本文中采用的SIFT提取视频中的和待检测图像特征点，并利用特征点之间的映射关系找到视频中待检测物体的位置，绘制出绿色的边界并显示出来。

检测视频
视频地址

图片：待检测的图片（仙剑奇侠传5的游戏盒子）

程序源代码

#include <iostream>
#include <opencv2\core\core.hpp>
#include <opencv2\imgproc\imgproc.hpp>
#include <opencv2\nonfree\features2d.hpp>
#include <opencv2\highgui\highgui.hpp>
#include <opencv2\calib3d\calib3d.hpp>using namespace cv;int _sift(Mat &img_object, Mat &img_scene);int main(int argc, char *argv[])
{//读取视频VideoCapture vc;vc.open("C:\\Users\\Arthur\\Desktop\\SRC\\video.mp4");double rate = vc.get(CV_CAP_PROP_FPS);//帧率int delay = 1000 / rate;Mat img = imread("C:\\Users\\Arthur\\Desktop\\SRC\\temp.jpg", CV_LOAD_IMAGE_COLOR);//模版图像VideoWriter vw;vw.open("C:\\Users\\Arthur\\Desktop\\SRC\\sift.avi",(int)vc.get(CV_CAP_PROP_FOURCC), // 也可设为CV_FOURCC_PROMPT，在运行时选取  (double)vc.get(CV_CAP_PROP_FPS), // 视频帧率  cv::Size((int)vc.get(CV_CAP_PROP_FRAME_WIDTH), (int)vc.get(CV_CAP_PROP_FRAME_HEIGHT)), // 视频大小  true); // 是否输出彩色视频  namedWindow("1");if (vc.isOpened()){while (1){Mat frame;//原始图像每5帧图像取1帧进行处理for (int i = 0; i < 5; i++){vc.read(frame);}if (frame.empty()){break;}_sift(img, frame);imshow("1", frame);vw << frame;waitKey(1);}}vc.release();return 0;
}int _sift(Mat &img_object, Mat &img_scene)
{//Mat img_object = imread("1.jpg", CV_LOAD_IMAGE_COLOR);//Mat img_scene = imread("2.jpg", CV_LOAD_IMAGE_COLOR);double t = (double)getTickCount();if (!img_object.data || !img_scene.data){std::cout << "Error reading images!" << std::endl;return -1;}//检测SIFT特征点int minHeassian = 400;SiftFeatureDetector detector(minHeassian);std::vector<KeyPoint> keypoints_object, keypoints_scene;detector.detect(img_object, keypoints_object);detector.detect(img_scene, keypoints_scene);//计算特征向量SiftDescriptorExtractor extractor;Mat descriptors_object, descriptors_scene;extractor.compute(img_object, keypoints_object, descriptors_object);extractor.compute(img_scene, keypoints_scene, descriptors_scene);//利用FLANN匹配算法匹配特征描述向量FlannBasedMatcher matcher;std::vector<DMatch> matches;matcher.match(descriptors_object, descriptors_scene, matches);double max_dist = 0; double min_dist = 100;//快速计算特征点之间的最大和最小距离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);//只画出好的匹配点(匹配特征点之间距离小于3*min_dist)std::vector<DMatch> good_matches;for (int i = 0; i < descriptors_object.rows; i++){if (matches[i].distance < 3 * min_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);//定位物体/std::vector<Point2f> obj;std::vector<Point2f> scene;for (int i = 0; i < good_matches.size(); i++){//从好的匹配中获取特征点obj.push_back(keypoints_object[good_matches[i].queryIdx].pt);scene.push_back(keypoints_scene[good_matches[i].trainIdx].pt);}//找出匹配特征点之间的变换Mat H = findHomography(obj, scene, CV_RANSAC);//得到image_1的角点(需要寻找的物体)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);//匹配四个角点perspectiveTransform(obj_corners, scene_corners, H);//画出匹配的物体两个匹配的图片//line(img_matches, scene_corners[0] + Point2f(img_object.cols, 0), scene_corners[1] + Point2f(img_object.cols, 0), Scalar(0,255,0), 4);//line(img_matches, scene_corners[1] + Point2f(img_object.cols, 0), scene_corners[2] + Point2f(img_object.cols, 0), Scalar(0,255,0), 4);//line(img_matches, scene_corners[2] + Point2f(img_object.cols, 0), scene_corners[3] + Point2f(img_object.cols, 0), Scalar(0,255,0), 4);//line(img_matches, scene_corners[3] + Point2f(img_object.cols, 0), scene_corners[0] + Point2f(img_object.cols, 0), Scalar(0,255,0), 4);//匹配之后画出匹配图形的轮廓line(img_scene, scene_corners[0], scene_corners[1], Scalar(0, 255, 0), 4);line(img_scene, scene_corners[1], scene_corners[2], Scalar(0, 255, 0), 4);line(img_scene, scene_corners[2], scene_corners[3], Scalar(0, 255, 0), 4);line(img_scene, scene_corners[3], scene_corners[0], Scalar(0, 255, 0), 4);//imshow("Good Matches & Object detection", img_matches);//imshow("识别图像", img_scene);t = 1000 * ((double)getTickCount() - t) / getTickFrequency();std::cout << "the time is :" << t << std::endl;//waitKey(0);
}

为了达到实时处理的效果，可以使用SURF替代SIFT，不过处理效果不如SIFT理想。
本文中的程序采用的是Opencv的2.4.8版本，在2.4.5版本以后可以结合VS2013和Image Watch插件，在调试的时候可以实时显示出图像，方便观测结果，再也不需要用各种imshow（）来显示结果。
图片：Image Watch直接显示内存中图片信息

SIFT原理解析可以查看SIFT算法详解 这篇博文