学习OpenCV——通过KeyPoints进行目标定位
来源:互联网 发布:怎么在淘宝上领优惠券 编辑:程序博客网 时间:2024/05/17 04:42
目前的AR应用基本都是基于marker的比较多,但是不依靠marker首先要完成的定位工作。这篇文章主要描述,使用特征点进行检测和定位的问题(其中包含一些matching优化方式,具体请参考:学习OpenCV——KeyPoint Matching 优化方式)。
步骤:
1. 目标图特征点检测和描述子计算;
2. 打开camera采集图像,并计算特征点及描述子;
3. 进行特征点匹配,采用KNN或Cross-check方式;
4. 寻找单应性变换矩阵,并通过单应性变换矩阵进行进一步优化,去除伪匹配;
5. 通过单应性变换矩阵进行目标定位。
步骤:
1. 目标图特征点检测和描述子计算;
2. 打开camera采集图像,并计算特征点及描述子;
3. 进行特征点匹配,采用KNN或Cross-check方式;
4. 寻找单应性变换矩阵,并通过单应性变换矩阵进行进一步优化,去除伪匹配;
5. 通过单应性变换矩阵进行目标定位。
#include <opencv/cv.h>#include <opencv/highgui.h>#include <vector>#include <iostream>using namespace cv;using namespace std;Mat src,frameImg;int width;int height;vector<Point> srcCorner(4);vector<Point> dstCorner(4);static bool createDetectorDescriptorMatcher( const string& detectorType, const string& descriptorType, const string& matcherType,Ptr<FeatureDetector>& featureDetector,Ptr<DescriptorExtractor>& descriptorExtractor,Ptr<DescriptorMatcher>& descriptorMatcher ){cout << "< Creating feature detector, descriptor extractor and descriptor matcher ..." << endl;featureDetector = FeatureDetector::create( detectorType );descriptorExtractor = DescriptorExtractor::create( descriptorType );descriptorMatcher = DescriptorMatcher::create( matcherType );cout << ">" << endl;bool isCreated = !( featureDetector.empty() || descriptorExtractor.empty() || descriptorMatcher.empty() );if( !isCreated )cout << "Can not create feature detector or descriptor extractor or descriptor matcher of given types." << endl << ">" << endl;return isCreated;}bool refineMatchesWithHomography(const std::vector<cv::KeyPoint>& queryKeypoints, const std::vector<cv::KeyPoint>& trainKeypoints, float reprojectionThreshold, std::vector<cv::DMatch>& matches, cv::Mat& homography ){const int minNumberMatchesAllowed = 4; if (matches.size() < minNumberMatchesAllowed) return false; // Prepare data for cv::findHomography std::vector<cv::Point2f> queryPoints(matches.size()); std::vector<cv::Point2f> trainPoints(matches.size()); for (size_t i = 0; i < matches.size(); i++) { queryPoints[i] = queryKeypoints[matches[i].queryIdx].pt; trainPoints[i] = trainKeypoints[matches[i].trainIdx].pt; } // Find homography matrix and get inliers mask std::vector<unsigned char> inliersMask(matches.size()); homography = cv::findHomography(queryPoints, trainPoints, CV_FM_RANSAC, reprojectionThreshold, inliersMask); std::vector<cv::DMatch> inliers; for (size_t i=0; i<inliersMask.size(); i++) { if (inliersMask[i]) inliers.push_back(matches[i]); } matches.swap(inliers);Mat homoShow;drawMatches(src,queryKeypoints,frameImg,trainKeypoints,matches,homoShow,Scalar::all(-1),CV_RGB(255,255,255),Mat(),2); imshow("homoShow",homoShow); return matches.size() > minNumberMatchesAllowed; }bool matchingDescriptor(const vector<KeyPoint>& queryKeyPoints,const vector<KeyPoint>& trainKeyPoints,const Mat& queryDescriptors,const Mat& trainDescriptors, Ptr<DescriptorMatcher>& descriptorMatcher,bool enableRatioTest = true){vector<vector<DMatch>> m_knnMatches;vector<DMatch>m_Matches;if (enableRatioTest){cout<<"KNN Matching"<<endl;const float minRatio = 1.f / 1.5f;descriptorMatcher->knnMatch(queryDescriptors,trainDescriptors,m_knnMatches,2);for (size_t i=0; i<m_knnMatches.size(); i++){const cv::DMatch& bestMatch = m_knnMatches[i][0];const cv::DMatch& betterMatch = m_knnMatches[i][1];float distanceRatio = bestMatch.distance / betterMatch.distance;if (distanceRatio < minRatio){m_Matches.push_back(bestMatch);}}}else{cout<<"Cross-Check"<<endl;Ptr<cv::DescriptorMatcher> BFMatcher(new cv::BFMatcher(cv::NORM_HAMMING, true));BFMatcher->match(queryDescriptors,trainDescriptors, m_Matches );}Mat homo;float homographyReprojectionThreshold = 1.0;bool homographyFound = refineMatchesWithHomography(queryKeyPoints,trainKeyPoints,homographyReprojectionThreshold,m_Matches,homo);if (!homographyFound)return false;else{double h[9];bool isFound=true;h[0]=homo.at<double>(0,0); h[1]=homo.at<double>(0,1); h[2]=homo.at<double>(0,2); h[3]=homo.at<double>(1,0); h[4]=homo.at<double>(1,1); h[5]=homo.at<double>(1,2); h[6]=homo.at<double>(2,0); h[7]=homo.at<double>(2,1); h[8]=homo.at<double>(2,2);printf("homo\n" "%f %f %f\n" "%f %f %f\n" "%f %f %f\n", homo.at<double>(0,0), homo.at<double>(0,1), homo.at<double>(0,2), homo.at<double>(1,0), homo.at<double>(1,1), homo.at<double>(1,2), homo.at<double>(2,0), homo.at<double>(2,1), homo.at<double>(2,2)); for (int i=0;i<4;i++){float x = (float)srcCorner[i].x;float y = (float)srcCorner[i].y; float Z = (float)1./(h[6]*x + h[7]*y + h[8]); float X = (float)(h[0]*x + h[1]*y + h[2])*Z; float Y = (float)(h[3]*x + h[4]*y + h[5])*Z; //if(X>=0&&X<width&&Y>=0&&Y<height){dstCorner[i]=Point(int(X),int(Y));}//else{//isFound &= false;}}if (isFound){line(frameImg,dstCorner[0],dstCorner[1],CV_RGB(255,0,0),2);line(frameImg,dstCorner[1],dstCorner[2],CV_RGB(255,0,0),2);line(frameImg,dstCorner[2],dstCorner[3],CV_RGB(255,0,0),2);line(frameImg,dstCorner[3],dstCorner[0],CV_RGB(255,0,0),2);return true;}return true;}}int main(){string filename = "D:\\Img\\Heads\\03.jpg";src = imread(filename,0);width = src.cols;height = src.rows;string detectorType = "ORB";string descriptorType = "ORB";string matcherType = "BruteForce";Ptr<FeatureDetector> featureDetector;Ptr<DescriptorExtractor> descriptorExtractor;Ptr<DescriptorMatcher> descriptorMatcher;if( !createDetectorDescriptorMatcher( detectorType, descriptorType, matcherType, featureDetector, descriptorExtractor, descriptorMatcher ) ){cout<<"Creat Detector Descriptor Matcher False!"<<endl;return -1;}//Intial: read the pattern img keyPoint vector<KeyPoint> queryKeypoints; Mat queryDescriptor; featureDetector->detect(src,queryKeypoints); descriptorExtractor->compute(src,queryKeypoints,queryDescriptor); VideoCapture cap(0); // open the default camera if(!cap.isOpened()) // check if we succeeded { cout<<"Can't Open Camera!"<<endl; return -1; } srcCorner[0] = Point(0,0); srcCorner[1] = Point(width,0); srcCorner[2] = Point(width,height); srcCorner[3] = Point(0,height); vector<KeyPoint> trainKeypoints; Mat trainDescriptor; Mat frame,grayFrame; char key=0; //frame = imread("D:\\Img\\Heads\\00.jpg"); while (key!=27) { cap>>frame; frame.copyTo(frameImg); cvtColor(frame,grayFrame,CV_BGR2GRAY); trainKeypoints.clear();// if (!trainDescriptor.empty())trainDescriptor.setTo(0); featureDetector->detect(grayFrame,trainKeypoints); if(trainKeypoints.size()!=0) { descriptorExtractor->compute(grayFrame,trainKeypoints,trainDescriptor); bool isFound = matchingDescriptor(queryKeypoints,trainKeypoints,queryDescriptor,trainDescriptor,descriptorMatcher); imshow("foundImg",frameImg); } key = waitKey(1); } }
0 0
- 学习OpenCV——通过KeyPoints进行目标定位
- 学习OpenCV——通过KeyPoints进行目标定位
- 学习OpenCV范例(二十一)——Keypoints+Knn+findHomography进行目标定位
- 学习OpenCV范例(二十一)——Keypoints+Knn+findHomography进行目标定位
- Keypoints+Knn+findHomography进行目标定位
- Keypoints+Knn+findHomography进行目标定位
- 利用OpenCV通过HSV直方图来进行图片定位
- 学习OpenCV——车牌检测(定位)
- 学习OpenCV——车牌检测(定位)
- 学习OpenCV——车牌检测(定位)
- 学习OpenCV——车牌检测(定位)
- Python-opencv之目标定位
- 自动光学检查(AOI) 的核心——快速准确对目标进行定位配准
- zynq学习笔记——HLS FAST corner导出keypoints(一)
- zynq学习笔记——HLS FAST corner导出keypoints(二)
- 利用OpenCV定位目标区域并剪切
- (转) 学习OpenCV——车牌检测(定位)
- Android 通过GPS进行定位
- VS2010的快捷键和VS2012变化的快捷键
- ios获取当前连接的网络名称
- 【一切皆有可能】一个平面设计师转程序员的全过程(手游程序员)
- UILabel 的常见属性和方法:
- 在asp.net web form项目中使用json
- 学习OpenCV——通过KeyPoints进行目标定位
- 人世间最美好的一个地方
- 第四周作业-键盘输入数据 和 数据类型。
- Android - 开发实例(10):让控件变得可拖拽
- 关于pmon、smon、mman、mmon、mmnl后台进程的解释
- 第四周作业
- 定时任务 Cron 格式
- iOS系列译文:深入理解 CocoaPods
- 实习期经验记录,比较杂乱