windows下利用vs2015+opencv3.1.0+contrib3.1.0进行SIFT特征点检测（x64）

最新推荐文章于 2023-01-11 21:49:42 发布

xlm_022

最新推荐文章于 2023-01-11 21:49:42 发布

阅读量244

点赞数

CC 4.0 BY-SA版权

分类专栏： cv-ml 文章标签：特征点检测 SIFT算法 opencv

本文链接：https://blog.youkuaiyun.com/weixin_41220184/article/details/96978470

cv-ml 专栏收录该内容

1 篇文章

订阅专栏

本文详细介绍了在Windows环境下，使用Visual Studio 2015和OpenCV 3.1.0（含contrib）库进行SIFT特征点检测的步骤。包括环境配置、库文件引用、代码实现及可能出现的问题解决方案。通过示例代码展示了如何检测和匹配图像的SIFT特征点。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

opencv3将opencv2单一的库分成了两个部分：成熟的Opencv库以及opencv-contrib库，这篇博客利用的是已经编译好的opencv文件，编译完成的库文件见已上传资源部分https://download.youkuaiyun.com/download/weixin_41220184/11419344。

（1）首先需要配置环境变量，新增一个系统变量，变量名字为OPENCV值为#opencv。

然后在用户变量path新增一个值#opencv/x64/vc14/bin。

（2）打开vs2015,新建一个工程并在属性管理器下面找到Debug|x64 cpp.x64.user鼠标右键--》属性--》vc++目录--》包含目录里面增加#opencv/include,#opencv/include/opencv,#opencv/include/opencv2三条记录

（3）在vc++目录--》库目录里面增加#opencv\x64\vc14\lib记录

（4)在连接器--》输入--》附加依赖项添加记录（#\opencv\x64\vc14\lib文件夹里面的lib文件），如下所示
opencv_aruco310d.lib
opencv_bgsegm310d.lib
opencv_bioinspired310d.lib
opencv_calib3d310d.lib
opencv_ccalib310d.lib
opencv_core310d.lib
opencv_datasets310d.lib
opencv_dnn310d.lib
opencv_dpm310d.lib
opencv_face310d.lib
opencv_features2d310d.lib
opencv_flann310d.lib
opencv_fuzzy310d.lib
opencv_highgui310d.lib
opencv_imgcodecs310d.lib
opencv_imgproc310d.lib
opencv_line_descriptor310d.lib
opencv_ml310d.lib
opencv_objdetect310d.lib
opencv_optflow310d.lib
opencv_photo310d.lib
opencv_plot310d.lib
opencv_reg310d.lib
opencv_rgbd310d.lib
opencv_saliency310d.lib
opencv_shape310d.lib
opencv_stereo310d.lib
opencv_stitching310d.lib
opencv_structured_light310d.lib
opencv_superres310d.lib
opencv_surface_matching310d.lib
opencv_text310d.lib
opencv_text310d.lib
opencv_text310d.lib
opencv_video310d.lib
opencv_videoio310d.lib
opencv_videostab310d.lib
opencv_xfeatures2d310d.lib
opencv_ximgproc310d.lib
opencv_xobjdetect310d.lib
opencv_xphoto310d.lib

最后进行特征点检测，代码如下：

#include <opencv\cv.hpp>
#include<opencv2\xfeatures2d.hpp>
#include <vector>
#include<iostream>
using namespace std;
using namespace cv;

void main()
{
   Mat srcImg1 = imread("C://Users//lenovo//Desktop//img1.jpg");
   Mat srcImg2 = imread("C://Users//lenovo//Desktop//img2.jpg");
   vector<KeyPoint> keypoints_1, keypoints_2;
   Ptr<cv::Feature2D> f2d = xfeatures2d::SIFT::create();
   //detect Keypoints
   f2d->detect(srcImg1, keypoints_1);
   f2d->detect(srcImg2, keypoints_2);
   // caculate descriptors
   Mat descriptors1, descriptors2;
   f2d->compute(srcImg1, keypoints_1, descriptors1);
   f2d->compute(srcImg2, keypoints_2, descriptors2);
   //Matching descriptors
   BFMatcher matcher;
   vector<DMatch> matches;
   matcher.match(descriptors1, descriptors2, matches);
   //绘制图
   Mat img_matches;
   drawMatches(srcImg1, keypoints_1, srcImg2, keypoints_2, matches, img_matches);
   imshow("【特征点匹配图", img_matches);
   imwrite("C://Users//lenovo//Desktop//img3.jpg", img_matches);
   waitKey(0);
}