图像特征点—SIFT特征点

清疚 2022-03-16 14:49 259阅读 0赞

# 图像特征点—SIFT特征点 #

关于SIFT特征点，以下三篇博客说的非常详细，再次不再赘述。  
[https://mp.weixin.qq.com/s/XVB88f119gRqpwTTRvTyrA][https_mp.weixin.qq.com_s_XVB88f119gRqpwTTRvTyrA]  
[https://mp.weixin.qq.com/s/Vx-8xsXd6aXoJupr0BEMow][https_mp.weixin.qq.com_s_Vx-8xsXd6aXoJupr0BEMow]  
[https://mp.weixin.qq.com/s/8WAgDmc1R\_9rGRjM9eanDg][https_mp.weixin.qq.com_s_8WAgDmc1R_9rGRjM9eanDg]

## OpenCV 代码测试 ##

#include <iostream>
    #include<opencv2/highgui/highgui.hpp>
    #include<opencv2/imgproc/imgproc.hpp>
    #include <opencv2/opencv.hpp> 
    #include<opencv2/xfeatures2d.hpp>
    #include<opencv2/core/core.hpp>
     
    using namespace cv;  
    using namespace std;
    using namespace cv::xfeatures2d;
    
    int main()
    {
           Mat image = imread("../pig.jpg");
    
           Ptr<Feature2D> sift = xfeatures2d::SIFT::create();
    
           vector<KeyPoint> kps;
           Mat         descriptor;
    
           sift->detect(image,kps);
           sift->compute(image,kps,descriptor);
    
           Mat outImage;
           drawKeypoints(image,kps,outImage,Scalar::all(-1),0);
           imshow("SIFT",outImage);
    
           cout<<"特征点的数量："<<kps.size()<<endl;
           cout<<"描述子的维度:"<<descriptor.size()<<endl;
    
    
           waitKey(0);
    
    }

测试效果  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3UwMTQ3MDk3NjA_size_16_color_FFFFFF_t_70_pic_center]  
![在这里插入图片描述][20190228085246108.png_pic_center]

## PS :Opencv中SIFT运行时直接报错问题 ##

在用SIFT函数时，opencv报出一下错误：

OpenCV(3.4.3) Error: The function/feature is not implemented (This algorithm is patented and is excluded in this configuration; Set OPENCV_ENABLE_NONFREE CMake option and rebuild the library) in cv::xfeatures2d::SIFT::create, file D:\library\opencv-3.4.3\opencv_contrib-3.4.3\modules\xfeatures2d\src\sift.cpp, line 1207

原因是在编译opencv时没有选择 **OPENCV\_ENABLE\_NONFREE**。按照网上的说法，只要cmake时勾选这部分，然后重新编译即可。但是本机在配置了其他环境之后Opencv编译过程总是出错。

无奈之下只能调用ROS中的Opencv，调用方式如下：

set(OpenCV_DIR /opt/ros/kinetic/share/OpenCV-3.3.1-dev)
    find_package(OpenCV REQUIRED)
    include_directories(${OPenCV_DIRS})

参考博客：  
[https://blog.csdn.net/fxmfxm9304/article/details/86093564][https_blog.csdn.net_fxmfxm9304_article_details_86093564]  
[https://blog.csdn.net/zhoukehu\_CSDN/article/details/83145026][https_blog.csdn.net_zhoukehu_CSDN_article_details_83145026]

[https_mp.weixin.qq.com_s_XVB88f119gRqpwTTRvTyrA]: https://mp.weixin.qq.com/s/XVB88f119gRqpwTTRvTyrA
[https_mp.weixin.qq.com_s_Vx-8xsXd6aXoJupr0BEMow]: https://mp.weixin.qq.com/s/Vx-8xsXd6aXoJupr0BEMow
[https_mp.weixin.qq.com_s_8WAgDmc1R_9rGRjM9eanDg]: https://mp.weixin.qq.com/s/8WAgDmc1R_9rGRjM9eanDg
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3UwMTQ3MDk3NjA_size_16_color_FFFFFF_t_70_pic_center]: /images/20220316/fca4f1562f2d4bd1a61c252940594e27.png
[20190228085246108.png_pic_center]: /images/20220316/2ce7a39dd0dd438b8904babdd322f092.png
[https_blog.csdn.net_fxmfxm9304_article_details_86093564]: https://blog.csdn.net/fxmfxm9304/article/details/86093564
[https_blog.csdn.net_zhoukehu_CSDN_article_details_83145026]: https://blog.csdn.net/zhoukehu_CSDN/article/details/83145026