OpenCV 图像拼接-Stitcher类-Stitching detailed使用与参数介绍

关于OpenCV图像拼接的方法，如果不熟悉的话，可以先看看我整理的如下四篇博客：

• OpenCV常用图像拼接方法(一)：直接拼接(硬拼)

• OpenCV常用图像拼接方法(二)：基于模板匹配拼接

• OpenCV常用图像拼接方法(三)：基于特征匹配拼接

• OpenCV常用图像拼接方法(四)：基于Stitcher类拼接

本篇博客是Stitcher类的扩展介绍，通过例程stitching_detailed.cpp的使用和参数介绍，帮助大家了解Stitcher类拼接的具体步骤和方法，先看看其内部的流程结构图(如下)：

stitching_detailed.cpp目录如下，可以在自己安装的OpenCV目录下找到，笔者这里使用的OpenCV4.4版本 

stitching_detailed.cpp具体源码如下： 

// 05_Image_Stitch_Stitching_Detailed.cpp : 此文件包含 "main" 函数。程序执行将在此处开始并结束。
//
#include "pch.h"
#include <iostream>
#include <fstream>
#include <string>
#include "opencv2/opencv_modules.hpp"
#include <opencv2/core/utility.hpp>
#include "opencv2/imgcodecs.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/stitching/detail/autocalib.hpp"
#include "opencv2/stitching/detail/blenders.hpp"
#include "opencv2/stitching/detail/timelapsers.hpp"
#include "opencv2/stitching/detail/camera.hpp"
#include "opencv2/stitching/detail/exposure_compensate.hpp"
#include "opencv2/stitching/detail/matchers.hpp"
#include "opencv2/stitching/detail/motion_estimators.hpp"
#include "opencv2/stitching/detail/seam_finders.hpp"
#include "opencv2/stitching/detail/warpers.hpp"
#include "opencv2/stitching/warpers.hpp"
 
#ifdef HAVE_OPENCV_XFEATURES2D
#include "opencv2/xfeatures2d.hpp"
#include "opencv2/xfeatures2d/nonfree.hpp"
#endif
 
#define ENABLE_LOG 1
#define LOG(msg) std::cout << msg
#define LOGLN(msg) std::cout << msg << std::endl
 
using namespace std;
using namespace cv;
using namespace cv::detail;
 
static void printUsage(char** argv)
{
    cout <<
        "Rotation model images stitcher.

"
        << argv[0] << " img1 img2 [...imgN] [flags]

"
        "Flags:
"
        "  --preview
"
        "      Run stitching in the preview mode. Works faster than usual mode,
"
        "      but output image will have lower resolution.
"
        "  --try_cuda (yes|no)
"
        "      Try to use CUDA. The default value is 'no'. All default values
"
        "      are for CPU mode.
"
        "
Motion Estimation Flags:
"
        "  --work_megapix <float>
"
        "      Resolution for image registration step. The default is 0.6 Mpx.
"
        "  --features (surf|orb|sift|akaze)
"
        "      Type of features used for images matching.
"
        "      The default is surf if available, orb otherwise.
"
        "  --matcher (homography|affine)
"
        "      Matcher used for pairwise image matching.
"
        "  --estimator (homography|affine)
"
        "      Type of estimator used for transformation estimation.
"
        "  --match_conf <float>
"
        "      Confidence for feature matching step. The default is 0.65 for surf and 0.3 for orb.
"
        "  --conf_thresh <float>
"
        "      Threshold for two images are from the same panorama confidence.
"
        "      The default is 1.0.
"
        "  --ba (no|reproj|ray|affine)
"
        "      Bundle adjustment cost function. The default is ray.
"
        "  --ba_refine_mask (mask)
"
        "      Set refinement mask for bundle adjustment. It looks like 'x_xxx',
"
        "      where 'x' means refine respective parameter and '_' means don't
"
        "      refine one, and has the following format:
"
        "      <fx><skew><ppx><aspect><ppy>. The default mask is 'xxxxx'. If bundle
"
        "      adjustment doesn't support estimation of selected parameter then
"
        "      the respective flag is ignored.
"
        "  --wave_correct (no|horiz|vert)
"
        "      Perform wave effect correction. The default is 'horiz'.
"
        "  --save_graph <file_name>
"
        "      Save matches graph represented in DOT language to <file_name> file.
"
        "      Labels description: Nm is number of matches, Ni is number of inliers,
"
        "      C is confidence.
"
        "
Compositing Flags:
"
        "  --warp (affine|plane|cylindrical|spherical|fisheye|stereographic|compressedPlaneA2B1|compressedPlaneA1.5B1|compressedPlanePortraitA2B1|compressedPlanePortraitA1.5B1|paniniA2B1|paniniA1.5B1|paniniPortraitA2B1|paniniPortraitA1.5B1|mercator|transverseMercator)
"
        "      Warp surface type. The default is 'spherical'.
"
        "  --seam_megapix <float>
"
        "      Resolution for seam estimation step. The default is 0.1 Mpx.
"
        "  --seam (no|voronoi|gc_color|gc_colorgrad)
"
        "      Seam estimation method. The default is 'gc_color'.
"
        "  --compose_megapix <float>
"
        "      Resolution for compositing step. Use -1 for original resolution.
"
        "      The default is -1.
"
        "  --expos_comp (no|gain|gain_blocks|channels|channels_blocks)
"
        "      Exposure compensation method. The default is 'gain_blocks'.
"
        "  --expos_comp_nr_feeds <int>
"
        "      Number of exposure compensation feed. The default is 1.
"
        "  --expos_comp_nr_filtering <int>
"
        "      Number of filtering iterations of the exposure compensation gains.
"
        "      Only used when using a block exposure compensation method.
"
        "      The default is 2.
"
        "  --expos_comp_block_size <int>
"
        "      BLock size in pixels used by the exposure compensator.
"
        "      Only used when using a block exposure compensation method.
"
        "      The default is 32.
"
        "  --blend (no|feather|multiband)
"
        "      Blending method. The default is 'multiband'.
"
        "  --blend_strength <float>
"
        "      Blending strength from [0,100] range. The default is 5.
"
        "  --output <result_img>
"
        "      The default is 'result.jpg'.
"
        "  --timelapse (as_is|crop) 
"
        "      Output warped images separately as frames of a time lapse movie, with 'fixed_' prepended to input file names.
"
        "  --rangewidth <int>
"
        "      uses range_width to limit number of images to match with.
";
}
 
 
// Default command line args
vector<String> img_names;
bool preview = false;
bool try_cuda = false;
double work_megapix = 0.6;
double seam_megapix = 0.1;
double compose_megapix = -1;
float conf_thresh = 1.f;
#ifdef HAVE_OPENCV_XFEATURES2D
string features_type = "surf";
float match_conf = 0.65f;
#else
string features_type = "orb";
float match_conf = 0.3f;
#endif
string matcher_type = "homography";
string estimator_type = "homography";
string ba_cost_func = "ray";
string ba_refine_mask = "xxxxx";
bool do_wave_correct = true;
WaveCorrectKind wave_correct = detail::WAVE_CORRECT_HORIZ;
bool save_graph = false;
std::string save_graph_to;
string warp_type = "spherical";
int expos_comp_type = ExposureCompensator::GAIN_BLOCKS;
int expos_comp_nr_feeds = 1;
int expos_comp_nr_filtering = 2;
int expos_comp_block_size = 32;
string seam_find_type = "gc_color";
int blend_type = Blender::MULTI_BAND;
int timelapse_type = Timelapser::AS_IS;
float blend_strength = 5;
string result_name = "result.jpg";
bool timelapse = false;
int range_width = -1;
 
 
static int parseCmdArgs(int argc, char** argv)
{
    if (argc == 1)
    {
        printUsage(argv);
        return -1;
    }
    for (int i = 1; i < argc; ++i)
    {
        if (string(argv[i]) == "--help" || string(argv[i]) == "/?")
        {
            printUsage(argv);
            return -1;
        }
        else if (string(argv[i]) == "--preview")
        {
            preview = true;
        }
        else if (string(argv[i]) == "--try_cuda")
        {
            if (string(argv[i + 1]) == "no")
                try_cuda = false;
            else if (string(argv[i + 1]) == "yes")
                try_cuda = true;
            else
            {
                cout << "Bad --try_cuda flag value
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--work_megapix")
        {
            work_megapix = atof(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--seam_megapix")
        {
            seam_megapix = atof(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--compose_megapix")
        {
            compose_megapix = atof(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--result")
        {
            result_name = argv[i + 1];
            i++;
        }
        else if (string(argv[i]) == "--features")
        {
            features_type = argv[i + 1];
            if (string(features_type) == "orb")
                match_conf = 0.3f;
            i++;
        }
        else if (string(argv[i]) == "--matcher")
        {
            if (string(argv[i + 1]) == "homography" || string(argv[i + 1]) == "affine")
                matcher_type = argv[i + 1];
            else
            {
                cout << "Bad --matcher flag value
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--estimator")
        {
            if (string(argv[i + 1]) == "homography" || string(argv[i + 1]) == "affine")
                estimator_type = argv[i + 1];
            else
            {
                cout << "Bad --estimator flag value
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--match_conf")
        {
            match_conf = static_cast<float>(atof(argv[i + 1]));
            i++;
        }
        else if (string(argv[i]) == "--conf_thresh")
        {
            conf_thresh = static_cast<float>(atof(argv[i + 1]));
            i++;
        }
        else if (string(argv[i]) == "--ba")
        {
            ba_cost_func = argv[i + 1];
            i++;
        }
        else if (string(argv[i]) == "--ba_refine_mask")
        {
            ba_refine_mask = argv[i + 1];
            if (ba_refine_mask.size() != 5)
            {
                cout << "Incorrect refinement mask length.
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--wave_correct")
        {
            if (string(argv[i + 1]) == "no")
                do_wave_correct = false;
            else if (string(argv[i + 1]) == "horiz")
            {
                do_wave_correct = true;
                wave_correct = detail::WAVE_CORRECT_HORIZ;
            }
            else if (string(argv[i + 1]) == "vert")
            {
                do_wave_correct = true;
                wave_correct = detail::WAVE_CORRECT_VERT;
            }
            else
            {
                cout << "Bad --wave_correct flag value
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--save_graph")
        {
            save_graph = true;
            save_graph_to = argv[i + 1];
            i++;
        }
        else if (string(argv[i]) == "--warp")
        {
            warp_type = string(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--expos_comp")
        {
            if (string(argv[i + 1]) == "no")
                expos_comp_type = ExposureCompensator::NO;
            else if (string(argv[i + 1]) == "gain")
                expos_comp_type = ExposureCompensator::GAIN;
            else if (string(argv[i + 1]) == "gain_blocks")
                expos_comp_type = ExposureCompensator::GAIN_BLOCKS;
            else if (string(argv[i + 1]) == "channels")
                expos_comp_type = ExposureCompensator::CHANNELS;
            else if (string(argv[i + 1]) == "channels_blocks")
                expos_comp_type = ExposureCompensator::CHANNELS_BLOCKS;
            else
            {
                cout << "Bad exposure compensation method
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--expos_comp_nr_feeds")
        {
            expos_comp_nr_feeds = atoi(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--expos_comp_nr_filtering")
        {
            expos_comp_nr_filtering = atoi(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--expos_comp_block_size")
        {
            expos_comp_block_size = atoi(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--seam")
        {
            if (string(argv[i + 1]) == "no" ||
                string(argv[i + 1]) == "voronoi" ||
                string(argv[i + 1]) == "gc_color" ||
                string(argv[i + 1]) == "gc_colorgrad" ||
                string(argv[i + 1]) == "dp_color" ||
                string(argv[i + 1]) == "dp_colorgrad")
                seam_find_type = argv[i + 1];
            else
            {
                cout << "Bad seam finding method
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--blend")
        {
            if (string(argv[i + 1]) == "no")
                blend_type = Blender::NO;
            else if (string(argv[i + 1]) == "feather")
                blend_type = Blender::FEATHER;
            else if (string(argv[i + 1]) == "multiband")
                blend_type = Blender::MULTI_BAND;
            else
            {
                cout << "Bad blending method
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--timelapse")
        {
            timelapse = true;
 
            if (string(argv[i + 1]) == "as_is")
                timelapse_type = Timelapser::AS_IS;
            else if (string(argv[i + 1]) == "crop")
                timelapse_type = Timelapser::CROP;
            else
            {
                cout << "Bad timelapse method
";
                return -1;
            }
            i++;
        }
        else if (string(argv[i]) == "--rangewidth")
        {
            range_width = atoi(argv[i + 1]);
            i++;
        }
        else if (string(argv[i]) == "--blend_strength")
        {
            blend_strength = static_cast<float>(atof(argv[i + 1]));
            i++;
        }
        else if (string(argv[i]) == "--output")
        {
            result_name = argv[i + 1];
            i++;
        }
        else
            img_names.push_back(argv[i]);
    }
    if (preview)
    {
        compose_megapix = 0.6;
    }
    return 0;
}
 
 
int main(int argc, char* argv[])
{
#if ENABLE_LOG
    int64 app_start_time = getTickCount();
#endif
 
#if 0
    cv::setBreakOnError(true);
#endif
 
    int retval = parseCmdArgs(argc, argv);
    if (retval)
        return retval;
 
    // Check if have enough images
    int num_images = static_cast<int>(img_names.size());
    if (num_images < 2)
    {
        LOGLN("Need more images");
        return -1;
    }
 
    double work_scale = 1, seam_scale = 1, compose_scale = 1;
    bool is_work_scale_set = false, is_seam_scale_set = false, is_compose_scale_set = false;
 
    LOGLN("Finding features...");
#if ENABLE_LOG
    int64 t = getTickCount();
#endif
 
    Ptr<Feature2D> finder;
    if (features_type == "orb")
    {
        finder = ORB::create();
    }
    else if (features_type == "akaze")
    {
        finder = AKAZE::create();
    }
#ifdef HAVE_OPENCV_XFEATURES2D
    else if (features_type == "surf")
    {
        finder = xfeatures2d::SURF::create();
    }
#endif
    else if (features_type == "sift")
    {
        finder = SIFT::create();
    }
    else
    {
        cout << "Unknown 2D features type: '" << features_type << "'.
";
        return -1;
    }
 
    Mat full_img, img;
    vector<ImageFeatures> features(num_images);
    vector<Mat> images(num_images);
    vector<Size> full_img_sizes(num_images);
    double seam_work_aspect = 1;
 
    for (int i = 0; i < num_images; ++i)
    {
        full_img = imread(samples::findFile(img_names[i]));
        full_img_sizes[i] = full_img.size();
 
        if (full_img.empty())
        {
            LOGLN("Can't open image " << img_names[i]);
            return -1;
        }
        if (work_megapix < 0)
        {
            img = full_img;
            work_scale = 1;
            is_work_scale_set = true;
        }
        else
        {
            if (!is_work_scale_set)
            {
                work_scale = min(1.0, sqrt(work_megapix * 1e6 / full_img.size().area()));
                is_work_scale_set = true;
            }
            resize(full_img, img, Size(), work_scale, work_scale, INTER_LINEAR_EXACT);
        }
        if (!is_seam_scale_set)
        {
            seam_scale = min(1.0, sqrt(seam_megapix * 1e6 / full_img.size().area()));
            seam_work_aspect = seam_scale / work_scale;
            is_seam_scale_set = true;
        }
 
        computeImageFeatures(finder, img, features[i]);
        features[i].img_idx = i;
        LOGLN("Features in image #" << i + 1 << ": " << features[i].keypoints.size());
 
        resize(full_img, img, Size(), seam_scale, seam_scale, INTER_LINEAR_EXACT);
        images[i] = img.clone();
    }
 
    full_img.release();
    img.release();
 
    LOGLN("Finding features, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");
 
    LOG("Pairwise matching");
#if ENABLE_LOG
    t = getTickCount();
#endif
    vector<MatchesInfo> pairwise_matches;
    Ptr<FeaturesMatcher> matcher;
    if (matcher_type == "affine")
        matcher = makePtr<AffineBestOf2NearestMatcher>(false, try_cuda, match_conf);
    else if (range_width == -1)
        matcher = makePtr<BestOf2NearestMatcher>(try_cuda, match_conf);
    else
        matcher = makePtr<BestOf2NearestRangeMatcher>(range_width, try_cuda, match_conf);
 
    (*matcher)(features, pairwise_matches);
    matcher->collectGarbage();
 
    LOGLN("Pairwise matching, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");
 
    // Check if we should save matches graph
    if (save_graph)
    {
        LOGLN("Saving matches graph...");
        ofstream f(save_graph_to.c_str());
        f << matchesGraphAsString(img_names, pairwise_matches, conf_thresh);
    }
 
    // Leave only images we are sure are from the same panorama
    vector<int> indices = leaveBiggestComponent(features, pairwise_matches, conf_thresh);
    vector<Mat> img_subset;
    vector<String> img_names_subset;
    vector<Size> full_img_sizes_subset;
    for (size_t i = 0; i < indices.size(); ++i)
    {
        img_names_subset.push_back(img_names[indices[i]]);
        img_subset.push_back(images[indices[i]]);
        full_img_sizes_subset.push_back(full_img_sizes[indices[i]]);
    }
 
    images = img_subset;
    img_names = img_names_subset;
    full_img_sizes = full_img_sizes_subset;
 
    // Check if we still have enough images
    num_images = static_cast<int>(img_names.size());
    if (num_images < 2)
    {
        LOGLN("Need more images");
        return -1;
    }
 
    Ptr<Estimator> estimator;
    if (estimator_type == "affine")
        estimator = makePtr<AffineBasedEstimator>();
    else
        estimator = makePtr<HomographyBasedEstimator>();
 
    vector<CameraParams> cameras;
    if (!(*estimator)(features, pairwise_matches, cameras))
    {
        cout << "Homography estimation failed.
";
        return -1;
    }
 
    for (size_t i = 0; i < cameras.size(); ++i)
    {
        Mat R;
        cameras[i].R.convertTo(R, CV_32F);
        cameras[i].R = R;
        LOGLN("Initial camera intrinsics #" << indices[i] + 1 << ":
K:
" << cameras[i].K() << "
R:
" << cameras[i].R);
    }
 
    Ptr<detail::BundleAdjusterBase> adjuster;
    if (ba_cost_func == "reproj") adjuster = makePtr<detail::BundleAdjusterReproj>();
    else if (ba_cost_func == "ray") adjuster = makePtr<detail::BundleAdjusterRay>();
    else if (ba_cost_func == "affine") adjuster = makePtr<detail::BundleAdjusterAffinePartial>();
    else if (ba_cost_func == "no") adjuster = makePtr<NoBundleAdjuster>();
    else
    {
        cout << "Unknown bundle adjustment cost function: '" << ba_cost_func << "'.
";
        return -1;
    }
    adjuster->setConfThresh(conf_thresh);
    Mat_<uchar> refine_mask = Mat::zeros(3, 3, CV_8U);
    if (ba_refine_mask[0] == 'x') refine_mask(0, 0) = 1;
    if (ba_refine_mask[1] == 'x') refine_mask(0, 1) = 1;
    if (ba_refine_mask[2] == 'x') refine_mask(0, 2) = 1;
    if (ba_refine_mask[3] == 'x') refine_mask(1, 1) = 1;
    if (ba_refine_mask[4] == 'x') refine_mask(1, 2) = 1;
    adjuster->setRefinementMask(refine_mask);
    if (!(*adjuster)(features, pairwise_matches, cameras))
    {
        cout << "Camera parameters adjusting failed.
";
        return -1;
    }
 
    // Find median focal length
 
    vector<double> focals;
    for (size_t i = 0; i < cameras.size(); ++i)
    {
        LOGLN("Camera #" << indices[i] + 1 << ":
K:
" << cameras[i].K() << "
R:
" << cameras[i].R);
        focals.push_back(cameras[i].focal);
    }
 
    sort(focals.begin(), focals.end());
    float warped_image_scale;
    if (focals.size() % 2 == 1)
        warped_image_scale = static_cast<float>(focals[focals.size() / 2]);
    else
        warped_image_scale = static_cast<float>(focals[focals.size() / 2 - 1] + focals[focals.size() / 2]) * 0.5f;
 
    if (do_wave_correct)
    {
        vector<Mat> rmats;
        for (size_t i = 0; i < cameras.size(); ++i)
            rmats.push_back(cameras[i].R.clone());
        waveCorrect(rmats, wave_correct);
        for (size_t i = 0; i < cameras.size(); ++i)
            cameras[i].R = rmats[i];
    }
 
    LOGLN("Warping images (auxiliary)... ");
#if ENABLE_LOG
    t = getTickCount();
#endif
 
    vector<Point> corners(num_images);
    vector<UMat> masks_warped(num_images);
    vector<UMat> images_warped(num_images);
    vector<Size> sizes(num_images);
    vector<UMat> masks(num_images);
 
    // Prepare images masks
    for (int i = 0; i < num_images; ++i)
    {
        masks[i].create(images[i].size(), CV_8U);
        masks[i].setTo(Scalar::all(255));
    }
 
    // Warp images and their masks
 
    Ptr<WarperCreator> warper_creator;
#ifdef HAVE_OPENCV_CUDAWARPING
    if (try_cuda && cuda::getCudaEnabledDeviceCount() > 0)
    {
        if (warp_type == "plane")
            warper_creator = makePtr<cv::PlaneWarperGpu>();
        else if (warp_type == "cylindrical")
            warper_creator = makePtr<cv::CylindricalWarperGpu>();
        else if (warp_type == "spherical")
            warper_creator = makePtr<cv::SphericalWarperGpu>();
    }
    else
#endif
    {
        if (warp_type == "plane")
            warper_creator = makePtr<cv::PlaneWarper>();
        else if (warp_type == "affine")
            warper_creator = makePtr<cv::AffineWarper>();
        else if (warp_type == "cylindrical")
            warper_creator = makePtr<cv::CylindricalWarper>();
        else if (warp_type == "spherical")
            warper_creator = makePtr<cv::SphericalWarper>();
        else if (warp_type == "fisheye")
            warper_creator = makePtr<cv::FisheyeWarper>();
        else if (warp_type == "stereographic")
            warper_creator = makePtr<cv::StereographicWarper>();
        else if (warp_type == "compressedPlaneA2B1")
            warper_creator = makePtr<cv::CompressedRectilinearWarper>(2.0f, 1.0f);
        else if (warp_type == "compressedPlaneA1.5B1")
            warper_creator = makePtr<cv::CompressedRectilinearWarper>(1.5f, 1.0f);
        else if (warp_type == "compressedPlanePortraitA2B1")
            warper_creator = makePtr<cv::CompressedRectilinearPortraitWarper>(2.0f, 1.0f);
        else if (warp_type == "compressedPlanePortraitA1.5B1")
            warper_creator = makePtr<cv::CompressedRectilinearPortraitWarper>(1.5f, 1.0f);
        else if (warp_type == "paniniA2B1")
            warper_creator = makePtr<cv::PaniniWarper>(2.0f, 1.0f);
        else if (warp_type == "paniniA1.5B1")
            warper_creator = makePtr<cv::PaniniWarper>(1.5f, 1.0f);
        else if (warp_type == "paniniPortraitA2B1")
            warper_creator = makePtr<cv::PaniniPortraitWarper>(2.0f, 1.0f);
        else if (warp_type == "paniniPortraitA1.5B1")
            warper_creator = makePtr<cv::PaniniPortraitWarper>(1.5f, 1.0f);
        else if (warp_type == "mercator")
            warper_creator = makePtr<cv::MercatorWarper>();
        else if (warp_type == "transverseMercator")
            warper_creator = makePtr<cv::TransverseMercatorWarper>();
    }
 
    if (!warper_creator)
    {
        cout << "Can't create the following warper '" << warp_type << "'
";
        return 1;
    }
 
    Ptr<RotationWarper> warper = warper_creator->create(static_cast<float>(warped_image_scale * seam_work_aspect));
 
    for (int i = 0; i < num_images; ++i)
    {
        Mat_<float> K;
        cameras[i].K().convertTo(K, CV_32F);
        float swa = (float)seam_work_aspect;
        K(0, 0) *= swa; K(0, 2) *= swa;
        K(1, 1) *= swa; K(1, 2) *= swa;
 
        corners[i] = warper->warp(images[i], K, cameras[i].R, INTER_LINEAR, BORDER_REFLECT, images_warped[i]);
        sizes[i] = images_warped[i].size();
 
        warper->warp(masks[i], K, cameras[i].R, INTER_NEAREST, BORDER_CONSTANT, masks_warped[i]);
    }
 
    vector<UMat> images_warped_f(num_images);
    for (int i = 0; i < num_images; ++i)
        images_warped[i].convertTo(images_warped_f[i], CV_32F);
 
    LOGLN("Warping images, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");
 
    LOGLN("Compensating exposure...");
#if ENABLE_LOG
    t = getTickCount();
#endif
 
    Ptr<ExposureCompensator> compensator = ExposureCompensator::createDefault(expos_comp_type);
    if (dynamic_cast<GainCompensator*>(compensator.get()))
    {
        GainCompensator* gcompensator = dynamic_cast<GainCompensator*>(compensator.get());
        gcompensator->setNrFeeds(expos_comp_nr_feeds);
    }
 
    if (dynamic_cast<ChannelsCompensator*>(compensator.get()))
    {
        ChannelsCompensator* ccompensator = dynamic_cast<ChannelsCompensator*>(compensator.get());
        ccompensator->setNrFeeds(expos_comp_nr_feeds);
    }
 
    if (dynamic_cast<BlocksCompensator*>(compensator.get()))
    {
        BlocksCompensator* bcompensator = dynamic_cast<BlocksCompensator*>(compensator.get());
        bcompensator->setNrFeeds(expos_comp_nr_feeds);
        bcompensator->setNrGainsFilteringIterations(expos_comp_nr_filtering);
        bcompensator->setBlockSize(expos_comp_block_size, expos_comp_block_size);
    }
 
    compensator->feed(corners, images_warped, masks_warped);
 
    LOGLN("Compensating exposure, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");
 
    LOGLN("Finding seams...");
#if ENABLE_LOG
    t = getTickCount();
#endif
 
    Ptr<SeamFinder> seam_finder;
    if (seam_find_type == "no")
        seam_finder = makePtr<detail::NoSeamFinder>();
    else if (seam_find_type == "voronoi")
        seam_finder = makePtr<detail::VoronoiSeamFinder>();
    else if (seam_find_type == "gc_color")
    {
#ifdef HAVE_OPENCV_CUDALEGACY
        if (try_cuda && cuda::getCudaEnabledDeviceCount() > 0)
            seam_finder = makePtr<detail::GraphCutSeamFinderGpu>(GraphCutSeamFinderBase::COST_COLOR);
        else
#endif
            seam_finder = makePtr<detail::GraphCutSeamFinder>(GraphCutSeamFinderBase::COST_COLOR);
    }
    else if (seam_find_type == "gc_colorgrad")
    {
#ifdef HAVE_OPENCV_CUDALEGACY
        if (try_cuda && cuda::getCudaEnabledDeviceCount() > 0)
            seam_finder = makePtr<detail::GraphCutSeamFinderGpu>(GraphCutSeamFinderBase::COST_COLOR_GRAD);
        else
#endif
            seam_finder = makePtr<detail::GraphCutSeamFinder>(GraphCutSeamFinderBase::COST_COLOR_GRAD);
    }
    else if (seam_find_type == "dp_color")
        seam_finder = makePtr<detail::DpSeamFinder>(DpSeamFinder::COLOR);
    else if (seam_find_type == "dp_colorgrad")
        seam_finder = makePtr<detail::DpSeamFinder>(DpSeamFinder::COLOR_GRAD);
    if (!seam_finder)
    {
        cout << "Can't create the following seam finder '" << seam_find_type << "'
";
        return 1;
    }
 
    seam_finder->find(images_warped_f, corners, masks_warped);
 
    LOGLN("Finding seams, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");
 
    // Release unused memory
    images.clear();
    images_warped.clear();
    images_warped_f.clear();
    masks.clear();
 
    LOGLN("Compositing...");
#if ENABLE_LOG
    t = getTickCount();
#endif
 
    Mat img_warped, img_warped_s;
    Mat dilated_mask, seam_mask, mask, mask_warped;
    Ptr<Blender> blender;
    Ptr<Timelapser> timelapser;
    //double compose_seam_aspect = 1;
    double compose_work_aspect = 1;
 
    for (int img_idx = 0; img_idx < num_images; ++img_idx)
    {
        LOGLN("Compositing image #" << indices[img_idx] + 1);
 
        // Read image and resize it if necessary
        full_img = imread(samples::findFile(img_names[img_idx]));
        if (!is_compose_scale_set)
        {
            if (compose_megapix > 0)
                compose_scale = min(1.0, sqrt(compose_megapix * 1e6 / full_img.size().area()));
            is_compose_scale_set = true;
 
            // Compute relative scales
            //compose_seam_aspect = compose_scale / seam_scale;
            compose_work_aspect = compose_scale / work_scale;
 
            // Update warped image scale
            warped_image_scale *= static_cast<float>(compose_work_aspect);
            warper = warper_creator->create(warped_image_scale);
 
            // Update corners and sizes
            for (int i = 0; i < num_images; ++i)
            {
                // Update intrinsics
                cameras[i].focal *= compose_work_aspect;
                cameras[i].ppx *= compose_work_aspect;
                cameras[i].ppy *= compose_work_aspect;
 
                // Update corner and size
                Size sz = full_img_sizes[i];
                if (std::abs(compose_scale - 1) > 1e-1)
                {
                    sz.width = cvRound(full_img_sizes[i].width * compose_scale);
                    sz.height = cvRound(full_img_sizes[i].height * compose_scale);
                }
 
                Mat K;
                cameras[i].K().convertTo(K, CV_32F);
                Rect roi = warper->warpRoi(sz, K, cameras[i].R);
                corners[i] = roi.tl();
                sizes[i] = roi.size();
            }
        }
        if (abs(compose_scale - 1) > 1e-1)
            resize(full_img, img, Size(), compose_scale, compose_scale, INTER_LINEAR_EXACT);
        else
            img = full_img;
        full_img.release();
        Size img_size = img.size();
 
        Mat K;
        cameras[img_idx].K().convertTo(K, CV_32F);
 
        // Warp the current image
        warper->warp(img, K, cameras[img_idx].R, INTER_LINEAR, BORDER_REFLECT, img_warped);
 
        // Warp the current image mask
        mask.create(img_size, CV_8U);
        mask.setTo(Scalar::all(255));
        warper->warp(mask, K, cameras[img_idx].R, INTER_NEAREST, BORDER_CONSTANT, mask_warped);
 
        // Compensate exposure
        compensator->apply(img_idx, corners[img_idx], img_warped, mask_warped);
 
        img_warped.convertTo(img_warped_s, CV_16S);
        img_warped.release();
        img.release();
        mask.release();
 
        dilate(masks_warped[img_idx], dilated_mask, Mat());
        resize(dilated_mask, seam_mask, mask_warped.size(), 0, 0, INTER_LINEAR_EXACT);
        mask_warped = seam_mask & mask_warped;
 
        if (!blender && !timelapse)
        {
            blender = Blender::createDefault(blend_type, try_cuda);
            Size dst_sz = resultRoi(corners, sizes).size();
            float blend_width = sqrt(static_cast<float>(dst_sz.area())) * blend_strength / 100.f;
            if (blend_width < 1.f)
                blender = Blender::createDefault(Blender::NO, try_cuda);
            else if (blend_type == Blender::MULTI_BAND)
            {
                MultiBandBlender* mb = dynamic_cast<MultiBandBlender*>(blender.get());
                mb->setNumBands(static_cast<int>(ceil(log(blend_width) / log(2.)) - 1.));
                LOGLN("Multi-band blender, number of bands: " << mb->numBands());
            }
            else if (blend_type == Blender::FEATHER)
            {
                FeatherBlender* fb = dynamic_cast<FeatherBlender*>(blender.get());
                fb->setSharpness(1.f / blend_width);
                LOGLN("Feather blender, sharpness: " << fb->sharpness());
            }
            blender->prepare(corners, sizes);
        }
        else if (!timelapser && timelapse)
        {
            timelapser = Timelapser::createDefault(timelapse_type);
            timelapser->initialize(corners, sizes);
        }
 
        // Blend the current image
        if (timelapse)
        {
            timelapser->process(img_warped_s, Mat::ones(img_warped_s.size(), CV_8UC1), corners[img_idx]);
            String fixedFileName;
            size_t pos_s = String(img_names[img_idx]).find_last_of("/\");
            if (pos_s == String::npos)
            {
                fixedFileName = "fixed_" + img_names[img_idx];
            }
            else
            {
                fixedFileName = "fixed_" + String(img_names[img_idx]).substr(pos_s + 1, String(img_names[img_idx]).length() - pos_s);
            }
            imwrite(fixedFileName, timelapser->getDst());
        }
        else
        {
            blender->feed(img_warped_s, mask_warped, corners[img_idx]);
        }
    }
 
    if (!timelapse)
    {
        Mat result, result_mask;
        blender->blend(result, result_mask);
 
        LOGLN("Compositing, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");
 
        imwrite(result_name, result);
    }
 
    LOGLN("Finished, total time: " << ((getTickCount() - app_start_time) / getTickFrequency()) << " sec");
    return 0;
}

stitching_detail 程序运行流程

• 命令行调用程序，输入源图像以及程序的参数      
• 特征点检测，判断是使用 surf 还是 orb，默认是 surf
• 对图像的特征点进行匹配，使用最近邻和次近邻方法，将两个最优的匹配的置信度 保存下来
• 对图像进行排序以及将置信度高的图像保存到同一个集合中，删除置信度比较低的图像间的匹配，得到能正确匹配的图像序列。这样将置信度高于门限的所有匹配合并到一个集合中 
• 对所有图像进行相机参数粗略估计，然后求出旋转矩阵
• 使用光束平均法进一步精准的估计出旋转矩阵
• 波形校正，水平或者垂直
• 拼接      
• 融合，多频段融合，光照补偿

stitching_detail 程序接口介绍 

• img1 img2 img3 输入图像      
• --preview  以预览模式运行程序，比正常模式要快，但输出图像分辨率低，拼接的分辨 率 compose_megapix 设置为 0.6
• --try_gpu  (yes|no)  是否使用 CUDA加速，默认为 no，使用CPU模式
• /* 运动估计参数 */    
• --work_megapix <--work_megapix <float>> 图像匹配时的分辨率大小，默认为 0.6    
• --features (surf | orb | sift | akaze) 选择 surf 或者 orb 算法进行特征点匹配，默认为 surf  
• --matcher (homography | affine) 用于成对图像匹配的匹配器  
• --estimator (homography | affine) 用于转换估计的估计器类型
• --match_conf <float> 特征点匹配步骤的匹配置信度，最近邻匹配距离与次近邻匹配距离的比值，surf 默认为 0.65，orb 默认为 0.3    
• --conf_thresh <float> 两幅图来自同一全景图的置信度，默认为 1.0    
• --ba (no | reproj | ray | affine) 光束平均法的误差函数选择，默认是 ray 方法    
• --ba_refine_mask (mask) 光束平均法设置优化掩码
• --wave_correct (no|horiz|vert) 波形校验水平，垂直或者没有 默认是 horiz(水平)
• --save_graph <file_name> 将匹配的图形以点的形式保存到文件中， Nm 代表匹配的数量，NI代表正确匹配的数量，C 表示置信度
• /*图像融合参数:*/ 
• --warp (plane|cylindrical|spherical|fisheye|stereographic|compressedPlaneA2B1|compressedPla  neA1.5B1|compressedPlanePortraitA2B1|compressedPlanePortraitA1.5B1|paniniA2B1|paniniA1.5B1|paniniPortraitA2B1|paniniPor traitA1.5B1|mercator|transverseMercator)     选择融合的平面，默认是球形    
• --seam_megapix <float> 拼接缝像素的大小 默认是 0.1
• --seam (no|voronoi|gc_color|gc_colorgrad) 拼接缝隙估计方法 默认是 gc_color    
• --compose_megapix <float> 拼接分辨率，默认为-1    
• --expos_comp (no|gain|gain_blocks) 光照补偿方法，默认是 gain_blocks    
• --blend (no|feather|multiband) 融合方法，默认是多频段融合    
• --blend_strength <float> 融合强度，0-100.默认是 5.    
• --output <result_img> 输出图像的文件名，默认是 result,jpg     命令使用实例，以及程序运行时的提示： 

上面使用默认参数，详细输出信息如下：

E:PracticeOpenCVAlgorithm_SummaryImage_Stitchingx64Debug>05_Image_Stitch_Stitching_Detailed.exe ./imgs/boat1.jpg ./imgs/boat2.jpg ./imgs/boat3.jpg ./imgs/boat4.jpg ./imgs/boat5.jpg ./imgs/boat6.jpg
Finding features...
[ INFO:0] global C:uildmaster_winpack-build-win64-vc15opencvmodulescoresrcocl.cpp (891) cv::ocl::haveOpenCL Initialize OpenCL runtime...
Features in image #1: 500
[ INFO:0] global C:uildmaster_winpack-build-win64-vc15opencvmodulescoresrcocl.cpp (433) cv::ocl::OpenCLBinaryCacheConfigurator::OpenCLBinaryCacheConfigurator Successfully initialized OpenCL cache directory: C:UsersA4080599AppDataLocalTempopencv4.4opencl_cache
[ INFO:0] global C:uildmaster_winpack-build-win64-vc15opencvmodulescoresrcocl.cpp (457) cv::ocl::OpenCLBinaryCacheConfigurator::prepareCacheDirectoryForContext Preparing OpenCL cache configuration for context: NVIDIA_Corporation--GeForce_GTX_1070--411_31
Features in image #2: 500
Features in image #3: 500
Features in image #4: 500
Features in image #5: 500
Features in image #6: 500
Finding features, time: 5.46377 sec
Pairwise matchingPairwise matching, time: 3.24159 sec
Initial camera intrinsics #1:
K:
[534.6674906996568, 0, 474.5;
 0, 534.6674906996568, 316;
 0, 0, 1]
R:
[0.91843718, -0.09762425, -1.1678253;
 0.0034433089, 1.0835428, -0.025021957;
 0.28152198, 0.16100603, 0.91920781]
Initial camera intrinsics #2:
K:
[534.6674906996568, 0, 474.5;
 0, 534.6674906996568, 316;
 0, 0, 1]
R:
[1.001171, -0.085758291, -0.64530683;
 0.010103324, 1.0520245, -0.030576767;
 0.15743911, 0.12035993, 1]
Initial camera intrinsics #3:
K:
[534.6674906996568, 0, 474.5;
 0, 534.6674906996568, 316;
 0, 0, 1]
R:
[1, 0, 0;
 0, 1, 0;
 0, 0, 1]
Initial camera intrinsics #4:
K:
[534.6674906996568, 0, 474.5;
 0, 534.6674906996568, 316;
 0, 0, 1]
R:
[0.8474561, 0.028589081, 0.75133896;
 -0.0014587968, 0.92028928, 0.033205934;
 -0.17483309, 0.018777205, 0.84592116]
Initial camera intrinsics #5:
K:
[534.6674906996568, 0, 474.5;
 0, 534.6674906996568, 316;
 0, 0, 1]
R:
[0.60283858, 0.069275051, 1.2121853;
 -0.014153662, 0.85474133, 0.014057174;
 -0.29529575, 0.053770453, 0.61932623]
Initial camera intrinsics #6:
K:
[534.6674906996568, 0, 474.5;
 0, 534.6674906996568, 316;
 0, 0, 1]
R:
[0.41477469, 0.075901195, 1.4396564;
 -0.015423983, 0.82344943, 0.0061162044;
 -0.35168326, 0.055747174, 0.42653102]
Camera #1:
K:
[1068.953598931666, 0, 474.5;
 0, 1068.953598931666, 316;
 0, 0, 1]
R:
[0.84266716, -0.010490002, -0.53833258;
 0.004485324, 0.99991232, -0.01246338;
 0.53841609, 0.0080878884, 0.84264034]
Camera #2:
K:
[1064.878323247434, 0, 474.5;
 0, 1064.878323247434, 316;
 0, 0, 1]
R:
[0.95117813, -0.015436338, -0.3082563;
 0.01137107, 0.99982315, -0.014980057;
 0.308433, 0.010743499, 0.95118535]
Camera #3:
K:
[1065.382193682081, 0, 474.5;
 0, 1065.382193682081, 316;
 0, 0, 1]
R:
[1, -1.6298145e-09, 0;
 -1.5716068e-09, 1, 0;
 0, 0, 1]
Camera #4:
K:
[1067.611537959627, 0, 474.5;
 0, 1067.611537959627, 316;
 0, 0, 1]
R:
[0.91316396, -7.9067249e-06, 0.40759254;
 -0.0075879274, 0.99982637, 0.017019274;
 -0.4075219, -0.018634165, 0.91300529]
Camera #5:
K:
[1080.708135180496, 0, 474.5;
 0, 1080.708135180496, 316;
 0, 0, 1]
R:
[0.70923853, 0.0025724203, 0.70496398;
 -0.0098195076, 0.99993235, 0.0062302947;
 -0.70490021, -0.01134116, 0.70921582]
Camera #6:
K:
[1080.90412660159, 0, 474.5;
 0, 1080.90412660159, 316;
 0, 0, 1]
R:
[0.49985889, 3.5938341e-05, 0.86610687;
 -0.00682831, 0.99996907, 0.0038993564;
 -0.86607999, -0.0078631733, 0.49984369]
Warping images (auxiliary)...
Warping images, time: 0.0791121 sec
Compensating exposure...
Compensating exposure, time: 0.72288 sec
Finding seams...
Finding seams, time: 3.09237 sec
Compositing...
Compositing image #1
Multi-band blender, number of bands: 8
Compositing image #2
Compositing image #3
Compositing image #4
Compositing image #5
Compositing image #6
Compositing, time: 13.7766 sec
Finished, total time: 29.4535 sec

输入图像boat1.jpg、boat2.jpg、boat3.jpg、boat4.jpg、boat5.jpg、boat6.jpg如下(可以在OpenCV安装目录下找到D:OpenCV4.4opencv_extra-master estdatastitching)

 

 

 

结果图：

参数warp_type 设置为"plane"，效果图如下：

参数warp_type 设置为"fisheye"，效果图如下(旋转90°后)：

其他的参数可以根据自己需要修改，如果要自己完成还需要详细了解拼接步骤再优化。