slam十四讲之第八讲optical_flow代码解析

slam十四讲之第八讲optical_flow代码解析

以下均在ubuntu20.04下完成，请大家批品指正

//
// Created by Xiang on 2017/12/19.
//

#include <opencv2/opencv.hpp>
#include <string>
#include <chrono>
#include <Eigen/Core>
#include <Eigen/Dense>

using namespace std;
using namespace cv;

string file_1 = "./LK1.png";  // first image
string file_2 = "./LK2.png";  // second image


// 定义各个模块模板
/// Optical flow tracker and interface  光流追踪
class OpticalFlowTracker {
public:
    OpticalFlowTracker(
        const Mat &img1_,
        const Mat &img2_,
        const vector<KeyPoint> &kp1_,
        vector<KeyPoint> &kp2_,
        vector<bool> &success_,
        bool inverse_ = true, bool has_initial_ = false) : //可逆   无初值
        img1(img1_), img2(img2_), kp1(kp1_), kp2(kp2_), success(success_), inverse(inverse_),
        has_initial(has_initial_) {}

    void calculateOpticalFlow(const Range &range);

private:
    const Mat &img1;
    const Mat &img2;
    const vector<KeyPoint> &kp1;
    vector<KeyPoint> &kp2;
    vector<bool> &success;
    bool inverse = true;
    bool has_initial = false;
};

/**
 * single level optical flow
 * @param [in] img1 the first image
 * @param [in] img2 the second image
 * @param [in] kp1 keypoints in img1
 * @param [in|out] kp2 keypoints in img2, if empty, use initial guess in kp1
 * @param [out] success true if a keypoint is tracked successfully
 * @param [in] inverse use inverse formulation?
 */
 //单层
void OpticalFlowSingleLevel(
    const Mat &img1,
    const Mat &img2,
    const vector<KeyPoint> &kp1,
    vector<KeyPoint> &kp2,
    vector<bool> &success,
    bool inverse = false,
    bool has_initial_guess = false
);

/**
 * multi level optical flow, scale of pyramid is set to 2 by default
 * the image pyramid will be create inside the function
 * @param [in] img1 the first pyramid
 * @param [in] img2 the second pyramid
 * @param [in] kp1 keypoints in img1
 * @param [out] kp2 keypoints in img2
 * @param [out] success true if a keypoint is tracked successfully
 * @param [in] inverse set true to enable inverse formulation
 */
 //多层
void OpticalFlowMultiLevel(
    const Mat &img1,
    const Mat &img2,
    const vector<KeyPoint> &kp1,
    vector<KeyPoint> &kp2,
    vector<bool> &success,
    bool inverse = false
);

/**
 * get a gray scale value from reference image (bi-linear interpolated)
 * @param img
 * @param x
 * @param y
 * @return the interpolated value of this pixel
 */
 //计算灰度值
inline float GetPixelValue(const cv::Mat &img, float x, float y) {
    // boundary check 边缘检测
    if (x < 0) x = 0;
    if (y < 0) y = 0;
    if (x >= img.cols) x = img.cols - 1;
    if (y >= img.rows) y = img.rows - 1;
    uchar *data = &img.data[int(y) * img.step + int(x)];//对应点的灰度值
    float xx = x - floor(x);// floor ：小于等于该值的最大整数
    float yy = y - floor(y);
    return float(   //双线性插值计算公式
        (1 - xx) * (1 - yy) * data[0] +
        xx * (1 - yy) * data[1] +
        (1 - xx) * yy * data[img.step] +
        xx * yy * data[img.step + 1]
    );
}


//第二大块  负责输出结果

int main(int argc, char **argv) {

    // images, note they are CV_8UC1, not CV_8UC3 单通道
    Mat img1 = imread(file_1, 0);
    Mat img2 = imread(file_2, 0);

    // key points, using GFTT here.角点追踪
    vector<KeyPoint> kp1;
    Ptr<GFTTDetector> detector = GFTTDetector::create(500, 0.01, 20); // maximum 500 keypoints 最多500个特征点 0.01表示关键点强度阈值，只保留大于该阈值的关键点（阈值 = 最强关键点强度 * qualityLevel） 20 决定关键点间的最小距离；
    detector->detect(img1, kp1);

    // now lets track these key points in the second image
    // first use single level LK in the validation picture 调用单层光流输出结果
    vector<KeyPoint> kp2_single;
    vector<bool> success_single;
    OpticalFlowSingleLevel(img1, img2, kp1, kp2_single, success_single);

    // then test multi-level LK 调用多层光流输出结果
    vector<KeyPoint> kp2_multi;
    vector<bool> success_multi;
    chrono::steady_clock::time_point t1 = chrono::steady_clock::now();
    OpticalFlowMultiLevel(img1, img2, kp1, kp2_multi, success_multi, true);
    chrono::steady_clock::time_point t2 = chrono::steady_clock::now();
    auto time_used = chrono::duration_cast<chrono::duration<double>>(t2 - t1);
    cout << "optical flow by gauss-newton: " << time_used.count() << endl;

    // use opencv's flow for validation 调用opencv输出结果
    vector<Point2f> pt1, pt2;
    for (auto &kp: kp1) pt1.push_back(kp.pt);
    vector<uchar> status;
    vector<float> error;
    t1 = chrono::steady_clock::now();
    cv::calcOpticalFlowPyrLK(img1, img2, pt1, pt2, status, error);
    t2 = chrono::steady_clock::now();
    time_used = chrono::duration_cast<chrono::duration<double>>(t2 - t1);
    cout << "optical flow by opencv: " << time_used.count() << endl;

    // plot the differences of those functions  画图
    Mat img2_single;
    cv::cvtColor(img2, img2_single, cv::COLOR_GRAY2BGR);//cv::COLOR_GRAY2BGR此处有改动。opencv版本不同不太一样
    for (int i = 0; i < kp2_single.size(); i++) {
        if (success_single[i]) {
            cv::circle(img2_single, kp2_single[i].pt, 2, cv::Scalar(0, 250, 0), 2);//半径 2 粗细 2 颜色(0, 250, 0)
            cv::line(img2_single, kp1[i].pt, kp2_single[i].pt, cv::Scalar(0, 250, 0));
        }
    }

    Mat img2_multi;
    cv::cvtColor(img2, img2_multi, cv::COLOR_GRAY2BGR);
    for (int i = 0; i < kp2_multi.size(); i++) {
        if (success_multi[i]) {
            cv::circle(img2_multi, kp2_multi[i].pt, 2, cv::Scalar(0, 250, 0), 2);
            cv::line(img2_multi, kp1[i].pt, kp2_multi[i].pt, cv::Scalar(0, 250, 0));
        }
    }

    Mat img2_CV;
    cv::cvtColor(img2, img2_CV, cv::COLOR_GRAY2BGR);
    for (int i = 0; i < pt2.size(); i++) {
        if (status[i]) {
            cv::circle(img2_CV, pt2[i], 2, cv::Scalar(0, 250, 0), 2);
            cv::line(img2_CV, pt1[i], pt2[i], cv::Scalar(0, 250, 0));
        }
    }

    cv::imshow("tracked single level", img2_single);
    cv::imshow("tracked multi level", img2_multi);
    cv::imshow("tracked by opencv", img2_CV);
    cv::waitKey(0);

    return 0;
}

//第三大块 负责实际计算供上面调用

void OpticalFlowSingleLevel(
    const Mat &img1,
    const Mat &img2,
    const vector<KeyPoint> &kp1,
    vector<KeyPoint> &kp2,
    vector<bool> &success,
    bool inverse, bool has_initial) {
    kp2.resize(kp1.size());
    success.resize(kp1.size());
    OpticalFlowTracker tracker(img1, img2, kp1, kp2, success, inverse, has_initial);
    parallel_for_(Range(0, kp1.size()),
                  std::bind(&OpticalFlowTracker::calculateOpticalFlow, &tracker, placeholders::_1));// //通过cv::parallel_for_并行调用了calculateOpticalFlow函数，循环次数为kp1.size()，传入了tracker数据。
}

void OpticalFlowTracker::calculateOpticalFlow(const Range &range) {
    // parameters
    int half_patch_size = 4;//窗口8*8
    int iterations = 10;//迭代10次
    for (size_t i = range.start; i < range.end; i++) {//长度为 kp1.size
        auto kp = kp1[i];
        double dx = 0, dy = 0; // dx,dy need to be estimated
        if (has_initial) {
            dx = kp2[i].pt.x - kp.pt.x;
            dy = kp2[i].pt.y - kp.pt.y;
        }

        double cost = 0, lastCost = 0;
        bool succ = true; // indicate if this point succeeded

        // Gauss-Newton iterations
        Eigen::Matrix2d H = Eigen::Matrix2d::Zero();    // hessian
        Eigen::Vector2d b = Eigen::Vector2d::Zero();    // bias
        Eigen::Vector2d J;  // jacobian
        for (int iter = 0; iter < iterations; iter++) {
            if (inverse == false) {
                H = Eigen::Matrix2d::Zero();
                b = Eigen::Vector2d::Zero();
            } else {//反向光流，H矩阵不变，只计算一次，每次迭代计算残差b
                // only reset b
                b = Eigen::Vector2d::Zero();
            }

            cost = 0;

            // compute cost and jacobian
            for (int x = -half_patch_size; x < half_patch_size; x++)
                for (int y = -half_patch_size; y < half_patch_size; y++) {
                    double error = GetPixelValue(img1, kp.pt.x + x, kp.pt.y + y) -
                                   GetPixelValue(img2, kp.pt.x + x + dx, kp.pt.y + y + dy);;  // Jacobian kp.pt.x为初值 一个矩阵的中心那种
                                   //dx(i,j) = [I(i+1,j) - I(i-1,j)]/2;
				    //dy(i,j) = [I(i,j+1) - I(i,j-1)]/2;
                    if (inverse == false) {
                        J = -1.0 * Eigen::Vector2d(
                            0.5 * (GetPixelValue(img2, kp.pt.x + dx + x + 1, kp.pt.y + dy + y) -
                                   GetPixelValue(img2, kp.pt.x + dx + x - 1, kp.pt.y + dy + y)),
                            0.5 * (GetPixelValue(img2, kp.pt.x + dx + x, kp.pt.y + dy + y + 1) -
                                   GetPixelValue(img2, kp.pt.x + dx + x, kp.pt.y + dy + y - 1))
                        );
                    } else if (iter == 0) {
                        // in inverse mode, J keeps same for all iterations 可逆模型 雅可比矩阵可认为不变
                        // NOTE this J does not change when dx, dy is updated, so we can store it and only compute error
                        J = -1.0 * Eigen::Vector2d(
                            0.5 * (GetPixelValue(img1, kp.pt.x + x + 1, kp.pt.y + y) -
                                   GetPixelValue(img1, kp.pt.x + x - 1, kp.pt.y + y)),
                            0.5 * (GetPixelValue(img1, kp.pt.x + x, kp.pt.y + y + 1) -
                                   GetPixelValue(img1, kp.pt.x + x, kp.pt.y + y - 1))
                        );
                    }
                    // compute H, b and set cost;
                    b += -error * J;
                    cost += error * error;
                    if (inverse == false || iter == 0) {
                        // also update H
                        H += J * J.transpose();
                    }
                }

            // compute update
            Eigen::Vector2d update = H.ldlt().solve(b);

            if (std::isnan(update[0])) {  //更新效果不好，更新停止
                // sometimes occurred when we have a black or white patch and H is irreversible
                cout << "update is nan" << endl;
                succ = false;
                break;
            }

            if (iter > 0 && cost > lastCost) { //误差变大，迭代停止
                break;
            }

            // update dx, dy
            dx += update[0];
            dy += update[1];
            lastCost = cost;
            succ = true;

            if (update.norm() < 1e-2) {  //更新的距离小于某个值迭代停止
                // converge
                break;
            }
        }

        success[i] = succ;

        // set kp2
        kp2[i].pt = kp.pt + Point2f(dx, dy);//算出优化后的kp2
    }
}
//多层光流 需要金字塔结构
void OpticalFlowMultiLevel(
    const Mat &img1,
    const Mat &img2,
    const vector<KeyPoint> &kp1,
    vector<KeyPoint> &kp2,
    vector<bool> &success,
    bool inverse) {

    // parameters
    int pyramids = 4;
    double pyramid_scale = 0.5;
    double scales[] = {1.0, 0.5, 0.25, 0.125};

    // create pyramids
    chrono::steady_clock::time_point t1 = chrono::steady_clock::now();
    vector<Mat> pyr1, pyr2; // image pyramids
    for (int i = 0; i < pyramids; i++) {
        if (i == 0) {
            pyr1.push_back(img1);//正常大小，直接存到pyr
            pyr2.push_back(img2);
        } else {
            Mat img1_pyr, img2_pyr;
            cv::resize(pyr1[i - 1], img1_pyr,
                       cv::Size(pyr1[i - 1].cols * pyramid_scale, pyr1[i - 1].rows * pyramid_scale));//把图片按照金字塔每层的尺寸进行存放
            cv::resize(pyr2[i - 1], img2_pyr,
                       cv::Size(pyr2[i - 1].cols * pyramid_scale, pyr2[i - 1].rows * pyramid_scale));
            pyr1.push_back(img1_pyr);
            pyr2.push_back(img2_pyr);
        }
    }
    chrono::steady_clock::time_point t2 = chrono::steady_clock::now();
    auto time_used = chrono::duration_cast<chrono::duration<double>>(t2 - t1);
    cout << "build pyramid time: " << time_used.count() << endl;

    // coarse-to-fine LK tracking in pyramids 金字塔中由粗到精的LK跟踪
    //定义顶层金字塔
    vector<KeyPoint> kp1_pyr, kp2_pyr;
    for (auto &kp:kp1) {
        auto kp_top = kp;//特征点放入顶层金字塔
        kp_top.pt *= scales[pyramids - 1];
        kp1_pyr.push_back(kp_top);
        kp2_pyr.push_back(kp_top);
    }

    for (int level = pyramids - 1; level >= 0; level--) {
        // from coarse to fine 有粗到细
        success.clear();
        t1 = chrono::steady_clock::now();
        OpticalFlowSingleLevel(pyr1[level], pyr2[level], kp1_pyr, kp2_pyr, success, inverse, true);//导入数据进行计算
        t2 = chrono::steady_clock::now();
        auto time_used = chrono::duration_cast<chrono::duration<double>>(t2 - t1);
        cout << "track pyr " << level << " cost time: " << time_used.count() << endl;

        if (level > 0) {
            for (auto &kp: kp1_pyr)
                kp.pt /= pyramid_scale;//根据层数改变尺度
            for (auto &kp: kp2_pyr)
                kp.pt /= pyramid_scale;
        }
    }
// kp2，找到了kp2和kp1的匹配点坐标
    for (auto &kp: kp2_pyr)
        kp2.push_back(kp);//在金字塔2中找到对应位置
}