corners[2] = cvPoint(img_object.cols, img_object.rows); obj_corners[3] = cvPoint(0, img_object.rows);
std::vector<Point2f> scene_corners(4);
perspectiveTransform(obj_corners, scene_corners, H);
//-- Draw lines between the corners (the mapped object in the scene - image_2 )
line(img_matches2, scene_corners[0] + Point2f(img_object.cols, 0), scene_corners[1] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
line(img_matches2, scene_corners[1] + Point2f(img_object.cols, 0), scene_corners[2] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
line(img_matches2, scene_corners[2] + Point2f(img_object.cols, 0), scene_corners[3] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
line(img_matches2, scene_corners[3] + Point2f(img_object.cols, 0), scene_corners[0] + Point2f(img_object.cols, 0), Scalar(0, 255, 0), 4);
//-- Show detected matches
imshow("Good Matches & Object detection", img_matches2);
waitKey(0);
return 0;
}
阅读全文
0 0
- sift+RANSAC+findHomography
- 利用SIFT和RANSAC算法(openCV框架)实现物体的检测与定位,并求出变换矩阵(findFundamentalMat和findHomography的比较)
- RANSAC消除SIFT错配
- 【opencv】sift + RANSAC
- SIFT(ASIFT) Matching with RANSAC
- SIFT(ASIFT) Matching with RANSAC
- SIFT+RANSAC做图像矫正
- RANSAC用于SIFT特征匹配
- openCV中的findHomography函数分析以及RANSAC算法的详解(源代码分析)
- 利用RANSAC算法筛选SIFT特征匹配
- 利用RANSAC算法筛选SIFT特征匹配
- 利用RANSAC算法筛选SIFT特征匹配
- 利用RANSAC算法筛选SIFT特征匹配
- 利用RANSAC算法筛选SIFT特征匹配
- 利用RANSAC算法筛选SIFT特征匹配
- SIFT特征检测与RANSAC过滤
- 利用RANSAC算法筛选SIFT特征匹配
- ransac算法去除sift的噪声
- u-boot移植随笔(8):EEPROM移植及测试
- 在xilinx SDK中查询API函数的方法
- 视觉slam14讲——第10讲后端1
- 异常向量表
- golang调用lua脚本之安装golua
- sift+RANSAC+findHomography
- kubernetes1.8.4 安装指南 -- 6. 安装kubernetes master
- 如何下载Spring jar包(dist文件)
- Asp.net 框架解析----生成编译后的文件
- BZOJ2938 POI2000 病毒 补全AC自动机 Trie图判环
- 杭电acm P2019数列有序
- 分享式商业模型
- 使用阿里云的国内镜像仓库地址
- 二分图的匈牙利算法