ORBSLAM2源码学习（7） Initializer类

最新推荐文章于 2024-05-23 09:29:54 发布
最新推荐文章于 2024-05-23 09:29:54 发布
阅读量1.4k 收藏 2
点赞数
分类专栏： SLAM研究 文章标签： SLAM
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/u012936940/article/details/81414988
版权

Initializer类主要负责SLAM系统的初始化，在ORB中初始化非常重要，好的初始化是系统后续更少出错的基础。以单目为例，ORB中创建了一个初始化器，负责初始化工作。

void Tracking::MonocularInitialization()
{
    // 如果单目初始化器还没有被创建，则创建单目初始化器
    if(!mpInitializer)
    {
        // Set Reference Frame
        // 特征点数必须大于100
        if(mCurrentFrame.mvKeys.size()>100)
        {
            // 得到用于初始化的第一帧，初始化需要两帧
            mInitialFrame = Frame(mCurrentFrame);
            mLastFrame = Frame(mCurrentFrame);
            mvbPrevMatched.resize(mCurrentFrame.mvKeysUn.size());
            for(size_t i=0; i<mCurrentFrame.mvKeysUn.size(); i++)
                mvbPrevMatched[i]=mCurrentFrame.mvKeysUn[i].pt;

            if(mpInitializer)
                delete mpInitializer;

            // 由当前帧构造初始器 sigma:1.0 iterations:200
            mpInitializer =  new Initializer(mCurrentFrame,1.0,200);

            fill(mvIniMatches.begin(),mvIniMatches.end(),-1);

            return;
        }
    }
    else
    {
        // Try to initialize
        // 已经构造了初始化器，继续寻找用于初始化的第二帧
        // 如果当前帧特征点数大于100，则得到用于单目初始化的第二帧
        // 如果当前帧特征点太少，重新构造初始器
        // 因此只有连续两帧的特征点个数都大于100时，才能继续进行初始化
        if((int)mCurrentFrame.mvKeys.size()<=100)
        {
            delete mpInitializer;
            mpInitializer = static_cast<Initializer*>(NULL);
            fill(mvIniMatches.begin(),mvIniMatches.end(),-1);
            return;
        }

        // Find correspondences
        // 在mInitialFrame与mCurrentFrame中找匹配的特征点对
        // mvbPrevMatched为前一帧的特征点，存储了mInitialFrame中哪些点将进行接下来的匹配
        // mvIniMatches存储mInitialFrame,mCurrentFrame之间匹配的特征点
        ORBmatcher matcher(0.9,true);
        int nmatches = matcher.SearchForInitialization(mInitialFrame,mCurrentFrame,mvbPrevMatched,mvIniMatches,100);

        // Check if there are enough correspondences
        // 如果初始化的两帧之间的匹配点太少，重新初始化
        if(nmatches<100)
        {
            delete mpInitializer;
            mpInitializer = static_cast<Initializer*>(NULL);
            return;
        }

        cv::Mat Rcw; // Current Camera Rotation
        cv::Mat tcw; // Current Camera Translation
        vector<bool> vbTriangulated; // Triangulated Correspondences (mvIniMatches)

        // 通过H模型或F模型进行单目初始化，得到两帧间相对运动、初始MapPoints
        if(mpInitializer->Initialize(mCurrentFrame, mvIniMatches, Rcw, tcw, mvIniP3D, vbTriangulated))
        {
            // 删除无法进行三角化的匹配点
            for(size_t i=0, iend=mvIniMatches.size(); i<iend;i++)
            {
                if(mvIniMatches[i]>=0 && !vbTriangulated[i])
                {
                    mvIniMatches[i]=-1;
                    nmatches--;
                }
            }

            // Set Frame Poses
            // 将初始化的第一帧作为世界坐标系，因此第一帧变换矩阵为单位矩阵
            mInitialFrame.SetPose(cv::Mat::eye(4,4,CV_32F));
            cv::Mat Tcw = cv::Mat::eye(4,4,CV_32F);
            Rcw.copyTo(Tcw.rowRange(0,3).colRange(0,3));
            tcw.copyTo(Tcw.rowRange(0,3).col(3));
            mCurrentFrame.SetPose(Tcw);

            // 将三角化得到的3D点包装成MapPoints
            CreateInitialMapMonocular();
        }
    }
}

上面一段代码是跟踪mono_tum.cc 文件时会进入的一个函数，负责初始化工作，可以看到，ORB的初始化要求连续两帧的特征点都比较丰富且有足够匹配的特征点时才进行初始化工作，并且初始化时提取更多的特征点。

// 构造Frame
    if(mState==NOT_INITIALIZED || mState==NO_IMAGES_YET)// 没有成功初始化的前一个状态就是NO_IMAGES_YET，使用mpIniORBextractor提取更多特征点
        mCurrentFrame = Frame(mImGray,timestamp,mpIniORBextractor,mpORBVocabulary,mK,mDistCoef,mbf,mThDepth);
    else
        mCurrentFrame = Frame(mImGray,timestamp,mpORBextractorLeft,mpORBVocabulary,mK,mDistCoef,mbf,mThDepth);

下面是初始化这个类的完整代码，这个类不同其他类的是很多地方使用的方法比较固定，都是书上或者论文中固定的方法。

#include "Initializer.h"

#include "Thirdparty/DBoW2/DUtils/Random.h"

#include "Optimizer.h"
#include "ORBmatcher.h"

#include<thread>

namespace ORB_SLAM2
{

Initializer::Initializer(const Frame &ReferenceFrame, float sigma, int iterations)
{
    mK = ReferenceFrame.mK.clone();

    mvKeys1 = ReferenceFrame.mvKeysUn;

    mSigma = sigma;
    mSigma2 = sigma*sigma;
    mMaxIterations = iterations;
}

// 并行地计算基础矩阵和单应性矩阵，选取其中一个模型，恢复出最开始两帧之间的相对姿态以及点云
bool Initializer::Initialize(const Frame &CurrentFrame, const vector<int> &vMatches12, cv::Mat &R21, cv::Mat &t21,
                             vector<cv::Point3f> &vP3D, vector<bool> &vbTriangulated)
{
    // Fill structures with current keypoints and matches with reference frame
    // Reference Frame: 1, Current Frame: 2
    // Frame2 特征点
    mvKeys2 = CurrentFrame.mvKeysUn;

    mvMatches12.clear();
    mvMatches12.reserve(mvKeys2.size());
    // mvbMatched1记录每个特征点是否有匹配的特征点，
    mvbMatched1.resize(mvKeys1.size());

    for(size_t i=0, iend=vMatches12.size();i<iend; i++)
    {
        if(vMatches12[i]>=0)
        {
            mvMatches12.push_back(make_pair(i,vMatches12[i]));
            mvbMatched1[i]=true;
        }
        else
            mvbMatched1[i]=false;
    }

    // 匹配上的特征点的个数
    const int N = mvMatches12.size();

    // Indices for minimum set selection
    vector<size_t> vAllIndices;
    vAllIndices.reserve(N);
    vector<size_t> vAvailableIndices;

    for(int i=0; i<N; i++)
    {
        vAllIndices.push_back(i);
    }

    // Generate sets of 8 points for each RANSAC iteration
    // 在所有匹配特征点对中随机选择8对匹配特征点为一组，共选择mMaxIterations组
    // 用于FindHomography和FindFundamental求解
    // mMaxIterations:200
    mvSets = vector< vector<size_t> >(mMaxIterations,vector<size_t>(8,0));

    DUtils::Random::SeedRandOnce(0);

    for(int it=0; it<mMaxIterations; it++)
    {
        vAvailableIndices = vAllIndices;

        // Select a minimum set
        for(size_t j=0; j<8; j++)
        {
            // 产生0到N-1的随机数
            int randi = DUtils::Random::RandomInt(0,vAvailableIndices.size()-1);
            int idx = vAvailableIndices[randi];

            mvSets[it][j] = idx;

            vAvailableIndices[randi] = vAvailableIndices.back();
            vAvailableIndices.pop_back();
        }
    }

    // Launch threads to compute in parallel a fundamental matrix and a homography
    // 调用多线程分别用于计算fundamental和homography
    vector<bool> vbMatchesInliersH, vbMatchesInliersF;
    float SH, SF; // score for H and F
    cv::Mat H, F; // H and F

    // 计算homograpy和得分
    thread threadH(&Initializer::FindHomography,this,ref(vbMatchesInliersH), ref(SH), ref(H));
    // 计算fundamental和得分
    thread threadF(&Initializer::FindFundamental,this,ref(vbMatchesInliersF), ref(SF), ref(F));

    // Wait until both threads have finished
    threadH.join();
    threadF.join();

    // Compute ratio of scores
    // 计算得分比例，选取某个模型
    float RH = SH/(SH+SF);

    // Try to reconstruct from homography or fundamental depending on the ratio (0.40-0.45)
    // 从H矩阵或F矩阵中恢复R,t
    if(RH>0.40)
        return ReconstructH(vbMatchesInliersH,H,mK,R21,t21,vP3D,vbTriangulated,1.0,50);
    else //if(pF_HF>0.6)
        return ReconstructF(vbMatchesInliersF,F,mK,R21,t21,vP3D,vbTriangulated,1.0,50);

    return false;
}

// 假设场景为平面情况下通过前两帧求取Homography矩阵,并得到该模型的评分
void Initializer::FindHomography(vector<bool> &vbMatchesInliers, float &score, cv::Mat &H21)
{
    // Number of putative matches
    const int N = mvMatches12.size();

    // Normalize coordinates
    // 将特征点坐标归一化到均值为0，一阶绝对矩为1，归一化矩阵分别为T1、T2
    vector<cv::Point2f> vPn1, vPn2;
    cv::Mat T1, T2;
	// 归一化操作
    Normalize(mvKeys1,vPn1, T1);
    Normalize(mvKeys2,vPn2, T2);
    cv::Mat T2inv = T2.inv();

    // Best Results variables
    // 最佳的MatchesInliers与得分
    score = 0.0;
    vbMatchesInliers = vector<bool>(N,false);

    // Iteration variables
    vector<cv::Point2f> vPn1i(8);
    vector<cv::Point2f> vPn2i(8);
    cv::Mat H21i, H12i;
    // 每次RANSAC的MatchesInliers与得分
    vector<bool> vbCurrentInliers(N,false);
    float currentScore;

    // Perform all RANSAC iterations and save the solution with highest score
    for(int it=0; it<mMaxIterations; it++)
    {
        // Select a minimum set
        for(size_t j=0; j<8; j++)
        {
            int idx = mvSets[it][j];

            // vPn1i和vPn2i为匹配的特征点对的坐标
            vPn1i[j] = vPn1[mvMatches12[idx].first];
            vPn2i[j] = vPn2[mvMatches12[idx].second];
        }

		// 由归一化后的点计算单应矩阵
        cv::Mat Hn = ComputeH21(vPn1i,vPn2i);
        // 由归一化矩阵恢复原始的均值和尺度
        H21i = T2inv*Hn*T1;
        H12i = H21i.inv();

        // 利用重投影误差为当次RANSAC的结果评分
        currentScore = CheckHomography(H21i, H12i, vbCurrentInliers, mSigma);

        // 记录最优的vbMatchesInliers与score
        if(currentScore>score)
        {
            H21 = H21i.clone();
            vbMatchesInliers = vbCurrentInliers;
            score = currentScore;
        }
    }
}

// 假设场景为非平面情况下通过前两帧求取Fundamental矩阵,并得到该模型的评分
void Initializer::FindFundamental(vector<bool> &vbMatchesInliers, float &score, cv::Mat &F21)
{
    // Number of putative matches
    const int N = vbMatchesInliers.size();

    // Normalize coordinates
    vector<cv::Point2f> vPn1, vPn2;
    cv::Mat T1, T2;
    Normalize(mvKeys1,vPn1, T1);
    Normalize(mvKeys2,vPn2, T2);
    cv::Mat T2t = T2.t();

    // Best Results variables
    score = 0.0;
    vbMatchesInliers = vector<bool>(N,false);

    // Iteration variables
    vector<cv::Point2f> vPn1i(8);
    vector<cv::Point2f> vPn2i(8);
    cv::Mat F21i;
    vector<bool> vbCurrentInliers(N,false);
    float currentScore;

    // Perform all RANSAC iterations and save the solution with highest score
    for(int it=0; it<mMaxIterations; it++)
    {
        // Select a minimum set
        for(int j=0; j<8; j++)
        {
            int idx = mvSets[it][j];

            vPn1i[j] = vPn1[mvMatches12[idx].first];
            vPn2i[j] = vPn2[mvMatches12[idx].second];
        }

		// 由归一化后的坐标计算基础矩阵
        cv::Mat Fn = ComputeF21(vPn1i,vPn2i);
		// 由归一化矩阵恢复基础矩阵
        F21i = T2t*Fn*T1;

        // 利用重投影误差为当次RANSAC的结果评分
        currentScore = CheckFundamental(F21i, vbCurrentInliers, mSigma);

        if(currentScore>score)
        {
            F21 = F21i.clone();
            vbMatchesInliers = vbCurrentInliers;
            score = currentScore;
        }
    }
}

// |x'|     | h1 h2 h3 ||x|
// |y'| = a | h4 h5 h6 ||y|  x' = a H x, a为尺度因子
// |1 |     | h7 h8 h9 ||1|
// 使用DLT求解该模型
// x' = a H x 
// (x') 叉乘 (H x)  = 0
//  Ah = 0
// A = | 0  0  0 -x -y -1 xy' yy' y'|  h = | h1 h2 h3 h4 h5 h6 h7 h8 h9 |
//     |-x -y -1  0  0  0 xx' yx' x'|
// 通过SVD求解Ah = 0，A'A最小特征值对应的特征向量即为解
// Algorithm 4.1 in MVG
cv::Mat Initializer::ComputeH21(const vector<cv::Point2f> &vP1, const vector<cv::Point2f> &vP2)
{
    const int N = vP1.size();

    cv::Mat A(2*N,9,CV_32F); // 2N*9

    for(int i=0; i<N; i++)
    {
        const float u1 = vP1[i].x;
        const float v1 = vP1[i].y;
        const float u2 = vP2[i].x;
        const float v2 = vP2[i].y;

        A.at<float>(2*i,0) = 0.0;
        A.at<float>(2*i,1) = 0.0;
        A.at<float>(2*i,2) = 0.0;
        A.at<float>(2*i,3) = -u1;
        A.at<float>(2*i,4) = -v1;
        A.at<float>(2*i,5) = -1;
        A.at<float>(2*i,6) = v2*u1;
        A.at<float>(2*i,7) = v2*v1;
        A.at<float>(2*i,8) = v2;

        A.at<float>(2*i+1,0) = u1;
        A.at<float>(2*i+1,1) = v1;
        A.at<float>(2*i+1,2) = 1;
        A.at<float>(2*i+1,3) = 0.0;
        A.at<float>(2*i+1,4) = 0.0;
        A.at<float>(2*i+1,5) = 0.0;
        A.at<float>(2*i+1,6) = -u2*u1;
        A.at<float>(2*i+1,7) = -u2*v1;
        A.at<float>(2*i+1,8) = -u2;

    }

    cv::Mat u,w,vt;

    cv::SVDecomp(A,w,u,vt,cv::SVD::MODIFY_A | cv::SVD::FULL_UV);

    return vt.row(8).reshape(0, 3); 	// v的最后一列
}

// x'Fx = 0 整理可得：Af = 0
// A = | x'x x'y x' y'x y'y y' x y 1 |, f = | f1 f2 f3 f4 f5 f6 f7 f8 f9 |
// 通过SVD求解Af = 0，A'A最小特征值对应的特征向量即为解
// Algorithm 11.1 in MVG
cv::Mat Initializer::ComputeF21(const vector<cv::Point2f> &vP1,const vector<cv::Point2f> &vP2)
{
    const int N = vP1.size();

    cv::Mat A(N,9,CV_32F); // N*9

    for(int i=0; i<N; i++)
    {
        const float u1 = vP1[i].x;
        const float v1 = vP1[i].y;
        const float u2 = vP2[i].x;
        const float v2 = vP2[i].y;

        A.at<float>(i,0) = u2*u1;
        A.at<float>(i,1) = u2*v1;
        A.at<float>(i,2) = u2;
        A.at<float>(i,3) = v2*u1;
        A.at<float>(i,4) = v2*v1;
        A.at<float>(i,5) = v2;
        A.at<float>(i,6) = u1;
        A.at<float>(i,7) = v1;
        A.at<float>(i,8) = 1;
    }

    cv::Mat u,w,vt;

    cv::SVDecomp(A,w,u,vt,cv::SVD::MODIFY_A | cv::SVD::FULL_UV);

    cv::Mat Fpre = vt.row(8).reshape(0, 3); // v的最后一列

    cv::SVDecomp(Fpre,w,u,vt,cv::SVD::MODIFY_A | cv::SVD::FULL_UV);

    w.at<float>(2)=0; 		// 添加秩为2的约束，将第3个奇异值设为0

    return  u*cv::Mat::diag(w)*vt;
}

// 对给定的homography matrix打分
float Initializer::CheckHomography(const cv::Mat &H21, const cv::Mat &H12, vector<bool> &vbMatchesInliers, float sigma)
{   
    const int N = mvMatches12.size();
	
    const float h11 = H21.at<float>(0,0);
    const float h12 = H21.at<float>(0,1);
    const float h13 = H21.at<float>(0,2);
    const float h21 = H21.at<float>(1,0);
    const float h22 = H21.at<float>(1,1);
    const float h23 = H21.at<float>(1,2);
    const float h31 = H21.at<float>(2,0);
    const float h32 = H21.at<float>(2,1);
    const float h33 = H21.at<float>(2,2);

    const float h11inv = H12.at<float>(0,0);
    const float h12inv = H12.at<float>(0,1);
    const float h13inv = H12.at<float>(0,2);
    const float h21inv = H12.at<float>(1,0);
    const float h22inv = H12.at<float>(1,1);
    const float h23inv = H12.at<float>(1,2);
    const float h31inv = H12.at<float>(2,0);
    const float h32inv = H12.at<float>(2,1);
    const float h33inv = H12.at<float>(2,2);

    vbMatchesInliers.resize(N);

    float score = 0;

    // 基于卡方检验
    const float th = 5.991;

    const float invSigmaSquare = 1.0/(sigma*sigma);

    // N对特征匹配点
    for(int i=0; i<N; i++)
    {
        bool bIn = true;

        const cv::KeyPoint &kp1 = mvKeys1[mvMatches12[i].first];
        const cv::KeyPoint &kp2 = mvKeys2[mvMatches12[i].second];

        const float u1 = kp1.pt.x;
        const float v1 = kp1.pt.y;
        const float u2 = kp2.pt.x;
        const float v2 = kp2.pt.y;

        // Reprojection error in first image
        // 将图像2中的特征点单应到图像1中
        const float w2in1inv = 1.0/(h31inv*u2+h32inv*v2+h33inv);
        const float u2in1 = (h11inv*u2+h12inv*v2+h13inv)*w2in1inv;
        const float v2in1 = (h21inv*u2+h22inv*v2+h23inv)*w2in1inv;

        // 计算重投影误差
        const float squareDist1 = (u1-u2in1)*(u1-u2in1)+(v1-v2in1)*(v1-v2in1);

        // 根据方差归一化误差
        const float chiSquare1 = squareDist1*invSigmaSquare;

        if(chiSquare1>th)
            bIn = false;
        else
            score += th - chiSquare1;

        // Reprojection error in second image
        // 将图像1中的特征点单应到图像2中
        const float w1in2inv = 1.0/(h31*u1+h32*v1+h33);
        const float u1in2 = (h11*u1+h12*v1+h13)*w1in2inv;
        const float v1in2 = (h21*u1+h22*v1+h23)*w1in2inv;

        const float squareDist2 = (u2-u1in2)*(u2-u1in2)+(v2-v1in2)*(v2-v1in2);

        const float chiSquare2 = squareDist2*invSigmaSquare;

        if(chiSquare2>th)
            bIn = false;
        else
            score += th - chiSquare2;

        if(bIn)
            vbMatchesInliers[i]=true;
        else
            vbMatchesInliers[i]=false;
    }

    return score;
}

// 对给定的fundamental matrix打分
float Initializer::CheckFundamental(const cv::Mat &F21, vector<bool> &vbMatchesInliers, float sigma)
{
    const int N = mvMatches12.size();

    const float f11 = F21.at<float>(0,0);
    const float f12 = F21.at<float>(0,1);
    const float f13 = F21.at<float>(0,2);
    const float f21 = F21.at<float>(1,0);
    const float f22 = F21.at<float>(1,1);
    const float f23 = F21.at<float>(1,2);
    const float f31 = F21.at<float>(2,0);
    const float f32 = F21.at<float>(2,1);
    const float f33 = F21.at<float>(2,2);

    vbMatchesInliers.resize(N);

    float score = 0;

    const float th = 3.841;
    const float thScore = 5.991;

    const float invSigmaSquare = 1.0/(sigma*sigma);

    for(int i=0; i<N; i++)
    {
        bool bIn = true;

        const cv::KeyPoint &kp1 = mvKeys1[mvMatches12[i].first];
        const cv::KeyPoint &kp2 = mvKeys2[mvMatches12[i].second];

        const float u1 = kp1.pt.x;
        const float v1 = kp1.pt.y;
        const float u2 = kp2.pt.x;
        const float v2 = kp2.pt.y;

        // Reprojection error in second image
        // F21*x1可以算出x1在图像中x2对应的线l
        const float a2 = f11*u1+f12*v1+f13;
        const float b2 = f21*u1+f22*v1+f23;
        const float c2 = f31*u1+f32*v1+f33;

        // x2应该在l这条线上:x2点乘l = 0 
        const float num2 = a2*u2+b2*v2+c2;

        const float squareDist1 = num2*num2/(a2*a2+b2*b2); // 点到线的几何距离的平方

        const float chiSquare1 = squareDist1*invSigmaSquare;

        if(chiSquare1>th)
            bIn = false;
        else
            score += thScore - chiSquare1;

        // Reprojection error in second image
        const float a1 = f11*u2+f21*v2+f31;
        const float b1 = f12*u2+f22*v2+f32;
        const float c1 = f13*u2+f23*v2+f33;

        const float num1 = a1*u1+b1*v1+c1;

        const float squareDist2 = num1*num1/(a1*a1+b1*b1);

        const float chiSquare2 = squareDist2*invSigmaSquare;

        if(chiSquare2>th)
            bIn = false;
        else
            score += thScore - chiSquare2;

        if(bIn)
            vbMatchesInliers[i]=true;
        else
            vbMatchesInliers[i]=false;
    }

    return score;
}


//                          |0 -1  0|
// E = U Sigma V'   let W = |1  0  0|
//                          |0  0  1|
// 得到4个解 E = [R|t]
// R1 = UWV' R2 = UW'V' t1 = U3 t2 = -U3

// 从F恢复R t
// MVG 9.19
bool Initializer::ReconstructF(vector<bool> &vbMatchesInliers, cv::Mat &F21, cv::Mat &K,
                            cv::Mat &R21, cv::Mat &t21, vector<cv::Point3f> &vP3D, vector<bool> &vbTriangulated, float minParallax, int minTriangulated)
{
    int N=0;
    for(size_t i=0, iend = vbMatchesInliers.size() ; i<iend; i++)
        if(vbMatchesInliers[i])
            N++;

    // Compute Essential Matrix from Fundamental Matrix
	// 基本矩阵结合相机内参得到本质矩阵
    cv::Mat E21 = K.t()*F21*K;

    cv::Mat R1, R2, t;

    // Recover the 4 motion hypotheses
	// 分解本质矩阵
    DecomposeE(E21,R1,R2,t);  

    cv::Mat t1=t;
    cv::Mat t2=-t;

    // Reconstruct with the 4 hyphoteses and check
	// 检查四种解
    vector<cv::Point3f> vP3D1, vP3D2, vP3D3, vP3D4;
    vector<bool> vbTriangulated1,vbTriangulated2,vbTriangulated3, vbTriangulated4;
    float parallax1,parallax2, parallax3, parallax4;

    int nGood1 = CheckRT(R1,t1,mvKeys1,mvKeys2,mvMatches12,vbMatchesInliers,K, vP3D1, 4.0*mSigma2, vbTriangulated1, parallax1);
    int nGood2 = CheckRT(R2,t1,mvKeys1,mvKeys2,mvMatches12,vbMatchesInliers,K, vP3D2, 4.0*mSigma2, vbTriangulated2, parallax2);
    int nGood3 = CheckRT(R1,t2,mvKeys1,mvKeys2,mvMatches12,vbMatchesInliers,K, vP3D3, 4.0*mSigma2, vbTriangulated3, parallax3);
    int nGood4 = CheckRT(R2,t2,mvKeys1,mvKeys2,mvMatches12,vbMatchesInliers,K, vP3D4, 4.0*mSigma2, vbTriangulated4, parallax4);

    int maxGood = max(nGood1,max(nGood2,max(nGood3,nGood4)));

    R21 = cv::Mat();
    t21 = cv::Mat();

    // minTriangulated为可以三角化恢复三维点的个数
    int nMinGood = max(static_cast<int>(0.9*N),minTriangulated);

    int nsimilar = 0;
    if(nGood1>0.7*maxGood)
        nsimilar++;
    if(nGood2>0.7*maxGood)
        nsimilar++;
    if(nGood3>0.7*maxGood)
        nsimilar++;
    if(nGood4>0.7*maxGood)
        nsimilar++;

    // If there is not a clear winner or not enough triangulated points reject initialization
    // 四个结果中如果没有明显的最优结果，则返回失败
    if(maxGood<nMinGood || nsimilar>1)
    {
        return false;
    }

    // If best reconstruction has enough parallax initialize
    if(maxGood==nGood1)
    {
        if(parallax1>minParallax)
        {
            vP3D = vP3D1;
            vbTriangulated = vbTriangulated1;

            R1.copyTo(R21);
            t1.copyTo(t21);
            return true;
        }
    }else if(maxGood==nGood2)
    {
        if(parallax2>minParallax)
        {
            vP3D = vP3D2;
            vbTriangulated = vbTriangulated2;

            R2.copyTo(R21);
            t1.copyTo(t21);
            return true;
        }
    }else if(maxGood==nGood3)
    {
        if(parallax3>minParallax)
        {
            vP3D = vP3D3;
            vbTriangulated = vbTriangulated3;

            R1.copyTo(R21);
            t2.copyTo(t21);
            return true;
        }
    }else if(maxGood==nGood4)
    {
        if(parallax4>minParallax)
        {
            vP3D = vP3D4;
            vbTriangulated = vbTriangulated4;

            R2.copyTo(R21);
            t2.copyTo(t21);
            return true;
        }
    }

    return false;
}

// H恢复R,t
// 参考Faugeras SVD-based decomposition
bool Initializer::ReconstructH(vector<bool> &vbMatchesInliers, cv::Mat &H21, cv::Mat &K,
                      cv::Mat &R21, cv::Mat &t21, vector<cv::Point3f> &vP3D, vector<bool> &vbTriangulated, float minParallax, int minTriangulated)
{
    int N=0;
    for(size_t i=0, iend = vbMatchesInliers.size() ; i<iend; i++)
        if(vbMatchesInliers[i])
            N++;

    // We recover 8 motion hypotheses using the method of Faugeras et al.
    // Motion and structure from motion in a piecewise planar environment.
    // International Journal of Pattern Recognition and Artificial Intelligence, 1988

    // 所以将H矩阵由相机坐标系变换到图像坐标系
    cv::Mat invK = K.inv();
    cv::Mat A = invK*H21*K;

    cv::Mat U,w,Vt,V;
    cv::SVD::compute(A,w,U,Vt,cv::SVD::FULL_UV);
    V=Vt.t();

    float s = cv::determinant(U)*cv::determinant(Vt);

    float d1 = w.at<float>(0);
    float d2 = w.at<float>(1);
    float d3 = w.at<float>(2);

    // 检查特征值是否降序排列
    if(d1/d2<1.00001 || d2/d3<1.00001)
    {
        return false;
    }

    vector<cv::Mat> vR, vt, vn;
    vR.reserve(8);
    vt.reserve(8);
    vn.reserve(8);

    //n'=[x1 0 x3] 4 posibilities e1=e3=1, e1=1 e3=-1, e1=-1 e3=1, e1=e3=-1
    float aux1 = sqrt((d1*d1-d2*d2)/(d1*d1-d3*d3));
    float aux3 = sqrt((d2*d2-d3*d3)/(d1*d1-d3*d3));
    float x1[] = {aux1,aux1,-aux1,-aux1};
    float x3[] = {aux3,-aux3,aux3,-aux3};

    //case d'=d2
    float aux_stheta = sqrt((d1*d1-d2*d2)*(d2*d2-d3*d3))/((d1+d3)*d2);

    float ctheta = (d2*d2+d1*d3)/((d1+d3)*d2);
    float stheta[] = {aux_stheta, -aux_stheta, -aux_stheta, aux_stheta};

    for(int i=0; i<4; i++)
    {
        cv::Mat Rp=cv::Mat::eye(3,3,CV_32F);
        Rp.at<float>(0,0)=ctheta;
        Rp.at<float>(0,2)=-stheta[i];
        Rp.at<float>(2,0)=stheta[i];
        Rp.at<float>(2,2)=ctheta;

        cv::Mat R = s*U*Rp*Vt;
        vR.push_back(R);

        cv::Mat tp(3,1,CV_32F);
        tp.at<float>(0)=x1[i];
        tp.at<float>(1)=0;
        tp.at<float>(2)=-x3[i];
        tp*=d1-d3;

        cv::Mat t = U*tp;
        vt.push_back(t/cv::norm(t));

        cv::Mat np(3,1,CV_32F);
        np.at<float>(0)=x1[i];
        np.at<float>(1)=0;
        np.at<float>(2)=x3[i];

        cv::Mat n = V*np;
        if(n.at<float>(2)<0)
            n=-n;
        vn.push_back(n);
    }

    float aux_sphi = sqrt((d1*d1-d2*d2)*(d2*d2-d3*d3))/((d1-d3)*d2);

    float cphi = (d1*d3-d2*d2)/((d1-d3)*d2);
    float sphi[] = {aux_sphi, -aux_sphi, -aux_sphi, aux_sphi};

    for(int i=0; i<4; i++)
    {
        cv::Mat Rp=cv::Mat::eye(3,3,CV_32F);
        Rp.at<float>(0,0)=cphi;
        Rp.at<float>(0,2)=sphi[i];
        Rp.at<float>(1,1)=-1;
        Rp.at<float>(2,0)=sphi[i];
        Rp.at<float>(2,2)=-cphi;

        cv::Mat R = s*U*Rp*Vt;
        vR.push_back(R);

        cv::Mat tp(3,1,CV_32F);
        tp.at<float>(0)=x1[i];
        tp.at<float>(1)=0;
        tp.at<float>(2)=x3[i];
        tp*=d1+d3;

        cv::Mat t = U*tp;
        vt.push_back(t/cv::norm(t));

        cv::Mat np(3,1,CV_32F);
        np.at<float>(0)=x1[i];
        np.at<float>(1)=0;
        np.at<float>(2)=x3[i];

        cv::Mat n = V*np;
        if(n.at<float>(2)<0)
            n=-n;
        vn.push_back(n);
    }


    int bestGood = 0;
    int secondBestGood = 0;    
    int bestSolutionIdx = -1;
    float bestParallax = -1;
    vector<cv::Point3f> bestP3D;
    vector<bool> bestTriangulated;

    // Instead of applying the visibility constraints proposed in the Faugeras' paper (which could fail for points seen with low parallax)
    // We reconstruct all hypotheses and check in terms of triangulated points and parallax
    for(size_t i=0; i<8; i++)
    {
        float parallaxi;
        vector<cv::Point3f> vP3Di;
        vector<bool> vbTriangulatedi;
        int nGood = CheckRT(vR[i],vt[i],mvKeys1,mvKeys2,mvMatches12,vbMatchesInliers,K,vP3Di, 4.0*mSigma2, vbTriangulatedi, parallaxi);

        // 保留最优的和次优的
        if(nGood>bestGood)
        {
            secondBestGood = bestGood;
            bestGood = nGood;
            bestSolutionIdx = i;
            bestParallax = parallaxi;
            bestP3D = vP3Di;
            bestTriangulated = vbTriangulatedi;
        }
        else if(nGood>secondBestGood)
        {
            secondBestGood = nGood;
        }
    }


    if(secondBestGood<0.75*bestGood && bestParallax>=minParallax && bestGood>minTriangulated && bestGood>0.9*N)
    {
        vR[bestSolutionIdx].copyTo(R21);
        vt[bestSolutionIdx].copyTo(t21);
        vP3D = bestP3D;
        vbTriangulated = bestTriangulated;

        return true;
    }

    return false;
}

// 三角化
// MVG - 12.2
// 已知匹配特征点对{x x'}和相机矩阵{P P'}, 估计三维点 X
// x' = P'X  x = PX
//                         |X|
// |x|     |p1 p2  p3  p4 ||Y|     |x|    |--p0--||.|
// |y| = a |p5 p6  p7  p8 ||Z| ===>|y| = a|--p1--||X|
// |z|     |p9 p10 p11 p12||1|     |z|    |--p2--||.|
// 采用DLT的方法：x叉乘PX = 0
// |yp2 -  p1|     |0|
// |p0 -  xp2| X = |0|
// |xp1 - yp0|     |0|
// 两个点:
// |yp2   -  p1  |     |0|
// |p0    -  xp2 | X = |0| ===> AX = 0
// |y'p2' -  p1' |     |0|
// |p0'   - x'p2'|     |0| 
void Initializer::Triangulate(const cv::KeyPoint &kp1, const cv::KeyPoint &kp2, const cv::Mat &P1, const cv::Mat &P2, cv::Mat &x3D)
{
    cv::Mat A(4,4,CV_32F);

    A.row(0) = kp1.pt.x*P1.row(2)-P1.row(0);
    A.row(1) = kp1.pt.y*P1.row(2)-P1.row(1);
    A.row(2) = kp2.pt.x*P2.row(2)-P2.row(0);
    A.row(3) = kp2.pt.y*P2.row(2)-P2.row(1);

    cv::Mat u,w,vt;
    cv::SVD::compute(A,w,u,vt,cv::SVD::MODIFY_A| cv::SVD::FULL_UV);
    x3D = vt.row(3).t();
    x3D = x3D.rowRange(0,3)/x3D.at<float>(3);
}

// 归一化特征点
void Initializer::Normalize(const vector<cv::KeyPoint> &vKeys, vector<cv::Point2f> &vNormalizedPoints, cv::Mat &T)
{
    float meanX = 0;
    float meanY = 0;
    const int N = vKeys.size();

    vNormalizedPoints.resize(N);

    for(int i=0; i<N; i++)
    {
        meanX += vKeys[i].pt.x;
        meanY += vKeys[i].pt.y;
    }

    meanX = meanX/N;
    meanY = meanY/N;

    float meanDevX = 0;
    float meanDevY = 0;

    // 将所有vKeys点减去中心坐标，使x坐标和y坐标均值分别为0
    for(int i=0; i<N; i++)
    {
        vNormalizedPoints[i].x = vKeys[i].pt.x - meanX;
        vNormalizedPoints[i].y = vKeys[i].pt.y - meanY;

        meanDevX += fabs(vNormalizedPoints[i].x);
        meanDevY += fabs(vNormalizedPoints[i].y);
    }

    meanDevX = meanDevX/N;
    meanDevY = meanDevY/N;

    float sX = 1.0/meanDevX;
    float sY = 1.0/meanDevY;

    // 将x坐标和y坐标分别进行缩放，使得x坐标和y坐标的一阶绝对矩分别为1
    for(int i=0; i<N; i++)
    {
        vNormalizedPoints[i].x = vNormalizedPoints[i].x * sX;
        vNormalizedPoints[i].y = vNormalizedPoints[i].y * sY;
    }

    T = cv::Mat::eye(3,3,CV_32F);
    T.at<float>(0,0) = sX;
    T.at<float>(1,1) = sY;
    T.at<float>(0,2) = -meanX*sX;
    T.at<float>(1,2) = -meanY*sY;
}

// 检查每一组解
int Initializer::CheckRT(const cv::Mat &R, const cv::Mat &t, const vector<cv::KeyPoint> &vKeys1, const vector<cv::KeyPoint> &vKeys2,
                       const vector<Match> &vMatches12, vector<bool> &vbMatchesInliers,
                       const cv::Mat &K, vector<cv::Point3f> &vP3D, float th2, vector<bool> &vbGood, float &parallax)
{
    // Calibration parameters
    const float fx = K.at<float>(0,0);
    const float fy = K.at<float>(1,1);
    const float cx = K.at<float>(0,2);
    const float cy = K.at<float>(1,2);

    vbGood = vector<bool>(vKeys1.size(),false);
    vP3D.resize(vKeys1.size());

    vector<float> vCosParallax;
    vCosParallax.reserve(vKeys1.size());

    // Camera 1 Projection Matrix K[I|0]
    // 以第一个相机的光心作为世界坐标系
    cv::Mat P1(3,4,CV_32F,cv::Scalar(0));
    K.copyTo(P1.rowRange(0,3).colRange(0,3));
    // 第一个相机的光心在世界下的坐标
    cv::Mat O1 = cv::Mat::zeros(3,1,CV_32F);

    // Camera 2 Projection Matrix K[R|t]
    // 第二个相机的投影矩阵
    cv::Mat P2(3,4,CV_32F);
    R.copyTo(P2.rowRange(0,3).colRange(0,3));
    t.copyTo(P2.rowRange(0,3).col(3));
    P2 = K*P2;
    // 第二个相机的光心在世界系下的坐标
    cv::Mat O2 = -R.t()*t;

    int nGood=0;

    for(size_t i=0, iend=vMatches12.size();i<iend;i++)
    {
        if(!vbMatchesInliers[i])
            continue;

        // kp1和kp2是匹配特征点
        const cv::KeyPoint &kp1 = vKeys1[vMatches12[i].first];
        const cv::KeyPoint &kp2 = vKeys2[vMatches12[i].second];
        cv::Mat p3dC1;

        // 利用三角法恢复三维点p3dC1
        Triangulate(kp1,kp2,P1,P2,p3dC1);
		// 坐标是否有效
        if(!isfinite(p3dC1.at<float>(0)) || !isfinite(p3dC1.at<float>(1)) || !isfinite(p3dC1.at<float>(2)))
        {
            vbGood[vMatches12[i].first]=false;
            continue;
        }

        // Check parallax
        // 计算视差角余弦值
		// 相机1至3D点的向量和距离
        cv::Mat normal1 = p3dC1 - O1;
        float dist1 = cv::norm(normal1);
		// 相机2至3D点的向量和距离
        cv::Mat normal2 = p3dC1 - O2;
        float dist2 = cv::norm(normal2);

        float cosParallax = normal1.dot(normal2)/(dist1*dist2);

        // 判断3D点是否在两个摄像头前方
        // Check depth in front of first camera (only if enough parallax, as "infinite" points can easily go to negative depth)
        // 3D点深度为负，在第一个摄像头后方，淘汰
        if(p3dC1.at<float>(2)<=0 && cosParallax<0.99998)
            continue;

        // Check depth in front of second camera (only if enough parallax, as "infinite" points can easily go to negative depth)
        // 3D点深度为负，在第二个摄像头后方，淘汰
        cv::Mat p3dC2 = R*p3dC1+t;

        if(p3dC2.at<float>(2)<=0 && cosParallax<0.99998)
            continue;

        // Check reprojection error in first image
        // 计算3D点在第一个图像上的投影误差
        float im1x, im1y;
        float invZ1 = 1.0/p3dC1.at<float>(2);
        im1x = fx*p3dC1.at<float>(0)*invZ1+cx;
        im1y = fy*p3dC1.at<float>(1)*invZ1+cy;

        float squareError1 = (im1x-kp1.pt.x)*(im1x-kp1.pt.x)+(im1y-kp1.pt.y)*(im1y-kp1.pt.y);

        // 重投影误差太大，淘汰
        // 一般视差角比较小时重投影误差比较大
        if(squareError1>th2)
            continue;

        // Check reprojection error in second image
        // 计算3D点在第二个图像上的投影误差
        float im2x, im2y;
        float invZ2 = 1.0/p3dC2.at<float>(2);
        im2x = fx*p3dC2.at<float>(0)*invZ2+cx;
        im2y = fy*p3dC2.at<float>(1)*invZ2+cy;

        float squareError2 = (im2x-kp2.pt.x)*(im2x-kp2.pt.x)+(im2y-kp2.pt.y)*(im2y-kp2.pt.y);

        // 重投影误差太大，跳过淘汰
        if(squareError2>th2)
            continue;

        // 统计经过检验的3D点个数，记录3D点视差角
        vCosParallax.push_back(cosParallax);
        vP3D[vMatches12[i].first] = cv::Point3f(p3dC1.at<float>(0),p3dC1.at<float>(1),p3dC1.at<float>(2));
        nGood++;

        if(cosParallax<0.99998)
            vbGood[vMatches12[i].first]=true;
    }

    // 得到3D点中较大的视差角
    if(nGood>0)
    {
        // 从小到大排序
        sort(vCosParallax.begin(),vCosParallax.end());

        // 取一个较大的视差角
        size_t idx = min(50,int(vCosParallax.size()-1));
        parallax = acos(vCosParallax[idx])*180/CV_PI;
    }
    else
        parallax=0;

    return nGood;
}

// F矩阵通过结合内参可以得到Essential矩阵，分解E矩阵将得到4组解 
// MVG 9.19
void Initializer::DecomposeE(const cv::Mat &E, cv::Mat &R1, cv::Mat &R2, cv::Mat &t)
{
    cv::Mat u,w,vt;
    cv::SVD::compute(E,w,u,vt);

    u.col(2).copyTo(t);
    t=t/cv::norm(t);

    cv::Mat W(3,3,CV_32F,cv::Scalar(0));
    W.at<float>(0,1)=-1;
    W.at<float>(1,0)=1;
    W.at<float>(2,2)=1;

    R1 = u*W*vt;
    if(cv::determinant(R1)<0) // 旋转矩阵有行列式为1的约束
        R1=-R1;

    R2 = u*W.t()*vt;
    if(cv::determinant(R2)<0)
        R2=-R2;
}

} //namespace ORB_SLAM

 

Rap_God
关注
  • 0
    点赞
  • 踩
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
读懂ORBSLAM2——单目初始化器Initializer
xiaohu的博客
12-16 1322
参考： 一步步带你看懂orbslam2源码–单目初始化(三) 认真的虎ORBSLAM2源码解读(七)：单目初始化器Initializer 地图初始化的目的是计算两帧图像之间的相对位姿来三角化一组初始的地图云点。本文算法提出并行计算两个几何模型，一个是面向平面视图的单映矩阵，另一个是面向非平面视图的基础矩阵。然后，采用启发式的方法选择模型，并使用所选的模型从两图像的相对位姿中对地图点云进行重构。...
ORBSLAM2学习笔记4(Initializer)
Bobsweetie的专栏
07-03 314
单目初始化的类 Initializer.h /** * This file is part of ORB-SLAM2. * * Copyright (C) 2014-2016 Raúl Mur-Artal <raulmur at unizar dot es> (University of Zaragoza) * For more information see <https://github.com/raulmur/ORB_SLAM2> * * ORB-SLAM2 is free s
ORB-SLAM2从理论到代码实现（六）：Tracking程序详解（上）
最新发布
人无远虑，必有近忧
05-23 2071
Tracking线程流程框图：各流程对应的主要函数。
ORB-SLAM2代码详解06: 单目初始化器Initializer
ncepu_Chen的博客
05-14 3694
ORB-SLAM2代码详解06: 单目初始化器Initializer各成员变量/函数初始化函数`Initialize()`计算基础矩阵`F`和单应矩阵`H`RANSAC算法计算基础矩阵`F`: `FindFundamental()`八点法计算`F`矩阵: `ComputeF21()`计算单应矩阵`H`: `FindHomography()`卡方检验计算置信度得分: `CheckFundamental()`、`CheckHomography()`归一化: `Normalize()`使用基础矩阵`F`和单应矩阵
ORB-SLAM2 ---- Initializer::Normalize函数
qq_41694024的博客
11-12 535
归一化的思想及归一化代码解读
+ (void)initialize方法解释
fspinach的专栏
09-09 555
initialize 方法在类第一次初始化时调用，且仅调用一次。 下面是实例测试： 在各个测试类中实现initialize 方法。 + (void)initialize { NSLog(@"%s",__FUNCTION__); } 场景一： 只创建父类Parent - (void)viewDidLoad { [super viewDidLoad]; // Do any additional setup after loading the view. [
lecture5_2-文本特征提取1
08-08
本文将探讨三种主要的文本特征提取方法：TF-IDF、Word Embedding 和 Word2Vec，以及它们在深度学习文本分类任务中的应用，如卷积神经网络（CNN）和循环神经网络（RNN）。 首先，TF-IDF 是一种经典的文本特征表示...
Springboot Initializer
09-01
内网中连接不上https://start.spring.io，搭建\https://start.spring.io一样的服务器。 initializr-service-0.7.0.BUILD-SNAPSHOT.jar
spring initializer（Spring 版 + Aliyun 版）
04-25
Spring Initializer（Spring 版 + Aliyun 版） JDK Require：JDK 17 启动命令：java -jar xxx.jar 1、Spring 版：官网 https://start.spring.io/ -> 本地 http://localhost:8080/ 2、Aliyun 版：官网 ...
自己搭建SpringBoot initializer 服务器
06-15
由于https://start.spring.io/ 网站访问不稳定或者超时现象,本次搭建0.12.0 最新 版本 ，springboot ...已经打包的jar无须下载源码重新搭建，启动后访问 http://127.0.0.1:8080 适用开发工具IDEA .eclipse ，STS 等
TensorFlow 深度学习 实践（2）
12-21
在TensorFlow深度学习实践中，了解其编程模型和数据模型是至关重要的。TensorFlow是一个强大的开源库，用于构建和训练各种机器学习模型，尤其是深度学习模型。以下是对标题和描述中涉及知识点的详细说明： **一、...
SLAM基础问题总结（2）
落叶知秋了哟的博客
08-28 1060
1、什么是对极约束？基础矩阵F的推导过程，F的秩
单目初始化（二）：初始化函数
weixin_39061796的博客
07-23 462
本次主要讲解单目初始化中的初始化器中的初始化函数Initializer::Initialize 函数的参数如下 bool Initializer::Initialize(const Frame &CurrentFrame, // 当前帧 const vector<int> &vMatches12, // 当前帧和参考帧图像中特征点的匹配关系
ORB_SLAM2 源码解析 ORB_SLAM2简介（一）
m0_58173801的博客
08-29 1万+
一、ORB_SLAM2的特点 1、ORB_SLAM2是首个支持单目、双目和RGB-D相机的完整开源SLAM方案，能够实现地图重用，回环检测和重新定位的功能。 2、能够在GPU上进行实时工作，比如手机、无人机、汽车。 3、特征点法的巅峰之作，定位精度非常高。 4、能够实时计算处相机的位姿，并生成场景的稀疏三维重建地图。 二、算法流程框架 ORB-SLAM整体流程如下图所示 它主要有三个线程组成：跟踪、Local Mapping（又称小图）、Loop Closing（又称大图...
ORB-SLAM2源码逐行解析系列（一）：单目模式整体流程
LDST_CSDN的博客
05-15 1019
public :// 这个枚举类型用于 表示本系统所使用的传感器类型(SLAM的运行模式) enum eSensor {public :// 构造函数，用来初始化整个系统。System(const string & strVocFile , //指定ORB字典文件的路径 const string & strSettingsFile , //指定配置文件的路径 const eSensor sensor , //指定所使用的传感器类型 const bool bUseViewer = true);
ORB-SLAM2源码解读
weixin_46101998的博客
11-01 408
在这一优化过程中，我们实际上把上一帧之前建立的那些地图点作为了先验的信息，通过相机模型把这些地图点转化到当前帧的平面上，作为。
4. OpenCV 4.2.0 Mat - 基本图像容器（OpenCV 官方文档翻译）
Mr. Stone's Blog
04-29 631
官方文档链接：https://docs.opencv.org/4.2.0/d6/d6d/tutorial_mat_the_basic_image_container.html 目标 (Goal) 我们有多种方式可以从现实世界中获取数字图像：数字照相机，扫描仪，计算机断层扫描和磁共振成像等等。在任何情况下，我们看到的都是图像。然而，当我们将其转换为数字设备时，我们记录的是图像中每个点的数值。 例...
OpenCV Mat类详解和用法
热门推荐
AI吃大瓜的博客
04-13 15万+
OpenCV Mat类详解和用法      我们有多种方法可以获得从现实世界的数字图像：数码相机、扫描仪、计算机体层摄影或磁共振成像就是其中的几种。在每种情况下我们（人类）看到了什么是图像。但是，转换图像到我们的数字设备时我们的记录是图像的每个点的数值。       例如在上图中你可以看到车的镜子只是一个包含所有强度值的像素点矩阵。现在，我们如何获取和存储像素值可能根据最适合我们的需要而变...
OpenCV Mat矩阵(图像Mat)初始化及访问方法
duiwangxiaomi的博客
06-20 7万+
文章详细介绍了OpenCV Mat矩阵(图像Mat)初始化及访问方法
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值