g2o顶点和边 ICP计算6维度转换矩阵

维度转换矩阵"/>

g2o顶点和边 ICP计算6维度转换矩阵

3D-3D g2o顶点和边设置方法

• 顶点和边的设置
• • 顶点，优化变量
  • 设定一元边
• BA函数调用g2o
• 得到3D点（深度信息）

顶点和边的设置

顶点和边的说明可见上一条博客

顶点，优化变量

/// vertex and edges used in g2o ba 
class VertexPose : public g2o::BaseVertex<6, Sophus::SE3d> {
public:EIGEN_MAKE_ALIGNED_OPERATOR_NEW;
//初始估计值virtual void setToOriginImpl() override {_estimate = Sophus::SE3d();}/// left multiplication on SE3，更新virtual void oplusImpl(const double *update) override {Eigen::Matrix<double, 6, 1> update_eigen;update_eigen << update[0], update[1], update[2], update[3], update[4], update[5];_estimate = Sophus::SE3d::exp(update_eigen) * _estimate;}virtual bool read(istream &in) override {}virtual bool write(ostream &out) const override {}
};

设定一元边

误差方程关联的参数为两个三维坐标和一个6维转换矩阵（顶点，优化变量）

/// g2o edge
class EdgeProjectXYZRGBDPoseOnly : public g2o::BaseUnaryEdge<3, Eigen::Vector3d, VertexPose> {
public:EIGEN_MAKE_ALIGNED_OPERATOR_NEW;
//新建边的参数，有一个三维顶点是不变的_points
//另一个三维顶点是_measurementEdgeProjectXYZRGBDPoseOnly(const Eigen::Vector3d &point) : _point(point) {}virtual void computeError() override {const VertexPose *pose = static_cast<const VertexPose *> ( _vertices[0] );_error = _measurement - pose->estimate() * _point;}virtual void linearizeOplus() override {VertexPose *pose = static_cast<VertexPose *>(_vertices[0]);Sophus::SE3d T = pose->estimate();Eigen::Vector3d xyz_trans = T * _point;//新的雅可比矩阵设置方式//前3*3为单位阵_jacobianOplusXi.block<3, 3>(0, 0) = -Eigen::Matrix3d::Identity();//后3*3为T*xyz的反对称矩阵//Sophus::SO3d::hat() 反对称矩阵_jacobianOplusXi.block<3, 3>(0, 3) = Sophus::SO3d::hat(xyz_trans);}bool read(istream &in) {}bool write(ostream &out) const {}protected:Eigen::Vector3d _point;
};

BA函数调用g2o

void bundleAdjustment(const vector<Point3f> &pts1,const vector<Point3f> &pts2,Mat &R, Mat &t) {// 构建图优化，先设定g2otypedef g2o::BlockSolverX BlockSolverType;//最简单的方式，创建块。typedef g2o::LinearSolverDense<BlockSolverType::PoseMatrixType> LinearSolverType; // 线性求解器类型// 梯度下降方法，可以从GN, LM, DogLeg 中选auto solver = new g2o::OptimizationAlgorithmLevenberg(g2o::make_unique<BlockSolverType>(g2o::make_unique<LinearSolverType>()));g2o::SparseOptimizer optimizer;     // 图模型optimizer.setAlgorithm(solver);   // 设置求解器optimizer.setVerbose(true);       // 打开调试输出// vertexVertexPose *pose = new VertexPose(); // camera posepose->setId(0);//设置IDpose->setEstimate(Sophus::SE3d());//初始估计值optimizer.addVertex(pose);//优化器加入6维矩阵顶点// edgesfor (size_t i = 0; i < pts1.size(); i++) {EdgeProjectXYZRGBDPoseOnly *edge = new EdgeProjectXYZRGBDPoseOnly(Eigen::Vector3d(pts2[i].x, pts2[i].y, pts2[i].z));//其中一个点的坐标edge->setVertex(0, pose);//加入顶点edge->setMeasurement(Eigen::Vector3d(pts1[i].x, pts1[i].y, pts1[i].z));//另一个点坐标作为测量值edge->setInformation(Eigen::Matrix3d::Identity());//协方差矩阵optimizer.addEdge(edge);//加入边}chrono::steady_clock::time_point t1 = chrono::steady_clock::now();optimizer.initializeOptimization();//开始优化optimizer.optimize(10);chrono::steady_clock::time_point t2 = chrono::steady_clock::now();chrono::duration<double> time_used = chrono::duration_cast<chrono::duration<double>>(t2 - t1);cout << "optimization costs time: " << time_used.count() << " seconds." << endl;cout << endl << "after optimization:" << endl;cout << "T=\n" << pose->estimate().matrix() << endl;//输出整个矩阵// convert to cv::MatEigen::Matrix3d R_ = pose->estimate().rotationMatrix();//输出REigen::Vector3d t_ = pose->estimate().translation();//输出t//R转为Mat格式R = (Mat_<double>(3, 3) <<R_(0, 0), R_(0, 1), R_(0, 2),R_(1, 0), R_(1, 1), R_(1, 2),R_(2, 0), R_(2, 1), R_(2, 2));//t转为Mat格式t = (Mat_<double>(3, 1) << t_(0, 0), t_(1, 0), t_(2, 0));
}

此时就可以调用函数，计算3D-3D之间的转换矩阵。

得到3D点（深度信息）

//-- 读取图像Mat img_1 = imread(argv[1], CV_LOAD_IMAGE_COLOR);Mat img_2 = imread(argv[2], CV_LOAD_IMAGE_COLOR);
//匹配特征点vector<KeyPoint> keypoints_1, keypoints_2;vector<DMatch> matches;find_feature_matches(img_1, img_2, keypoints_1, keypoints_2, matches);cout << "一共找到了" << matches.size() << "组匹配点" << endl;// 建立3D点Mat depth1 = imread(argv[3], CV_LOAD_IMAGE_UNCHANGED);       // 深度图为16位无符号数，单通道图像Mat depth2 = imread(argv[4], CV_LOAD_IMAGE_UNCHANGED);       // 深度图为16位无符号数，单通道图像Mat K = (Mat_<double>(3, 3) << 520.9, 0, 325.1, 0, 521.0, 249.7, 0, 0, 1);//相机外参vector<Point3f> pts1, pts2;//遍历所有匹配好的二维特征点for (DMatch m:matches) {ushort d1 = depth1.ptr<unsigned short>(int(keypoints_1[m.queryIdx].pt.y))[int(keypoints_1[m.queryIdx].pt.x)];//根据RGBD得到特征点在第一张图中的深度ushort d2 = depth2.ptr<unsigned short>(int(keypoints_2[m.trainIdx].pt.y))[int(keypoints_2[m.trainIdx].pt.x)];if (d1 == 0 || d2 == 0)   // bad depthcontinue;//二维像素坐标转为相机坐标(u,v,1)Point2d p1 = pixel2cam(keypoints_1[m.queryIdx].pt, K);Point2d p2 = pixel2cam(keypoints_2[m.trainIdx].pt, K);//得到深度float dd1 = float(d1) / 5000.0;float dd2 = float(d2) / 5000.0;pts1.push_back(Point3f(p1.x * dd1, p1.y * dd1, dd1));pts2.push_back(Point3f(p2.x * dd2, p2.y * dd2, dd2));}

find_feature_matches函数

//找匹配的函数
void find_feature_matches(const Mat &img_1, const Mat &img_2,std::vector<KeyPoint> &keypoints_1,std::vector<KeyPoint> &keypoints_2,std::vector<DMatch> &matches) {//-- 初始化Mat descriptors_1, descriptors_2;// used in OpenCV3Ptr<FeatureDetector> detector = ORB::create();Ptr<DescriptorExtractor> descriptor = ORB::create();// 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");//-- 第一步:检测 Oriented FAST 角点位置detector->detect(img_1, keypoints_1);detector->detect(img_2, keypoints_2);//-- 第二步:根据角点位置计算 BRIEF 描述子descriptor->compute(img_1, keypoints_1, descriptors_1);descriptor->compute(img_2, keypoints_2, descriptors_2);//-- 第三步:对两幅图像中的BRIEF描述子进行匹配，使用 Hamming 距离vector<DMatch> match;// BFMatcher matcher ( NORM_HAMMING );matcher->match(descriptors_1, descriptors_2, match);//-- 第四步:匹配点对筛选double min_dist = 10000, max_dist = 0;//找出所有匹配之间的最小距离和最大距离, 即是最相似的和最不相似的两组点之间的距离for (int i = 0; i < descriptors_1.rows; i++) {double dist = match[i].distance;if (dist < min_dist) min_dist = dist;if (dist > max_dist) max_dist = dist;}printf("-- Max dist : %f \n", max_dist);printf("-- Min dist : %f \n", min_dist);//当描述子之间的距离大于两倍的最小距离时,即认为匹配有误.但有时候最小距离会非常小,设置一个经验值30作为下限.for (int i = 0; i < descriptors_1.rows; i++) {if (match[i].distance <= max(2 * min_dist, 30.0)) {matches.push_back(match[i]);}}
}