【opencv学习之九】opencv3.2配置opencv_contrib方法

最新推荐文章于 2025-06-16 13:30:36 发布

abcvincent

最新推荐文章于 2025-06-16 13:30:36 发布

阅读量3.5k

点赞数

CC 4.0 BY-SA版权

分类专栏： opencv 文章标签： opencv cmake sift

本文链接：https://blog.youkuaiyun.com/abcvincent/article/details/77898661

opencv 专栏收录该内容

47 篇文章

订阅专栏

本文详细介绍如何在OpenCV 3.2中配置并使用SIFT算法，包括所需软件的下载与安装步骤、CMake配置过程及Qt编译示例。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

opencv在3.0版本后sift等一些非免费开源的方法和函数被放到到了opencv_contrib库里，所以直接用opencv调用sift相关函数是无法加载的，需要自己Cmake源代码生成包含opencv_contrib的库；

首先准备如下：

1、下载vs2015，链接：https://pan.baidu.com/s/1c28f8ze，提取码：52dj；秘钥在网上找，然后安装；

2、下载qt5.8；官网需要注册，网盘链接：链接: https://pan.baidu.com/s/1jICDilg 密码: x9fm；安装；

3、下载qt-vs工具；网盘链接：链接: https://pan.baidu.com/s/1c2piQfI 密码: t64d；安装后，在vs里设置qt路径，如何安装查看前面博客；

4、下载opencv3.2，可以在github上下载，这里网盘链接：链接: https://pan.baidu.com/s/1skVLwKl 密码: 3r8q；安装；

5、下载opencv_contrib，也可以在GitHub上下载，另网盘：链接: https://pan.baidu.com/s/1gftgyjx 密码: rdem；解压放到opencv文件夹里；

6、下载Cmake，这个也可以在官网下载，另网盘链接：链接: https://pan.baidu.com/s/1nvJY7X3 密码: 3uv3；安装；

然后cmake opencv的源代码：

1、打开Cmake，选择opencv安装文件里的sources文件夹；

2、选择要build的文件夹；如下图：

3、点击Generate，后如下图，finish后等待Cmake；

4、完了后，找到“OPENCV_EXTRA_MODUALS_PATH”，设置其参数值为opencv_contrib源码包中的modules目录；如下：

5、点击configure.成功后显示configuring done，然后点击Generate；

6、都configure后，在你build的文件里会生成相应的文件，找到OpenCV.sln文件双击，用vs2015进行编译或者直接点击Cmake的open project按钮；

7、vs2015编译参考博客：http://blog.youkuaiyun.com/cosmispower/article/details/60601151；

最后编译好了，的lib在目标文件夹里的install文件里；qt5.8编译时候.pro文件添加如下，目录和include根据自己目录添加路径：

INCLUDEPATH+=D:/opencv320/install/include
INCLUDEPATH+=D:/opencv320/install/include/opencv
INCLUDEPATH+=D:/opencv320/install/include/opencv2

unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_aruco320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_bgsegm320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_bioinspired320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_calib3d320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_ccalib320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_core320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_datasets320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_dnn320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_dpm320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_face320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_features2d320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_flann320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_fuzzy320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_highgui320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_imgcodecs320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_imgproc320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_line_descriptor320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_ml320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_objdetect320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_optflow320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_phase_unwrapping320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_photo320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_plot320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_reg320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_rgbd320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_saliency320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_shape320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_stereo320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_stitching320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_structured_light320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_superres320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_surface_matching320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_text320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_tracking320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_video320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_videoio320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_videostab320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_xfeatures2d320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_ximgproc320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_xobjdetect320d
unix|win32: LIBS += -L$$PWD/../../opencv320/install/x64/vc14/lib/ -lopencv_xphoto320d

INCLUDEPATH += $$PWD/../../opencv320/install/x64/vc14
DEPENDPATH += $$PWD/../../opencv320/install/x64/vc14

qt编译的时候会异常跳出，vs2015编译的时候会报错缺少***dll；这时候把build对应编译的目录bin文件下的dll全部复制到c盘系统文件C:\Windows\System32，和C:\Windows\SysWOW64里面；再次编译程序就ok了；附sift测试代码qt mainwindow.cpp代码：

#include "mainwindow.h"
#include "ui_mainwindow.h"

#include <opencv\cv.h>
#include<opencv/highgui.h>

#include <opencv2/opencv.hpp>  //头文件
#include <opencv2/xfeatures2d.hpp>
using namespace cv;  //包含cv命名空间
using namespace std;

MainWindow::MainWindow(QWidget *parent) :
    QMainWindow(parent),
    ui(new Ui::MainWindow)
{
    ui->setupUi(this);

//           //声明IplImage指针
//           IplImage *pImg;
//           //载入图片
//           pImg = cvLoadImage("D:/1.jpg");
//           //创建窗口
//           cvNamedWindow("Image",1);
//           //显示图像
//           cvShowImage("Image",pImg);
//           //等待按键
//           cvWaitKey(-1);
//           //销毁窗口
//           cvDestroyWindow("Image");
//           //释放图像
//           cvReleaseImage(&pImg);

    //Create SIFT class pointer
    Ptr<Feature2D> f2d = xfeatures2d::SIFT::create();
    //读入图片
    Mat img_1 = imread("D:/source.png");
    Mat img_2 = imread("D:/mubiao.jpg");
    //Detect the keypoints
    vector<KeyPoint> keypoints_1, keypoints_2;
    f2d->detect(img_1, keypoints_1);
    f2d->detect(img_2, keypoints_2);
    //Calculate descriptors (feature vectors)
    Mat descriptors_1, descriptors_2;
    f2d->compute(img_1, keypoints_1, descriptors_1);
    f2d->compute(img_2, keypoints_2, descriptors_2);
    //Matching descriptor vector using BFMatcher
    BFMatcher matcher;
    vector<DMatch> matches;
    matcher.match(descriptors_1, descriptors_2, matches);
    //绘制匹配出的关键点
    Mat img_matches;
    drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, img_matches);
//    imshow("match图", img_matches);
//    //等待任意按键按下
//    waitKey(0);
    imshow("match",img_matches);
    waitKey(0);

}

MainWindow::~MainWindow()
{
    delete ui;
}

效果如下：