/*
 * ORB特徵點檢測匹配
 * 其他方法還有SIFT
 * SURF
 */
#include <iostream>
#include <opencv2/core/core.hpp>
#include <opencv2/features2d/features2d.hpp>//二維特徵提取
#include <opencv2/highgui/highgui.hpp>

using namespace std;//標準庫　名稱空間
using namespace cv; //opencv庫名稱空間
// 呼叫./feature_extraction 1.png 2.png
int main ( int argc, char** argv )
{
    if ( argc != 3 )//命令列引數　 1.png 　2.png
    {
        cout<<"用法:  feature_extraction img1 img2"<<endl;
        return 1;
    }
    //-- 讀取影象
    Mat img_1 = imread ( argv[1], CV_LOAD_IMAGE_COLOR );//彩色圖模式
    Mat img_2 = imread ( argv[2], CV_LOAD_IMAGE_COLOR );

    //-- 初始化
    std::vector<KeyPoint> keypoints_1, keypoints_2;//關鍵點容器  二維點
    Mat descriptors_1, descriptors_2;			      //關鍵點對應的描述子
    Ptr<FeatureDetector> detector = ORB::create();  //cv3下　ORB特徵檢測    其他 BRISK   FREAK
    //  cv::Ptr<cv::FastFeatureDetector> detector = cv::FastFeatureDetector::create();
    Ptr<DescriptorExtractor> descriptor = ORB::create();//cv3下　ORB描述子
    // Ptr<FeatureDetector> detector = FeatureDetector::create(detector_name);
    // Ptr<DescriptorExtractor> descriptor = DescriptorExtractor::create(descriptor_name);
   // use this if you are in OpenCV2 
    // Ptr<FeatureDetector> detector = FeatureDetector::create ( "ORB" );
    // Ptr<DescriptorExtractor> descriptor = DescriptorExtractor::create ( "ORB" );
    Ptr<DescriptorMatcher> matcher  = DescriptorMatcher::create ( "BruteForce-Hamming" );
    //二進位制描述子漢明距離  匹配

    //-- 第一步:檢測 Oriented FAST 角點位置
    detector->detect ( img_1,keypoints_1 );
    detector->detect ( img_2,keypoints_2 );

    //-- 第二步:根據角點位置計算 BRIEF 描述子
    descriptor->compute ( img_1, keypoints_1, descriptors_1 );
    descriptor->compute ( img_2, keypoints_2, descriptors_2 );

    Mat outimg1;//在原影象畫出特徵點的影象
    drawKeypoints( img_1, keypoints_1, outimg1, Scalar::all(-1), DrawMatchesFlags::DEFAULT );
    imshow("ORB特徵點",outimg1);//顯示畫上特徵點的影象

    //-- 第三步:對兩幅影象中的BRIEF描述子進行匹配，使用 Hamming 距離 字串距離  刪除 插入 替換次數
    vector<DMatch> matches;//default預設漢明匹配  容器
    //BFMatcher matcher ( NORM_HAMMING );
    matcher->match ( descriptors_1, descriptors_2, matches );//對兩幅照片的特徵描述子進行匹配

    //-- 第四步:匹配點對篩選
    double min_dist=10000, max_dist=0;

    //找出所有匹配之間的最小距離和最大距離, 即是最相似的和最不相似的兩組點之間的距離
    for ( int i = 0; i < descriptors_1.rows; i++ )
    {
        double dist = matches[i].distance;
        if ( dist < min_dist ) min_dist = dist;  //最短距離  最相似
        if ( dist > max_dist ) max_dist = dist; //最長距離 最不相似
    }
    
    // 僅供娛樂的寫法
    min_dist = min_element( matches.begin(), matches.end(), [](const DMatch& m1, const DMatch& m2) {return m1.distance<m2.distance;} )->distance;
    max_dist = max_element( matches.begin(), matches.end(), [](const DMatch& m1, const DMatch& m2) {return m1.distance<m2.distance;} )->distance;

    printf ( "-- Max dist : %f \n", max_dist );
    printf ( "-- Min dist : %f \n", min_dist );

    //當描述子之間的距離大於兩倍的最小距離時,即認為匹配有誤.
    //但有時候最小距離會非常小,設定一個經驗值30作為下限.
    std::vector< DMatch > good_matches;//兩幅影象好的特徵匹配 點對
    for ( int i = 0; i < descriptors_1.rows; i++ )
    {
        if ( matches[i].distance <= max ( 2*min_dist, 30.0 ) )//最大距離
        {
            good_matches.push_back ( matches[i] );
        }
    }

    //-- 第五步:繪製匹配結果
    Mat img_match;         //全部的匹配點對 影象
    Mat img_goodmatch;//篩選之後的較好的匹配點對影象
    drawMatches ( img_1, keypoints_1, img_2, keypoints_2, matches, img_match );//得到全部的匹配點對 影象
    drawMatches ( img_1, keypoints_1, img_2, keypoints_2, good_matches, img_goodmatch );//得到篩選之後的較好的匹配點對影象
    imshow ( "所有匹配點對", img_match );             //顯示 全部的匹配點對 影象
    imshow ( "優化後匹配點對", img_goodmatch );//顯示篩選之後的較好的匹配點對影象
    waitKey(0);

    return 0;
}