Task02 Данила Ярмаркин ИТМО

.github/workflows/cmake.yml

@@ -2,6 +2,7 @@ name: CMake
 
 on: [push, pull_request]
 
+
 env:
   BUILD_TYPE: RelWithDebInfo
 

.gitignore

@@ -2,3 +2,5 @@
 .idea
 build
 cmake-build*
+*.zip
+opencv-*

src/phg/matching/descriptor_matcher.cpp

@@ -3,25 +3,28 @@
 #include <opencv2/flann/miniflann.hpp>
 #include "flann_factory.h"
 
-void phg::DescriptorMatcher::filterMatchesRatioTest(const std::vector<std::vector<cv::DMatch>> &matches,
-                                                    std::vector<cv::DMatch> &filtered_matches)
-{
+void phg::DescriptorMatcher::filterMatchesRatioTest(const std::vector<std::vector<cv::DMatch>>& matches,
+                                                    std::vector<cv::DMatch>& filtered_matches) {
     filtered_matches.clear();
 
-    throw std::runtime_error("not implemented yet");
+    filtered_matches.reserve(matches.size());
+    for (const auto& match: matches) {
+        if (match.size() < 2) continue;
+        if (match[0].distance < 0.75f * match[1].distance)
+            filtered_matches.push_back(match[0]);
+    }
 }
 
 
-void phg::DescriptorMatcher::filterMatchesClusters(const std::vector<cv::DMatch> &matches,
+void phg::DescriptorMatcher::filterMatchesClusters(const std::vector<cv::DMatch>& matches,
                                                    const std::vector<cv::KeyPoint> keypoints_query,
                                                    const std::vector<cv::KeyPoint> keypoints_train,
-                                                   std::vector<cv::DMatch> &filtered_matches)
-{
+                                                   std::vector<cv::DMatch>& filtered_matches) {
     filtered_matches.clear();
 
-    const size_t  total_neighbours  = 5;  // total number of neighbours to test (including candidate)
-    const size_t  consistent_matches  = 3;  // minimum number of consistent matches (including candidate)
-    const float  radius_limit_scale  = 2.f;  // limit search radius by scaled median
+    const size_t total_neighbours = 5;  // total number of neighbours to test (including candidate)
+    const size_t consistent_matches = 3;  // minimum number of consistent matches (including candidate)
+    const float radius_limit_scale = 2.f;  // limit search radius by scaled median
 
     const int n_matches = matches.size();
 
@@ -35,42 +38,51 @@ void phg::DescriptorMatcher::filterMatchesClusters(const std::vector<cv::DMatch>
         points_query.at<cv::Point2f>(i) = keypoints_query[matches[i].queryIdx].pt;
         points_train.at<cv::Point2f>(i) = keypoints_train[matches[i].trainIdx].pt;
     }
-//
-//    // размерность всего 2, так что точное KD-дерево
-//    std::shared_ptr<cv::flann::IndexParams> index_params = flannKdTreeIndexParams(TODO);
-//    std::shared_ptr<cv::flann::SearchParams> search_params = flannKsTreeSearchParams(TODO);
-//
-//    std::shared_ptr<cv::flann::Index> index_query = flannKdTreeIndex(points_query, index_params);
-//    std::shared_ptr<cv::flann::Index> index_train = flannKdTreeIndex(points_train, index_params);
-//
-//    // для каждой точки найти total neighbors ближайших соседей
-//    cv::Mat indices_query(n_matches, total_neighbours, CV_32SC1);
-//    cv::Mat distances2_query(n_matches, total_neighbours, CV_32FC1);
-//    cv::Mat indices_train(n_matches, total_neighbours, CV_32SC1);
-//    cv::Mat distances2_train(n_matches, total_neighbours, CV_32FC1);
-//
-//    index_query->knnSearch(points_query, indices_query, distances2_query, total_neighbours, *search_params);
-//    index_train->knnSearch(points_train, indices_train, distances2_train, total_neighbours, *search_params);
-//
-//    // оценить радиус поиска для каждой картинки
-//    // NB: radius2_query, radius2_train: квадраты радиуса!
-//    float radius2_query, radius2_train;
-//    {
-//        std::vector<double> max_dists2_query(n_matches);
-//        std::vector<double> max_dists2_train(n_matches);
-//        for (int i = 0; i < n_matches; ++i) {
-//            max_dists2_query[i] = distances2_query.at<float>(i, total_neighbours - 1);
-//            max_dists2_train[i] = distances2_train.at<float>(i, total_neighbours - 1);
-//        }
-//
-//        int median_pos = n_matches / 2;
-//        std::nth_element(max_dists2_query.begin(), max_dists2_query.begin() + median_pos, max_dists2_query.end());
-//        std::nth_element(max_dists2_train.begin(), max_dists2_train.begin() + median_pos, max_dists2_train.end());
-//
-//        radius2_query = max_dists2_query[median_pos] * radius_limit_scale * radius_limit_scale;
-//        radius2_train = max_dists2_train[median_pos] * radius_limit_scale * radius_limit_scale;
-//    }
-//
+
+    // размерность всего 2, так что точное KD-дерево
+    std::shared_ptr<cv::flann::IndexParams> index_params = flannKdTreeIndexParams(1);
+    std::shared_ptr<cv::flann::SearchParams> search_params = flannKsTreeSearchParams(32);
+
+    std::shared_ptr<cv::flann::Index> index_query = flannKdTreeIndex(points_query, index_params);
+    std::shared_ptr<cv::flann::Index> index_train = flannKdTreeIndex(points_train, index_params);
+
+    // для каждой точки найти total neighbors ближайших соседей
+    cv::Mat indices_query(n_matches, total_neighbours, CV_32SC1);
+    cv::Mat distances2_query(n_matches, total_neighbours, CV_32FC1);
+    cv::Mat indices_train(n_matches, total_neighbours, CV_32SC1);
+    cv::Mat distances2_train(n_matches, total_neighbours, CV_32FC1);
+
+    index_query->knnSearch(points_query, indices_query, distances2_query, total_neighbours, *search_params);
+    index_train->knnSearch(points_train, indices_train, distances2_train, total_neighbours, *search_params);
+
+    // оценить радиус поиска для каждой картинки
+    // NB: radius2_query, radius2_train: квадраты радиуса!
+    float radius2_query, radius2_train;
+    {
+        std::vector<double> max_dists2_query(n_matches);
+        std::vector<double> max_dists2_train(n_matches);
+        for (int i = 0; i < n_matches; ++i) {
+            max_dists2_query[i] = distances2_query.at<float>(i, total_neighbours - 1);
+            max_dists2_train[i] = distances2_train.at<float>(i, total_neighbours - 1);
+        }
+
+        int median_pos = n_matches / 2;
+        std::nth_element(max_dists2_query.begin(), max_dists2_query.begin() + median_pos, max_dists2_query.end());
+        std::nth_element(max_dists2_train.begin(), max_dists2_train.begin() + median_pos, max_dists2_train.end());
+
+        radius2_query = max_dists2_query[median_pos] * radius_limit_scale * radius_limit_scale;
+        radius2_train = max_dists2_train[median_pos] * radius_limit_scale * radius_limit_scale;
+    }
+
 //    метч остается, если левое и правое множества первых total_neighbors соседей в радиусах поиска(radius2_query, radius2_train) имеют как минимум consistent_matches общих элементов
-//    // TODO заполнить filtered_matches
+    filtered_matches.reserve(n_matches);
+    for (int i = 0; i < n_matches; ++i) {
+        std::set<int> s;
+        for (int j = 0; j < total_neighbours && distances2_query.at<float>(i, j) <= radius2_query; ++j)
+            s.insert(indices_query.at<int>(i, j));
+        int intersections = 0;
+        for (int j = 0; j < total_neighbours && distances2_train.at<float>(i, j) <= radius2_train; ++j)
+            if (s.count(indices_train.at<int>(i, j))) ++intersections;
+        if (intersections >= consistent_matches) filtered_matches.push_back(matches[i]);
+    }
 }

src/phg/matching/flann_matcher.cpp

@@ -6,8 +6,8 @@
 phg::FlannMatcher::FlannMatcher()
 {
     // параметры для приближенного поиска
-//    index_params = flannKdTreeIndexParams(TODO);
-//    search_params = flannKsTreeSearchParams(TODO);
+    index_params = flannKdTreeIndexParams(4);
+    search_params = flannKsTreeSearchParams(32);
 }
 
 void phg::FlannMatcher::train(const cv::Mat &train_desc)
@@ -17,5 +17,13 @@ void phg::FlannMatcher::train(const cv::Mat &train_desc)
 
 void phg::FlannMatcher::knnMatch(const cv::Mat &query_desc, std::vector<std::vector<cv::DMatch>> &matches, int k) const
 {
-    throw std::runtime_error("not implemented yet");
+    cv::Mat idx, dst;
+    flann_index->knnSearch(query_desc, idx, dst, k, *search_params);
+    matches.resize(query_desc.rows);
+    for (int i = 0; i != idx.rows; ++i) {
+        auto& row = matches[i];
+        row.reserve(k);
+        for (int j = 0; j != idx.cols; ++j)
+            row.emplace_back(i, idx.at<int>(i, j), std::sqrt(dst.at<float>(i, j)));
+    }
 }

src/phg/sfm/homography.cpp

@@ -84,8 +84,12 @@ namespace {
             double w1 = ws1[i];
 
             // 8 elements of matrix + free term as needed by gauss routine
-//            A.push_back({TODO});
-//            A.push_back({TODO});
+            A.push_back({.0, .0, .0,
+                         -x0 * w1, -y0 * w1, -w0 * w1,
+                         x0 * y1, y0 * y1, -w0 * y1});
+            A.push_back({x0 * w1, y0 * w1, w0 * w1,
+                         .0, .0, .0,
+                         -x0 * x1, -y0 * x1, w0 * x1});
         }
 
         int res = gauss(A, H);
@@ -162,63 +166,62 @@ namespace {
             throw std::runtime_error("findHomography: points_lhs.size() != points_rhs.size()");
         }
 
-        // TODO Дополнительный балл, если вместо обычной версии будет использована модификация a-contrario RANSAC
         // * [1] Automatic Homographic Registration of a Pair of Images, with A Contrario Elimination of Outliers. (Lionel Moisan, Pierre Moulon, Pascal Monasse)
         // * [2] Adaptive Structure from Motion with a contrario model estimation. (Pierre Moulon, Pascal Monasse, Renaud Marlet)
         // * (простое описание для понимания)
         // * [3] http://ikrisoft.blogspot.com/2015/01/ransac-with-contrario-approach.html
 
-//        const int n_matches = points_lhs.size();
+        const int n_matches = points_lhs.size();
 //
 //        // https://en.wikipedia.org/wiki/Random_sample_consensus#Parameters
-//        const int n_trials = TODO;
-//
-//        const int n_samples = TODO;
-//        uint64_t seed = 1;
-//        const double reprojection_error_threshold_px = 2;
-//
-//        int best_support = 0;
-//        cv::Mat best_H;
-//
-//        std::vector<int> sample;
-//        for (int i_trial = 0; i_trial < n_trials; ++i_trial) {
-//            randomSample(sample, n_matches, n_samples, &seed);
-//
-//            cv::Mat H = estimateHomography4Points(points_lhs[sample[0]], points_lhs[sample[1]], points_lhs[sample[2]], points_lhs[sample[3]],
-//                                                  points_rhs[sample[0]], points_rhs[sample[1]], points_rhs[sample[2]], points_rhs[sample[3]]);
-//
-//            int support = 0;
-//            for (int i_point = 0; i_point < n_matches; ++i_point) {
-//                try {
-//                    cv::Point2d proj = phg::transformPoint(points_lhs[i_point], H);
-//                    if (cv::norm(proj - cv::Point2d(points_rhs[i_point])) < reprojection_error_threshold_px) {
-//                        ++support;
-//                    }
-//                } catch (const std::exception &e)
-//                {
-//                    std::cerr << e.what() << std::endl;
-//                }
-//            }
-//
-//            if (support > best_support) {
-//                best_support = support;
-//                best_H = H;
-//
-//                std::cout << "estimateHomographyRANSAC : support: " << best_support << "/" << n_matches << std::endl;
-//
-//                if (best_support == n_matches) {
-//                    break;
-//                }
-//            }
-//        }
-//
-//        std::cout << "estimateHomographyRANSAC : best support: " << best_support << "/" << n_matches << std::endl;
-//
-//        if (best_support == 0) {
-//            throw std::runtime_error("estimateHomographyRANSAC : failed to estimate homography");
-//        }
-//
-//        return best_H;
+
+        const int n_samples = 4;
+        const int n_trials = std::ceil(std::log(1 - 0.999) / std::log(1 - std::pow(0.5, n_samples)));
+        uint64_t seed = 1;
+        const double reprojection_error_threshold_px = 2;
+
+        int best_support = 0;
+        cv::Mat best_H;
+
+        std::vector<int> sample;
+        for (int i_trial = 0; i_trial < n_trials; ++i_trial) {
+            randomSample(sample, n_matches, n_samples, &seed);
+
+            cv::Mat H = estimateHomography4Points(points_lhs[sample[0]], points_lhs[sample[1]], points_lhs[sample[2]], points_lhs[sample[3]],
+                                                  points_rhs[sample[0]], points_rhs[sample[1]], points_rhs[sample[2]], points_rhs[sample[3]]);
+
+            int support = 0;
+            for (int i_point = 0; i_point < n_matches; ++i_point) {
+                try {
+                    cv::Point2d proj = phg::transformPoint(points_lhs[i_point], H);
+                    if (cv::norm(proj - cv::Point2d(points_rhs[i_point])) < reprojection_error_threshold_px) {
+                        ++support;
+                    }
+                } catch (const std::exception &e)
+                {
+                    std::cerr << e.what() << std::endl;
+                }
+            }
+
+            if (support > best_support) {
+                best_support = support;
+                best_H = H;
+
+                std::cout << "estimateHomographyRANSAC : support: " << best_support << "/" << n_matches << std::endl;
+
+                if (best_support == n_matches) {
+                    break;
+                }
+            }
+        }
+
+        std::cout << "estimateHomographyRANSAC : best support: " << best_support << "/" << n_matches << std::endl;
+
+        if (best_support == 0) {
+            throw std::runtime_error("estimateHomographyRANSAC : failed to estimate homography");
+        }
+
+        return best_H;
     }
 
 }
@@ -238,7 +241,8 @@ cv::Mat phg::findHomographyCV(const std::vector<cv::Point2f> &points_lhs, const
 // таким преобразованием внутри занимается функции cv::perspectiveTransform и cv::warpPerspective
 cv::Point2d phg::transformPoint(const cv::Point2d &pt, const cv::Mat &T)
 {
-    throw std::runtime_error("not implemented yet");
+    cv::Mat res = T * cv::Vec3d(pt.x, pt.y, 1);
+    return {res.at<double>(0) / res.at<double>(2), res.at<double>(1) / res.at<double>(2)};
 }
 
 cv::Point2d phg::transformPointCV(const cv::Point2d &pt, const cv::Mat &T) {

src/phg/sfm/panorama_stitcher.cpp

@@ -4,6 +4,7 @@
 #include <libutils/bbox2.h>
 #include <iostream>
 
+
 /*
  * imgs - список картинок
  * parent - список индексов, каждый индекс указывает, к какой картинке должна быть приклеена текущая картинка
@@ -20,12 +21,30 @@ cv::Mat phg::stitchPanorama(const std::vector<cv::Mat> &imgs,
 
     // вектор гомографий, для каждой картинки описывает преобразование до корня
     std::vector<cv::Mat> Hs(n_images);
-    {
-        // здесь надо посчитать вектор Hs
-        // при этом можно обойтись n_images - 1 вызовами функтора homography_builder
-        throw std::runtime_error("not implemented yet");
+
+    // здесь надо посчитать вектор Hs
+    // при этом можно обойтись n_images - 1 вызовами функтора homography_builder
+
+    std::vector<bool> used(n_images, false);
+    const auto dfs = [&](const auto &self, int i) {
+        if (used[i]) {
+            return Hs[i];
+        }
+        used[i] = true;
+
+        if (parent[i] == -1) {
+            Hs[i] = cv::Mat::eye(3, 3, CV_64FC1);
+        } else {
+            Hs[i] = homography_builder(imgs[i], imgs[parent[i]]) * self(self, parent[i]);
+        }
+        return Hs[i];
+    };
+
+    for (int i = 0; i < n_images; ++i) {
+        dfs(dfs, i);
     }
 
+
     bbox2<double, cv::Point2d> bbox;
     for (int i = 0; i < n_images; ++i) {
         double w = imgs[i].cols;