OPenCV 图像拼接之------stitching和stitching_detailed

Stitcher类与detail命名空间

OpenCV提供了高级别的函数封装在Stitcher类中，使用很方便，不用考虑太多的细节。

低级别函数封装在detail命名空间中，展示了opencv算法实现的很多步骤和细节，使熟悉如下拼接流水线的用户，方便自己定制。

可见OpenCV图像拼接模块的实现是十分精密和复杂的，拼接的结果很完善，但同时也是费时的，完全不能够实现实时应用。

我在研究detail源码时，由于水平有限，并不能自由灵活地对各种部件取其所需，取舍随意。

官方提供的stitching和stitching_detailed使用示例，分别是高级别和低级别封装这两种方式正确地使用示例。两种结果产生的拼接结果相同，后者却可以允许用户，在参数变量初始化时，选择各项算法。如下所示：

这涉及到以下算法流程：

1. 命令行调用程序，输入源图像以及程序的参数

2. 特征点检测，判断是使用surf还是orb，默认是surf。

3. 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。

4. 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。

5. 对所有图像进行相机参数粗略估计，然后求出旋转矩阵

6. 使用光束平均法进一步精准的估计出旋转矩阵。

7. 波形校正，水平或者垂直

8. 拼接

9. 融合，多频段融合，光照补偿，

---

Stitcher类使用示例

#include 
#include 
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/stitching/stitcher.hpp"
#include

using namespace std;
using namespace cv;

bool try_use_gpu = false;
vector imgs;
string result_name = "result.jpg";

void getFiles(string path, vector<string>& files)
{
    //文件句柄  
    long   hFile = 0;
    //文件信息  
    struct _finddata_t fileinfo;
    string p;
    if ((hFile = _findfirst(p.assign(path).append("/*").c_str(), &fileinfo)) != -1)
    {
        do
        {
            //如果是目录,迭代之  
            //如果不是,加入列表  
            if ((fileinfo.attrib &  _A_SUBDIR))
            {
                if (strcmp(fileinfo.name, ".") != 0 && strcmp(fileinfo.name, "..") != 0)
                    getFiles(p.assign(path).append("/").append(fileinfo.name), files);
            }
            else
            {
                files.push_back(p.assign(path).append("/").append(fileinfo.name));
            }
        } while (_findnext(hFile, &fileinfo) == 0);
        _findclose(hFile);
    }
}

int main(int argc, char* argv[])
{
    vector<string> filesName;
    getFiles("E:/workspace/iamge/dataset/",filesName);

    for (string fileName:filesName)
    {
        Mat img = imread(fileName,1);
        imgs.push_back(img);
    }

    Mat pano;
    Stitcher stitcher = Stitcher::createDefault(try_use_gpu);
    Stitcher::Status status = stitcher.stitch(imgs, pano);

    if (status != Stitcher::OK)
    {
        cout << "Can't stitch images, error code = " << int(status) << endl;
        return -1;
    }

    imwrite(result_name, pano);
    imshow(result_name,pano);
    waitKey(0);
    return 0;
}

其中的getfiles()函数的功能是获取一个目录下的所有文件地址。这使得可以在windows下批量的读取图像的地址。

---

stitching_detailed使用示例

#include 
#include 
#include 
#include "opencv2/opencv_modules.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/stitching/detail/autocalib.hpp"
#include "opencv2/stitching/detail/blenders.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/util.hpp"
#include "opencv2/stitching/detail/warpers.hpp"
#include "opencv2/stitching/warpers.hpp"

using namespace std;
using namespace cv;
using namespace cv::detail;


//
#define ENABLE_LOG 1

// Default command line args
vector<string> img_names;
bool preview = false;
bool try_gpu = true;
double work_megapix = 0.6;
double seam_megapix = 0.1;
double compose_megapix = -1;
float conf_thresh = 1.f;
string features_type = "surf";
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;
float match_conf = 0.3f;
string seam_find_type = "gc_color";
int blend_type = Blender::MULTI_BAND;
float blend_strength = 5;
string result_name = "result.jpg";


int main(int argc, char* argv[])
{
    //读入图像
    double ttt = getTickCount();

    img_names.push_back("E:/workspace/iamge/dataset/yard1.jpg");
    img_names.push_back("E:/workspace/iamge/dataset/yard2.jpg");
    img_names.push_back("E:/workspace/iamge/dataset/yard3.jpg");
    img_names.push_back("E:/workspace/iamge/dataset/yard4.jpg");

#if ENABLE_LOG
    int64 app_start_time = getTickCount();
#endif

    cv::setBreakOnError(true);

    /*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 finder;
    if (features_type == "surf")
    {
#if defined(HAVE_OPENCV_NONFREE) && defined(HAVE_OPENCV_GPU)
        if (try_gpu && gpu::getCudaEnabledDeviceCount() > 0)
            finder = new SurfFeaturesFinderGpu();
        else
#endif
            finder = new SurfFeaturesFinder();
    }
    else if (features_type == "orb")
    {
        finder = new OrbFeaturesFinder();
    }
    else
    {
        cout << "Unknown 2D features type: '" << features_type << "'.\n";
        return -1;
    }

    Mat full_img, img;
    vector features(num_images);
    vector images(num_images);
    vector full_img_sizes(num_images);
    double seam_work_aspect = 1;



    for (int i = 0; i < num_images; ++i)
    {
        full_img = imread(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);
        }
        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;
        }

        (*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);
        images[i] = img.clone();
    }

    finder->collectGarbage();
    full_img.release();
    img.release();

    LOGLN("Finding features, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");

    LOG("Pairwise matching");
#if ENABLE_LOG
    t = getTickCount();
#endif
    vector pairwise_matches;
    BestOf2NearestMatcher matcher(try_gpu, 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 img_subset;
    vector<string> img_names_subset;
    vector 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;
    }

    HomographyBasedEstimator estimator;
    vector cameras;
    estimator(features, pairwise_matches, cameras);

    for (size_t i = 0; i < cameras.size(); ++i)
    {
        Mat R;
        cameras[i].R.convertTo(R, CV_32F);
        cameras[i].R = R;
        LOGLN("Initial intrinsics #" << indices[i]+1 << ":\n" << cameras[i].K());
    }

    Ptr adjuster;
    if (ba_cost_func == "reproj") adjuster = new detail::BundleAdjusterReproj();
    else if (ba_cost_func == "ray") adjuster = new detail::BundleAdjusterRay();
    else
    {
        cout << "Unknown bundle adjustment cost function: '" << ba_cost_func << "'.\n";
        return -1;
    }
    adjuster->setConfThresh(conf_thresh);
    Mat_ 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);
    (*adjuster)(features, pairwise_matches, cameras);

    // Find median focal length

    vector<double> focals;
    for (size_t i = 0; i < cameras.size(); ++i)
    {
        LOGLN("Camera #" << indices[i]+1 << ":\n" << cameras[i].K());
        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 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 corners(num_images);
    vector masks_warped(num_images);
    vector images_warped(num_images);
    vector sizes(num_images);
    vector masks(num_images);

    // Preapre 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 warper_creator;
#if defined(HAVE_OPENCV_GPU)
    if (try_gpu && gpu::getCudaEnabledDeviceCount() > 0)
    {
        if (warp_type == "plane") warper_creator = new cv::PlaneWarperGpu();
        else if (warp_type == "cylindrical") warper_creator = new cv::CylindricalWarperGpu();
        else if (warp_type == "spherical") warper_creator = new cv::SphericalWarperGpu();
    }
    else
#endif
    {
        if (warp_type == "plane") warper_creator = new cv::PlaneWarper();
        else if (warp_type == "cylindrical") warper_creator = new cv::CylindricalWarper();
        else if (warp_type == "spherical") warper_creator = new cv::SphericalWarper();
        else if (warp_type == "fisheye") warper_creator = new cv::FisheyeWarper();
        else if (warp_type == "stereographic") warper_creator = new cv::StereographicWarper();
        else if (warp_type == "compressedPlaneA2B1") warper_creator = new cv::CompressedRectilinearWarper(2, 1);
        else if (warp_type == "compressedPlaneA1.5B1") warper_creator = new cv::CompressedRectilinearWarper(1.5, 1);
        else if (warp_type == "compressedPlanePortraitA2B1") warper_creator = new cv::CompressedRectilinearPortraitWarper(2, 1);
        else if (warp_type == "compressedPlanePortraitA1.5B1") warper_creator = new cv::CompressedRectilinearPortraitWarper(1.5, 1);
        else if (warp_type == "paniniA2B1") warper_creator = new cv::PaniniWarper(2, 1);
        else if (warp_type == "paniniA1.5B1") warper_creator = new cv::PaniniWarper(1.5, 1);
        else if (warp_type == "paniniPortraitA2B1") warper_creator = new cv::PaniniPortraitWarper(2, 1);
        else if (warp_type == "paniniPortraitA1.5B1") warper_creator = new cv::PaniniPortraitWarper(1.5, 1);
        else if (warp_type == "mercator") warper_creator = new cv::MercatorWarper();
        else if (warp_type == "transverseMercator") warper_creator = new cv::TransverseMercatorWarper();
    }

    if (warper_creator.empty())
    {
        cout << "Can't create the following warper '" << warp_type << "'\n";
        return 1;
    }

    Ptr 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 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");

    Ptr compensator = ExposureCompensator::createDefault(expos_comp_type);
    compensator->feed(corners, images_warped, masks_warped);

    Ptr seam_finder;
    if (seam_find_type == "no")
        seam_finder = new detail::NoSeamFinder();
    else if (seam_find_type == "voronoi")
        seam_finder = new detail::VoronoiSeamFinder();
    else if (seam_find_type == "gc_color")
    {
#if defined(HAVE_OPENCV_GPU)
        if (try_gpu && gpu::getCudaEnabledDeviceCount() > 0)
            seam_finder = new detail::GraphCutSeamFinderGpu(GraphCutSeamFinderBase::COST_COLOR);
        else
#endif
            seam_finder = new detail::GraphCutSeamFinder(GraphCutSeamFinderBase::COST_COLOR);
    }
    else if (seam_find_type == "gc_colorgrad")
    {
#if defined(HAVE_OPENCV_GPU)
        if (try_gpu && gpu::getCudaEnabledDeviceCount() > 0)
            seam_finder = new detail::GraphCutSeamFinderGpu(GraphCutSeamFinderBase::COST_COLOR_GRAD);
        else
#endif
            seam_finder = new detail::GraphCutSeamFinder(GraphCutSeamFinderBase::COST_COLOR_GRAD);
    }
    else if (seam_find_type == "dp_color")
        seam_finder = new detail::DpSeamFinder(DpSeamFinder::COLOR);
    else if (seam_find_type == "dp_colorgrad")
        seam_finder = new detail::DpSeamFinder(DpSeamFinder::COLOR_GRAD);
    if (seam_finder.empty())
    {
        cout << "Can't create the following seam finder '" << seam_find_type << "'\n";
        return 1;
    }

    seam_finder->find(images_warped_f, corners, masks_warped);

    // 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;
    //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(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);
        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());
        mask_warped = seam_mask & mask_warped;

        if (blender.empty())
        {
            blender = Blender::createDefault(blend_type, try_gpu);
            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_gpu);
            else if (blend_type == Blender::MULTI_BAND)
            {
                MultiBandBlender* mb = dynamic_cast(static_cast(blender));
                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(static_cast(blender));
                fb->setSharpness(1.f/blend_width);
                LOGLN("Feather blender, sharpness: " << fb->sharpness());
            }
            blender->prepare(corners, sizes);
        }

        // Blend the current image
        blender->feed(img_warped_s, mask_warped, corners[img_idx]);
    }

    Mat result, result_mask;

    blender->blend(result, result_mask);

    LOGLN("Compositing, time: " << ((getTickCount() - t) / getTickFrequency()) << " sec");

    imwrite(result_name, result);
    result.convertTo(result,CV_8UC1);
    imshow("stitch",result);
    ttt = ((double)getTickCount() - ttt) / getTickFrequency();
    cout << "总的拼接时间:" << ttt << endl;
    waitKey(0);

    LOGLN("Finished, total time: " << ((getTickCount() - app_start_time) / getTickFrequency()) << " sec");
    return 0;
}

拼接结果

输入4张图像，每张分辨率为327*245，总的拼接时间为9.25s。