opencv+SIFT+RANSAC+簡單的圖像拼接

OpenCV2.4.9+X64+VS2015測試通過

需要的小夥伴配置好環境就可以用了，只是個最簡單功能，初學者可以試試。
#include <stdio.h>  
#include <opencv2/nonfree/features2d.hpp>  
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/nonfree/nonfree.hpp>  
#include <opencv2/opencv.hpp>  
#include <cv.h>
#include <highgui.h>
#include <iostream>  


using namespace cv; 
using namespace std; 

int main()
{
	initModule_nonfree();//初始化模塊，使用SIFT或SURF時用到 
	Ptr<FeatureDetector> detector = FeatureDetector::create( "SIFT" );//創建SIFT特徵檢測器，可改成SURF/ORB
	Ptr<DescriptorExtractor> descriptor_extractor = DescriptorExtractor::create( "SIFT" );//創建特徵向量生成器，可改成SURF/ORB
	Ptr<DescriptorMatcher> descriptor_matcher = DescriptorMatcher::create( "BruteForce" );//創建特徵匹配器  
	if( detector.empty() || descriptor_extractor.empty() )  
		cout<<"fail to create detector!";  

	//讀入圖像  
	Mat img1 = imread("imLL.png");  
	Mat img2 = imread("imRR.png");  

	//特徵點檢測  
	double t = getTickCount();//當前滴答數  
	vector<KeyPoint> m_LeftKey,m_RightKey;  
	detector->detect( img1, m_LeftKey );//檢測img1中的SIFT特徵點，存儲到m_LeftKey中  
	detector->detect( img2, m_RightKey );  
	cout<<"圖像1特徵點個數:"<<m_LeftKey.size()<<endl;  
	cout<<"圖像2特徵點個數:"<<m_RightKey.size()<<endl;  

	//根據特徵點計算特徵描述子矩陣，即特徵向量矩陣  
	Mat descriptors1,descriptors2;  
	descriptor_extractor->compute( img1, m_LeftKey, descriptors1 );  
	descriptor_extractor->compute( img2, m_RightKey, descriptors2 );  
	t = ((double)getTickCount() - t)/getTickFrequency();  
	cout<<"SIFT算法用時："<<t<<"秒"<<endl;  

	cout<<"圖像1特徵描述矩陣大小："<<descriptors1.size()  
		<<"，特徵向量個數："<<descriptors1.rows<<"，維數："<<descriptors1.cols<<endl;  
	cout<<"圖像2特徵描述矩陣大小："<<descriptors2.size()  
		<<"，特徵向量個數："<<descriptors2.rows<<"，維數："<<descriptors2.cols<<endl;  

	//畫出特徵點  
	Mat img_m_LeftKey,img_m_RightKey;  
	drawKeypoints(img1,m_LeftKey,img_m_LeftKey,Scalar::all(-1),0);  
	drawKeypoints(img2,m_RightKey,img_m_RightKey,Scalar::all(-1),0);  
	//imshow("Src1",img_m_LeftKey);  
	//imshow("Src2",img_m_RightKey);  

	//特徵匹配  
	vector<DMatch> matches;//匹配結果  
	descriptor_matcher->match( descriptors1, descriptors2, matches );//匹配兩個圖像的特徵矩陣  
	cout<<"Match個數："<<matches.size()<<endl;  

	//計算匹配結果中距離的最大和最小值  
	//距離是指兩個特徵向量間的歐式距離，表明兩個特徵的差異，值越小表明兩個特徵點越接近  
	double max_dist = 0;  
	double min_dist = 100;  
	for(int i=0; i<matches.size(); i++)  
	{  
		double dist = matches[i].distance;  
		if(dist < min_dist) min_dist = dist;  
		if(dist > max_dist) max_dist = dist;  
	}  
	cout<<"最大距離："<<max_dist<<endl;  
	cout<<"最小距離："<<min_dist<<endl;  

	//篩選出較好的匹配點  
	vector<DMatch> goodMatches;  
	for(int i=0; i<matches.size(); i++)  
	{  
		if(matches[i].distance < 0.2 * max_dist)  
		{  
			goodMatches.push_back(matches[i]);  
		}  
	}  
	cout<<"goodMatch個數："<<goodMatches.size()<<endl;  

	//畫出匹配結果  
	Mat img_matches;  
	//紅色連接的是匹配的特徵點對，綠色是未匹配的特徵點  
	drawMatches(img1,m_LeftKey,img2,m_RightKey,goodMatches,img_matches,  
		Scalar::all(-1)/*CV_RGB(255,0,0)*/,CV_RGB(0,255,0),Mat(),2);  

	imshow("MatchSIFT",img_matches);  
	IplImage result=img_matches;

	waitKey(0);


	//RANSAC匹配過程
	vector<DMatch> m_Matches=goodMatches;
	// 分配空間
	int ptCount = (int)m_Matches.size();
	Mat p1(ptCount, 2, CV_32F);
	Mat p2(ptCount, 2, CV_32F);

	// 把Keypoint轉換爲Mat
	Point2f pt;
	for (int i=0; i<ptCount; i++)
	{
		pt = m_LeftKey[m_Matches[i].queryIdx].pt;
		p1.at<float>(i, 0) = pt.x;
		p1.at<float>(i, 1) = pt.y;

		pt = m_RightKey[m_Matches[i].trainIdx].pt;
		p2.at<float>(i, 0) = pt.x;
		p2.at<float>(i, 1) = pt.y;
	}

	// 用RANSAC方法計算F
	Mat m_Fundamental;
	vector<uchar> m_RANSACStatus;       // 這個變量用於存儲RANSAC後每個點的狀態
	findFundamentalMat(p1, p2, m_RANSACStatus, FM_RANSAC);
	
	// 計算野點個數

	int OutlinerCount = 0;
	for (int i=0; i<ptCount; i++)
	{
		if (m_RANSACStatus[i] == 0)    // 狀態爲0表示野點
		{
			OutlinerCount++;
		}
	}
	int InlinerCount = ptCount - OutlinerCount;   // 計算內點
	cout<<"內點數爲："<<InlinerCount<<endl;

	
   // 這三個變量用於保存內點和匹配關係
   vector<Point2f> m_LeftInlier;
   vector<Point2f> m_RightInlier;
   vector<DMatch> m_InlierMatches;

	m_InlierMatches.resize(InlinerCount);
	m_LeftInlier.resize(InlinerCount);
	m_RightInlier.resize(InlinerCount);
	InlinerCount=0;
	float inlier_minRx=img1.cols;        //用於存儲內點中右圖最小橫座標，以便後續融合

	for (int i=0; i<ptCount; i++)
	{
		if (m_RANSACStatus[i] != 0)
		{
			m_LeftInlier[InlinerCount].x = p1.at<float>(i, 0);
			m_LeftInlier[InlinerCount].y = p1.at<float>(i, 1);
			m_RightInlier[InlinerCount].x = p2.at<float>(i, 0);
			m_RightInlier[InlinerCount].y = p2.at<float>(i, 1);
			m_InlierMatches[InlinerCount].queryIdx = InlinerCount;
			m_InlierMatches[InlinerCount].trainIdx = InlinerCount;

			if(m_RightInlier[InlinerCount].x<inlier_minRx) inlier_minRx=m_RightInlier[InlinerCount].x;   //存儲內點中右圖最小橫座標

			InlinerCount++;
		}
	}

	// 把內點轉換爲drawMatches可以使用的格式
	vector<KeyPoint> key1(InlinerCount);
	vector<KeyPoint> key2(InlinerCount);
	KeyPoint::convert(m_LeftInlier, key1);
	KeyPoint::convert(m_RightInlier, key2);

    // 顯示計算F過後的內點匹配
	Mat OutImage;
	drawMatches(img1, key1, img2, key2, m_InlierMatches, OutImage);
	cvNamedWindow( "Match features", 1);
	cvShowImage("Match features", &IplImage(OutImage));
	waitKey(0);

	cvDestroyAllWindows();

	//矩陣H用以存儲RANSAC得到的單應矩陣
	Mat H = findHomography( m_LeftInlier, m_RightInlier, RANSAC );

	//存儲左圖四角，及其變換到右圖位置
	std::vector<Point2f> obj_corners(4);
	obj_corners[0] = Point(0,0); obj_corners[1] = Point( img1.cols, 0 );
	obj_corners[2] = Point( img1.cols, img1.rows ); obj_corners[3] = Point( 0, img1.rows );
	std::vector<Point2f> scene_corners(4);
	perspectiveTransform( obj_corners, scene_corners, H);

	//畫出變換後圖像位置
	Point2f offset( (float)img1.cols, 0);  
	line( OutImage, scene_corners[0]+offset, scene_corners[1]+offset, Scalar( 0, 255, 0), 4 );
	line( OutImage, scene_corners[1]+offset, scene_corners[2]+offset, Scalar( 0, 255, 0), 4 );
	line( OutImage, scene_corners[2]+offset, scene_corners[3]+offset, Scalar( 0, 255, 0), 4 );
	line( OutImage, scene_corners[3]+offset, scene_corners[0]+offset, Scalar( 0, 255, 0), 4 );
	imshow( "Good Matches & Object detection", OutImage );
		while(1)
	{
		if(waitKey(100)==19) cvSaveImage("E:\\warp_position.jpg",  &IplImage(OutImage));  
		if(waitKey(100)==27) break;
	}                                                              //按esc繼續，ctl+s保存圖像
	
	int drift = scene_corners[1].x;                                                        //儲存偏移量

	//新建一個矩陣存儲配準後四角的位置
	int width = int(max(abs(scene_corners[1].x), abs(scene_corners[2].x)));
	int height= img1.rows;                                                                  //或者：int height = int(max(abs(scene_corners[2].y), abs(scene_corners[3].y)));
	float origin_x=0,origin_y=0;
		if(scene_corners[0].x<0) {
			if (scene_corners[3].x<0) origin_x+=min(scene_corners[0].x,scene_corners[3].x);
		else origin_x+=scene_corners[0].x;}
		width-=int(origin_x);
	if(scene_corners[0].y<0) {
		if (scene_corners[1].y) origin_y+=min(scene_corners[0].y,scene_corners[1].y);
		else origin_y+=scene_corners[0].y;}
	//可選：height-=int(origin_y);
	Mat imageturn=Mat::zeros(width,height,img1.type());

	//獲取新的變換矩陣，使圖像完整顯示
	for (int i=0;i<4;i++) {scene_corners[i].x -= origin_x; } 	//可選：scene_corners[i].y -= (float)origin_y; }
	Mat H1=getPerspectiveTransform(obj_corners, scene_corners);

	//進行圖像變換，顯示效果
	warpPerspective(img1,imageturn,H1,Size(width,height));	
	imshow("image_Perspective", imageturn);
	waitKey(0);


	//圖像融合
	int width_ol=width-int(inlier_minRx-origin_x);
	int start_x=int(inlier_minRx-origin_x);
    cout<<"width: "<<width<<endl;
	cout<<"img1.width: "<<img1.cols<<endl;
	cout<<"start_x: "<<start_x<<endl;
	cout<<"width_ol: "<<width_ol<<endl;

	uchar* ptr=imageturn.data;
	double alpha=0, beta=1;
	for (int row=0;row<height;row++) {
		ptr=imageturn.data+row*imageturn.step+(start_x)*imageturn.elemSize();
		for(int col=0;col<width_ol;col++)
		{
			uchar* ptr_c1=ptr+imageturn.elemSize1();  uchar*  ptr_c2=ptr_c1+imageturn.elemSize1();
			uchar* ptr2=img2.data+row*img2.step+(col+int(inlier_minRx))*img2.elemSize();
			uchar* ptr2_c1=ptr2+img2.elemSize1();  uchar* ptr2_c2=ptr2_c1+img2.elemSize1();

			
			alpha=double(col)/double(width_ol); beta=1-alpha;

			if (*ptr==0&&*ptr_c1==0&&*ptr_c2==0) {
				*ptr=(*ptr2);
				*ptr_c1=(*ptr2_c1);
				*ptr_c2=(*ptr2_c2);
			}

			*ptr=(*ptr)*beta+(*ptr2)*alpha;
			*ptr_c1=(*ptr_c1)*beta+(*ptr2_c1)*alpha;
			*ptr_c2=(*ptr_c2)*beta+(*ptr2_c2)*alpha;

			ptr+=imageturn.elemSize();
		}	}
	
	//imshow("image_overlap", imageturn);
	//waitKey(0);

	Mat img_result=Mat::zeros(height,width+img2.cols-drift,img1.type());
	uchar* ptr_r=imageturn.data;
	
	for (int row=0;row<height;row++) {
		ptr_r=img_result.data+row*img_result.step;

		for(int col=0;col<imageturn.cols;col++)
		{
			uchar* ptr_rc1=ptr_r+imageturn.elemSize1();  uchar*  ptr_rc2=ptr_rc1+imageturn.elemSize1();

			uchar* ptr=imageturn.data+row*imageturn.step+col*imageturn.elemSize();
			uchar* ptr_c1=ptr+imageturn.elemSize1();  uchar*  ptr_c2=ptr_c1+imageturn.elemSize1();

			*ptr_r=*ptr;
			*ptr_rc1=*ptr_c1;
			*ptr_rc2=*ptr_c2;

			ptr_r+=img_result.elemSize();
		}	

		ptr_r=img_result.data+row*img_result.step+imageturn.cols*img_result.elemSize();
		for(int col=imageturn.cols;col<img_result.cols;col++)
		{
			uchar* ptr_rc1=ptr_r+imageturn.elemSize1();  uchar*  ptr_rc2=ptr_rc1+imageturn.elemSize1();

			uchar* ptr2=img2.data+row*img2.step+(col-imageturn.cols+drift)*img2.elemSize();
			uchar* ptr2_c1=ptr2+img2.elemSize1();  uchar* ptr2_c2=ptr2_c1+img2.elemSize1();

			*ptr_r=*ptr2;
			*ptr_rc1=*ptr2_c1;
			*ptr_rc2=*ptr2_c2;

			ptr_r+=img_result.elemSize();
		}	
	}
	
	imshow("image_result", img_result);
		while(1)
	{
		if(waitKey(100)==19) cvSaveImage("E:\\final_result.jpg",  &IplImage(img_result));  
		if(waitKey(100)==27) break;                     //按esc退出，ctl+s保存圖像
	}

	return 0;
}
opencv+SIFT+RANSAC+簡單的圖像拼接

OpenCV2.4.9+X64+VS2015測試通過

示例

opencv+SIFT+RANSAC+簡單的圖像拼接

LeetCode 109 有序鏈表轉換二叉搜索樹 C++

opencv 32位申請內存不足突破2G方法

LeetCode 104. 二叉樹的最大深度 C++三種解法

LeetCode 394.字符串解碼

Mac下配置sublime實現LaTeX

https://yachay.unat.edu.pe/blog/index.php?comment_area=format_blog&comment_component=blog&comment_co

linux以太網驅動總結
