OpenCV中ORB特征点检测和匹配简单用法

最新推荐文章于 2025-07-11 16:06:37 发布

robinhjwy

最新推荐文章于 2025-07-11 16:06:37 发布

阅读量2.3w

点赞数 19

CC 4.0 BY-SA版权

分类专栏： OpenCV库使用文章标签： opencv

本文链接：https://blog.csdn.net/robinhjwy/article/details/77620924

本文介绍了在OpenCV中如何使用ORB（Oriented FAST and Rotated BRIEF）算法检测特征点并进行匹配。通过CMakeLists构建程序，包括检测关键点、计算描述符、绘制特征点图、进行匹配以及筛选和绘制匹配结果。重点指出匹配过程主要依赖于描述符。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

cmakelists:

cmake_minimum_required(VERSION 3.7)
project(feature_extraction_robin)

set(CMAKE_CXX_STANDARD 11)

find_package(OpenCV REQUIRED)
include_directories(${OPenCV_DIRS})


set(SOURCE_FILES main.cpp)
add_executable(feature_extraction_robin ${SOURCE_FILES})
target_link_libraries(feature_extraction_robin ${OpenCV_LIBS})

程序：

#include <iostream>
#include <opencv2/core/core.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <opencv2/highgui/highgui.hpp>

using namespace std;
using namespace cv;

int main(int argc, char** argv)
{

    if(argc!=3)//判断命令行输入对错
    {
        cout<<"usage: feature_extraction img1 img2"<<endl;
        return 1;
    }

    //读取要匹配的两张图像
    Mat img_1 = imread(argv[1], CV_LOAD_IMAGE_COLOR);
    Mat img_2 = imread(argv[2], CV_LOAD_IMA