贾志刚OpenCV3.2图像分割实战学习笔记

OpenCV图像分割资料分享：贾志刚的OpenCV图像分割实战视频教程全套资料（包含配套视频、配套PPT的PDF文件、源码和用到的图片素材等）：点这里

实例1：读取单张JPG图像（测试环境）

实例2：KMeans对随机生成数据进行分类

实例3：KMeans图像分割

实例4：GMM（高斯混合模型）样本数据训练与预言

实例5：GMM（高斯混合模型）图像分割

实例6：基于距离变换的分水岭粘连对象分离与计数

实例7：基于分水岭图像分割

实例8：Grabcut原理与演示应用

实例9：K-Means-证件照背景替换

实例10：绿幕视频背景替换

实例1：读取单张JPG图像（测试环境）

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;int main(int argc, char** argv)
{Mat src = imread("toux.jpg");//读取图像if (src.empty()) {printf("could not load image..\n");return -1;}   namedWindow("input image", CV_WINDOW_AUTOSIZE);//自动调整显示窗口大小imshow("input image", src);//显示图像waitKey(0);//等待return 0;
}

KMeans方法概述

1. 无监督学习方法（整个过程不需要人为干预）
2. 分类问题，输入分类数目，初始化中心位置
3. 硬分类方法，以距离度量（离那个中心点近就被划分为哪一类）
4. 迭代分类为聚类（不断迭代寻找最优中心点）

基本流程：

实例2：KMeans对随机生成数据进行分类

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace std;int main(int argc, char** argv) {Mat img(500, 600, CV_8UC3);//定义一张图RNG rng(12345);//定义随机数//不同类定义为不同颜色Scalar colorTab[] = {Scalar(0, 0, 255),Scalar(0, 255, 0),Scalar(255, 0, 0),Scalar(0, 255, 255),Scalar(255, 0, 255)};int numCluster = rng.uniform(2, 5);//定义分类种类数量块printf("number of clusters : %d\n", numCluster);//设置从原图像中抽取多少个数据点int sampleCount = rng.uniform(5, 1000);Mat points(sampleCount, 1, CV_32FC2);Mat labels;Mat centers;// 生成随机数for (int k = 0; k < numCluster; k++) {Point center;center.x = rng.uniform(0, img.cols);center.y = rng.uniform(0, img.rows);//得到不同小块Mat pointChunk = points.rowRange(k*sampleCount / numCluster, k == numCluster - 1 ? sampleCount : (k + 1)*sampleCount / numCluster);//用随机数对小块点进行填充rng.fill(pointChunk, RNG::NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));}randShuffle(points, 1, &rng);// 使用KMeanskmeans(points, numCluster, labels, TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1), 3, KMEANS_PP_CENTERS, centers);// 用不同颜色显示分类img = Scalar::all(255);for (int i = 0; i < sampleCount; i++) {int index = labels.at<int>(i);Point p = points.at<Point2f>(i);circle(img, p, 2, colorTab[index], -1, 8);}// 每个聚类的中心来绘制圆for (int i = 0; i < centers.rows;  i++) {int x = centers.at<float>(i, 0);int y = centers.at<float>(i, 1);printf("c.x= %d, c.y=%d", x, y);circle(img, Point(x, y), 40, colorTab[i], 1, LINE_AA);}imshow("KMeans-Data-Demo", img);waitKey(0);return 0;
}

可见，随机生成的数据被分成了四块，每块的中心坐标如下：

实例3：KMeans图像分割

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace std;int main(int argc, char** argv) {Mat src = imread("toux.jpg");if (src.empty()) {printf("could not load image...\n");return -1;}namedWindow("input image", CV_WINDOW_AUTOSIZE);imshow("input image", src);Scalar colorTab[] = {Scalar(0, 0, 255),Scalar(0, 255, 0),Scalar(255, 0, 0),Scalar(0, 255, 255),Scalar(255, 0, 255)};int width = src.cols;//图像的列int height = src.rows;//图像的行int dims = src.channels();//图像的通道数// 初始化定义int sampleCount = width*height;//获取图像的像素点数int clusterCount = 4;//要分类块数Mat points(sampleCount, dims, CV_32F, Scalar(10));//定义样本数据Mat labels;Mat centers(clusterCount, 1, points.type());//定义中心点(浮点数)// RGB 数据转换到样本数据int index = 0;for (int row = 0; row < height; row++) {for (int col = 0; col < width; col++) {index = row*width + col;Vec3b bgr = src.at<Vec3b>(row, col);points.at<float>(index, 0) = static_cast<int>(bgr[0]);//通道0points.at<float>(index, 1) = static_cast<int>(bgr[1]);//通道1points.at<float>(index, 2) = static_cast<int>(bgr[2]);//通道2}}// 运行K-MeansTermCriteria criteria = TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1);kmeans(points, clusterCount, labels, criteria, 3, KMEANS_PP_CENTERS, centers);//尝试3次// 显示图像分割结果Mat result = Mat::zeros(src.size(), src.type());for (int row = 0; row < height; row++) {for (int col = 0; col < width; col++) {index = row*width + col;int label = labels.at<int>(index, 0);result.at<Vec3b>(row, col)[0] = colorTab[label][0];result.at<Vec3b>(row, col)[1] = colorTab[label][1];result.at<Vec3b>(row, col)[2] = colorTab[label][2];}}for (int i = 0; i < centers.rows; i++) {int x = centers.at<float>(i, 0);int y = centers.at<float>(i, 1);printf("center %d = c.x : %d, c.y : %d\n", i, x, y);}imshow("KMeans Image Segmentation Demo", result);waitKey(0);return 0;
}

注：中心点是相对于图像RGB像素值而求定的位置。

实例4：GMM（高斯混合模型）样本数据训练与预言

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace cv::ml;
using namespace std;int main(int argc, char** argv) {Mat img = Mat::zeros(500, 500, CV_8UC3);RNG rng(12345);Scalar colorTab[] = {Scalar(0, 0, 255),Scalar(0, 255, 0),Scalar(255, 0, 0),Scalar(0, 255, 255),Scalar(255, 0, 255)};int numCluster = rng.uniform(2, 5);printf("number of clusters : %d\n", numCluster);int sampleCount = rng.uniform(5, 1000);Mat points(sampleCount, 2, CV_32FC1);Mat labels;// 生成随机数for (int k = 0; k < numCluster; k++) {Point center;center.x = rng.uniform(0, img.cols);center.y = rng.uniform(0, img.rows);Mat pointChunk = points.rowRange(k*sampleCount / numCluster,k == numCluster - 1 ? sampleCount : (k + 1)*sampleCount / numCluster);rng.fill(pointChunk, RNG::NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));}randShuffle(points, 1, &rng);Ptr<EM> em_model = EM::create();em_model->setClustersNumber(numCluster);em_model->setCovarianceMatrixType(EM::COV_MAT_SPHERICAL);//协方差矩阵//训练次数设置为100em_model->setTermCriteria(TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 100, 0.1));em_model->trainEM(points, noArray(), labels, noArray());// classify every image pixelsMat sample(1, 2, CV_32FC1);for (int row = 0; row < img.rows; row++) {for (int col = 0; col < img.cols; col++) {sample.at<float>(0) = (float)col;sample.at<float>(1) = (float)row;int response = cvRound(em_model->predict2(sample, noArray())[1]);Scalar c = colorTab[response];circle(img, Point(col, row), 1, c*0.75, -1);}}// draw the clustersfor (int i = 0; i < sampleCount; i++) {Point p(cvRound(points.at<float>(i, 0)), points.at<float>(i, 1));circle(img, p, 1, colorTab[labels.at<int>(i)], -1);}imshow("GMM-EM Demo", img);waitKey(0);return 0;
}

实例5：GMM（高斯混合模型）图像分割

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace cv::ml;
using namespace std;int main(int argc, char** argv) {Mat src = imread("toux.jpg");if (src.empty()) {printf("could not load iamge...\n");return -1;}namedWindow("input image", CV_WINDOW_AUTOSIZE);imshow("input image", src);// 初始化int numCluster = 3;const Scalar colors[] = {Scalar(255, 0, 0),Scalar(0, 255, 0),Scalar(0, 0, 255),Scalar(255, 255, 0)};int width = src.cols;int height = src.rows;int dims = src.channels();int nsamples = width*height;Mat points(nsamples, dims, CV_64FC1);Mat labels;Mat result = Mat::zeros(src.size(), CV_8UC3);// 图像RGB像素数据转换为样本数据 int index = 0;for (int row = 0; row < height; row++) {for (int col = 0; col < width; col++) {index = row*width + col;Vec3b rgb = src.at<Vec3b>(row, col);points.at<double>(index, 0) = static_cast<int>(rgb[0]);points.at<double>(index, 1) = static_cast<int>(rgb[1]);points.at<double>(index, 2) = static_cast<int>(rgb[2]);}}// EM Cluster TrainPtr<EM> em_model = EM::create();em_model->setClustersNumber(numCluster);em_model->setCovarianceMatrixType(EM::COV_MAT_SPHERICAL);//设置协方差矩阵//设置停止条件，训练100次结束em_model->setTermCriteria(TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 100, 0.1));em_model->trainEM(points, noArray(), labels, noArray());// 对每个像素标记颜色与显示Mat sample(dims, 1, CV_64FC1);double time = getTickCount();int r = 0, g = 0, b = 0;for (int row = 0; row < height; row++) {for (int col = 0; col < width; col++) {index = row*width + col;int label = labels.at<int>(index, 0);Scalar c = colors[label];result.at<Vec3b>(row, col)[0] = c[0];result.at<Vec3b>(row, col)[1] = c[1];result.at<Vec3b>(row, col)[2] = c[2];/*b = src.at<Vec3b>(row, col)[0];g = src.at<Vec3b>(row, col)[1];r = src.at<Vec3b>(row, col)[2];sample.at<double>(0) = b;sample.at<double>(1) = g;sample.at<double>(2) = r;int response = cvRound(em_model->predict2(sample, noArray())[1]);Scalar c = colors[response];result.at<Vec3b>(row, col)[0] = c[0];result.at<Vec3b>(row, col)[1] = c[1];result.at<Vec3b>(row, col)[2] = c[2];*/}}printf("execution time(ms) : %.2f\n", (getTickCount() - time)/getTickFrequency()*1000);imshow("EM-Segmentation", result);waitKey(0);return 0;
}

执行时间：

可见，GMM算法处理时间较长，并不适合工程实时图像处理。

分水岭分割方法概述

图像形态学操作：

 腐蚀与膨胀

 开闭操作

分水岭分割方法原理：

- 基于浸泡理论的分水岭分割方法
- 基于连通图的方法
- 基于距离变换的方法

分水岭算法的运用：

 分割粘连对象，实现形态学操作与对象计数
 图像分割

基于距离的分水岭分割流程：

API说明：

 OpenCV3.x中
 distanceTransform
 watershed

实例6：基于距离变换的分水岭粘连对象分离与计数

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace std;int main(int argc, char** argv) {Mat src = imread("pill_002.png");//pill_002.png  coins_001.jpgif (src.empty()) {printf("could not load image...\n");return -1;}namedWindow("input image", CV_WINDOW_AUTOSIZE);imshow("input image", src);Mat gray, binary, shifted;//边缘保留（空间、颜色差值<21、51) 减少差异化pyrMeanShiftFiltering(src, shifted, 21, 51);imshow("shifted", shifted);cvtColor(shifted, gray, COLOR_BGR2GRAY);//转换为灰度图像//灰度图像进行二值化threshold(gray, binary, 0, 255, THRESH_BINARY | THRESH_OTSU);imshow("binary", binary);// distance transform 距离变化Mat dist;distanceTransform(binary, dist, DistanceTypes::DIST_L2, 3, CV_32F);//使用3*3进行normalize(dist, dist, 0, 1, NORM_MINMAX);imshow("distance result", dist);// binarythreshold(dist, dist, 0.4, 1, THRESH_BINARY);imshow("distance binary", dist);// markers 找到山峰的旗子Mat dist_m;dist.convertTo(dist_m, CV_8U);vector<vector<Point>> contours;//寻找轮廓contoursfindContours(dist_m, contours, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE, Point(0, 0));// create markers 填充轮廓Mat markers = Mat::zeros(src.size(), CV_32SC1);for (size_t t = 0; t < contours.size(); t++) {drawContours(markers, contours, static_cast<int>(t), Scalar::all(static_cast<int>(t) + 1), -1);}//左上角显示一个圆（可有可无）circle(markers, Point(5, 5), 3, Scalar(255), -1);//markers放大10000倍进行显示imshow("markers", markers*10000);// 形态学操作 - 彩色图像也可以，目的是去掉干扰，让结果更好Mat k = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));morphologyEx(src, src, MORPH_ERODE, k);// 完成分水岭变换watershed(src, markers);Mat mark = Mat::zeros(markers.size(), CV_8UC1);markers.convertTo(mark, CV_8UC1);bitwise_not(mark, mark, Mat());//imshow("watershed result", mark);//中间是白色线进行分割// generate random color 生成随机颜色vector<Vec3b> colors;for (size_t i = 0; i < contours.size(); i++) {int r = theRNG().uniform(0, 255);int g = theRNG().uniform(0, 255);int b = theRNG().uniform(0, 255);colors.push_back(Vec3b((uchar)b, (uchar)g, (uchar)r));}// 颜色填充与最终显示Mat dst = Mat::zeros(markers.size(), CV_8UC3);int index = 0;for (int row = 0; row < markers.rows; row++) {for (int col = 0; col < markers.cols; col++) {index = markers.at<int>(row, col);if (index > 0 && index <= contours.size()) {dst.at<Vec3b>(row, col) = colors[index - 1];} else {dst.at<Vec3b>(row, col) = Vec3b(0, 0, 0);}}}imshow("Final Result", dst);printf("number of objects : %d\n", contours.size());waitKey(0);return 0;
}

1 输入图像： 2 进行边缘保留的shifted转换：

3 灰度和二值化： 4 距离变换：

5 距离变换后进行二值化： 6 寻找种子，生产Marker：

7 分水岭变换并填充： 8 计数结果：

实例7：基于分水岭图像分割

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace std;Mat watershedCluster(Mat &image, int &numSegments);
//参数分别为分割后图像，分割块数，输入原图
void createDisplaySegments(Mat &segments, int numSegments, Mat &image);
int main(int argc, char** argv) {Mat src = imread("cvtest.png");if (src.empty()) {printf("could not load image...\n");return -1;}namedWindow("input image", CV_WINDOW_AUTOSIZE);imshow("input image", src);int numSegments;Mat markers = watershedCluster(src, numSegments);createDisplaySegments(markers, numSegments, src);waitKey(0);return 0;
}Mat watershedCluster(Mat &image, int &numComp) {// 二值化Mat gray, binary;cvtColor(image, gray, COLOR_BGR2GRAY);threshold(gray, binary, 0, 255, THRESH_BINARY | THRESH_OTSU);// 形态学与距离变换Mat k = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));morphologyEx(binary, binary, MORPH_OPEN, k, Point(-1, -1));Mat dist;distanceTransform(binary, dist, DistanceTypes::DIST_L2, 3, CV_32F);normalize(dist, dist, 0.0, 1.0, NORM_MINMAX);// 开始生成标记threshold(dist, dist, 0.1, 1.0, THRESH_BINARY);normalize(dist, dist, 0, 255, NORM_MINMAX);dist.convertTo(dist, CV_8UC1);// 标记开始vector<vector<Point>> contours;vector<Vec4i> hireachy;findContours(dist, contours, hireachy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);if (contours.empty()) {return Mat();}Mat markers(dist.size(), CV_32S);markers = Scalar::all(0);for (int i = 0; i < contours.size(); i++) {drawContours(markers, contours, i, Scalar(i + 1), -1, 8, hireachy, INT_MAX);}circle(markers, Point(5, 5), 3, Scalar(255), -1);// 分水岭变换watershed(image, markers);numComp = contours.size();return markers;
}void createDisplaySegments(Mat &markers, int numSegments, Mat &image) {// generate random colorvector<Vec3b> colors;for (size_t i = 0; i < numSegments; i++) {int r = theRNG().uniform(0, 255);int g = theRNG().uniform(0, 255);int b = theRNG().uniform(0, 255);colors.push_back(Vec3b((uchar)b, (uchar)g, (uchar)r));}// 颜色填充与最终显示Mat dst = Mat::zeros(markers.size(), CV_8UC3);int index = 0;for (int row = 0; row < markers.rows; row++) {for (int col = 0; col < markers.cols; col++) {index = markers.at<int>(row, col);if (index > 0 && index <= numSegments) {dst.at<Vec3b>(row, col) = colors[index - 1];}else {dst.at<Vec3b>(row, col) = Vec3b(255, 255, 255);}}}imshow("分水岭图像分割-演示",dst);return;
}

Grabcut算法的基本流程

API介绍：

- grabCut
- setMouseCallback
- onMouse(int event, int x, int y, int flags, void* param)

 图像中对象抠图

实例8：Grabcut原理与演示应用

#include <opencv2/opencv.hpp>
#include <iostream>
#include <math.h>using namespace cv;
using namespace std;int numRun = 0;
Rect rect;
bool init = false;
Mat src, image;
Mat mask, bgModel, fgModel;//mask，背景，前景
const char* winTitle = "input image";void onMouse(int event, int x, int y, int flags, void* param);
void setROIMask();
void showImage();
void runGrabCut();
int main(int argc, char** argv) {src = imread("tx.png", 1);if (src.empty()) {printf("could not load image...\n");return -1;}mask.create(src.size(), CV_8UC1);mask.setTo(Scalar::all(GC_BGD));namedWindow(winTitle, CV_WINDOW_AUTOSIZE);//setMouseCallback(winTitle, onMouse, 0);//设置鼠标反馈事件imshow(winTitle, src);while (true) {char c = (char)waitKey(0);if (c == 'n') {runGrabCut();//运行GrabCut算法numRun++;showImage();printf("current iteative times : %d\n", numRun);//当前迭代次数}if ((int)c == 27) {break;}}waitKey(0);return 0;
}void showImage() {Mat result, binMask;binMask.create(mask.size(), CV_8UC1);binMask = mask & 1;if (init) {src.copyTo(result, binMask);} else {src.copyTo(result);//将src图像拷贝到result中}imwrite("tx2.png",result);rectangle(result, rect, Scalar(0, 0, 255), 2, 8);//在result上绘制红色矩形框rectimshow(winTitle, result);
}void setROIMask() {// GC_FGD = 1// GC_BGD =0;// GC_PR_FGD = 3// GC_PR_BGD = 2mask.setTo(GC_BGD);rect.x = max(0, rect.x);rect.y = max(0, rect.y);rect.width = min(rect.width, src.cols - rect.x);rect.height = min(rect.height, src.rows - rect.y);mask(rect).setTo(Scalar(GC_PR_FGD));
}//鼠标事件函数
void onMouse(int event, int x, int y, int flags, void* param) {switch (event){case EVENT_LBUTTONDOWN://鼠标左键按下rect.x = x;//矩形左上角x,y坐标rect.y = y;rect.width = 1;//矩形线条宽度、高度rect.height = 1;init = false;numRun = 0;break;case EVENT_MOUSEMOVE://鼠标移动if (flags & EVENT_FLAG_LBUTTON) {rect = Rect(Point(rect.x, rect.y), Point(x, y));showImage();//显示带矩形框的图像}break;case EVENT_LBUTTONUP://鼠标左键松开if (rect.width > 1 && rect.height > 1) {setROIMask();showImage();}break;default:break;}
}//运行GrabCut函数
void runGrabCut() {if (rect.width < 2 || rect.height < 2) {return;}if (init) {grabCut(src, mask, rect, bgModel, fgModel, 1);} {grabCut(src, mask, rect, bgModel, fgModel, 1, GC_INIT_WITH_RECT);init = true;}
}

鼠标选定方框后，按下键盘n键便可进行分割。

案例实战——证件照背景替换

关键知识点

 K-Means
 背景融合 – 高斯模糊
 遮罩层生成

算法设计步骤

实例9：K-Means-证件照背景替换

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace std;Mat mat_to_samples(Mat &image);
int main(int argc, char** argv) {Mat src = imread("tx.png");if (src.empty()) {printf("could not load image...\n");return -1;}namedWindow("输入图像", CV_WINDOW_AUTOSIZE);imshow("输入图像", src);// 组装数据Mat points = mat_to_samples(src);// 运行KMeansint numCluster = 4;Mat labels;Mat centers;TermCriteria criteria = TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1);kmeans(points, numCluster, labels, criteria, 3, KMEANS_PP_CENTERS, centers);// 去背景+遮罩生成Mat mask=Mat::zeros(src.size(), CV_8UC1);int index = src.rows*2 + 2;int cindex = labels.at<int>(index, 0);int height = src.rows;int width = src.cols;//Mat dst;//src.copyTo(dst);for (int row = 0; row < height; row++) {for (int col = 0; col < width; col++) {index = row*width + col;int label = labels.at<int>(index, 0);if (label == cindex) { // 背景//dst.at<Vec3b>(row, col)[0] = 0;//dst.at<Vec3b>(row, col)[1] = 0;//dst.at<Vec3b>(row, col)[2] = 0;mask.at<uchar>(row, col) = 0; } else {mask.at<uchar>(row, col) = 255;}}}imshow("mask-遮罩", mask);// 腐蚀 + 高斯模糊Mat k = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));//用3*3像素进行腐蚀（减少3*3）erode(mask, mask, k);imshow("腐蚀-mask", mask);GaussianBlur(mask, mask, Size(3, 3), 0, 0);//用3*3像素进行高斯模糊（增加3*3）  所以边界不变imshow("高斯模糊-mask", mask);// 通道混合RNG rng(12345);//随机数Vec3b color;color[0] = 217;//rng.uniform(0, 255);color[1] = 60;// rng.uniform(0, 255);color[2] = 160;// rng.uniform(0, 255);Mat result(src.size(), src.type());double w = 0.0;int b = 0, g = 0, r = 0;int b1 = 0, g1 = 0, r1 = 0;int b2 = 0, g2 = 0, r2 = 0;for (int row = 0; row < height; row++) {for (int col = 0; col < width; col++) {int m = mask.at<uchar>(row, col);if (m == 255) {result.at<Vec3b>(row, col) = src.at<Vec3b>(row, col); // 前景}else if (m == 0) {result.at<Vec3b>(row, col) = color; // 背景} else {w = m / 255.0;b1 = src.at<Vec3b>(row, col)[0];g1 = src.at<Vec3b>(row, col)[1];r1 = src.at<Vec3b>(row, col)[2];b2 = color[0];g2 = color[1];r2 = color[2];b = b1*w + b2*(1.0 - w);g = g1*w + g2*(1.0 - w);r = r1*w + r2*(1.0 - w);result.at<Vec3b>(row, col)[0] = b;result.at<Vec3b>(row, col)[1] = g;result.at<Vec3b>(row, col)[2] = r;}}}imshow("背景替换", result);waitKey(0);return 0;
}Mat mat_to_samples(Mat &image) {int w = image.cols;int h = image.rows;int samplecount = w*h;int dims = image.channels();Mat points(samplecount, dims, CV_32F, Scalar(10));int index = 0;for (int row = 0; row < h; row++) {for (int col = 0; col < w; col++) {index = row*w + col;Vec3b bgr = image.at<Vec3b>(row, col);points.at<float>(index, 0) = static_cast<int>(bgr[0]);points.at<float>(index, 1) = static_cast<int>(bgr[1]);points.at<float>(index, 2) = static_cast<int>(bgr[2]);}}return points;
}

案例实战——绿幕视频背景替换

关键知识点

 分割算法选择
 背景融合 – 高斯模糊
 遮罩层生成

算法选择

 GMM或者Kmeans - ?? Bad idea, very slow!!!
 基于色彩的处理方法
 RGB与HSV色彩空间

算法设计步骤

实例10：绿幕视频背景替换

如有资料等方面的问题，欢迎联系扣扣1837393417，共同探讨，共同进步！！！

#include <opencv2/opencv.hpp>
#include <iostream>using namespace cv;
using namespace std;Mat replace_and_blend(Mat &frame, Mat &mask);
Mat background_01;//背景1
Mat background_02;//背景2
int main(int argc, char** argv) {// start here...   background_01 = imread("bg_01.jpg");background_02 = imread("bg_02.jpg");VideoCapture capture;//视频抓取capture.open("01.mp4");if (!capture.isOpened()) {printf("could not find the video file...\n");return -1;}const char* title = "input video";const char* resultWin = "result video";namedWindow(title, CV_WINDOW_AUTOSIZE);namedWindow(resultWin, CV_WINDOW_AUTOSIZE);Mat frame, hsv, mask;int count = 0;//测试视频读取//while (capture.read(frame)) {//判断读取视频单帧是否成功，读取单帧图像复制给frame对象//  imshow(title, frame);// char c =waitKey(50);// if (c == 27) {//      break;//    }//}///mask测试//while (capture.read(frame)) {//  cvtColor(frame, hsv, COLOR_BGR2HSV);//转换为HSV//  //原背景选择HSV--绿色//    inRange(hsv, Scalar(35, 43, 46), Scalar(60, 255, 255), mask);//mask数据调整60// imshow("mask",mask);//显示mask//    count++;//    imshow(title, frame);//显示输入video//  char c = waitKey(1);// if (c == 27) {//      break;//    }//}/while (capture.read(frame)) {//判断读取视频单帧是否成功，读取单帧图像复制给frame对象cvtColor(frame, hsv, COLOR_BGR2HSV);//转换为HSVinRange(hsv, Scalar(35, 43, 46), Scalar(60, 255, 255), mask);// 形态学操作，3*3进行腐蚀，然后高斯进行3*3的模糊，边界不变Mat k = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));morphologyEx(mask, mask, MORPH_CLOSE, k);erode(mask, mask, k);GaussianBlur(mask, mask, Size(3, 3), 0, 0);//背景替换和混合Mat result = replace_and_blend(frame, mask);char c = waitKey(1);if (c == 27) {break;}imshow(resultWin, result);//显示处理结果videoimshow(title, frame);//显示输入video}waitKey(0);return 0;
}
//背景替换和混合
Mat replace_and_blend(Mat &frame, Mat &mask) {Mat result = Mat::zeros(frame.size(), frame.type());int h = frame.rows;int w = frame.cols;int dims = frame.channels();// replace and blendint m = 0;double wt = 0;int r = 0, g = 0, b = 0;int r1 = 0, g1 = 0, b1 = 0;int r2 = 0, g2 = 0, b2 = 0;for (int row = 0; row < h; row++) {uchar* current = frame.ptr<uchar>(row);//当前uchar* bgrow = background_01.ptr<uchar>(row);//背景2uchar* maskrow = mask.ptr<uchar>(row);//面罩 行uchar* targetrow = result.ptr<uchar>(row);//目标 行for (int col = 0; col < w; col++) {m = *maskrow++;if (m == 255) { // 赋值为背景*targetrow++ = *bgrow++;*targetrow++ = *bgrow++;*targetrow++ = *bgrow++;current += 3;} else if(m==0) {// 赋值为前景*targetrow++ = *current++;*targetrow++ = *current++;*targetrow++ = *current++;bgrow += 3;} else {b1 = *bgrow++;g1 = *bgrow++;r1 = *bgrow++;b2 = *current++;g2 = *current++;r2 = *current++;// 权重wt = m / 255.0;// 混合b = b1*wt + b2*(1.0 - wt);g = g1*wt + g2*(1.0 - wt);r = r1*wt + r2*(1.0 - wt);*targetrow++ = b;*targetrow++ = g;*targetrow++ = r;}}}return result;
}

视频读取测试视频播放

Mark测试

视频背景替换视频背景替换播放