RGB-D直接法

RGB-D直接法有下列分类:

  1. 感兴趣的P来自于稀疏关键点,通常一幅图像使用数百个到上千个特征点,这些特征点检测出来会耗费一定的时间,但是不计算描述子,而且使用的像素点很少,因此速度很快,可以在CPU上运行,但如果图像变化过于剧烈就会出现大概率丢失特征点的问题
  2. 感兴趣的P来自于所有有图像梯度的像素点,也就是是图像里的边界,由于像素梯度为0不会对估计造成任何影响,所以可以只考虑梯度明显的地方放弃梯度不明显的地方,这称为Semi-Dense直接法,可以重构一个半稠密结构
  3. 感兴趣的P来自于整副图像,由于计算资源消耗太大,不能够在CPU上运行

稀疏直接法的实验
数据部分介绍
同样是TUM数据集(9张对齐的深度图和彩色图,以及对齐的信息)
RGB-D直接法_第1张图片
RGB-D直接法_第2张图片
Cpp

#include 
#include 
#include 
#include 
#include 
#include 
#include 

#include 
#include 
#include 
#include 

#include 
#include 
#include 
#include 
#include 
#include 

using namespace std;
using namespace g2o;

/********************************************
 * 本节演示了RGBD上的稀疏直接法 
 ********************************************/

// 一次测量的值,包括一个世界坐标系下三维点与一个灰度值
struct Measurement
{
    Measurement ( Eigen::Vector3d p, float g ) : pos_world ( p ), grayscale ( g ) {}
    Eigen::Vector3d pos_world;
    float grayscale;
};

inline Eigen::Vector3d project2Dto3D ( int x, int y, int d, float fx, float fy, float cx, float cy, float scale )
{
    float zz = float ( d ) /scale;
    float xx = zz* ( x-cx ) /fx;
    float yy = zz* ( y-cy ) /fy;
    return Eigen::Vector3d ( xx, yy, zz );
}

inline Eigen::Vector2d project3Dto2D ( float x, float y, float z, float fx, float fy, float cx, float cy )
{
    float u = fx*x/z+cx;
    float v = fy*y/z+cy;
    return Eigen::Vector2d ( u,v );
}

// 直接法估计位姿
// 输入:测量值(空间点的灰度),新的灰度图,相机内参; 输出:相机位姿
// 返回:true为成功,false失败
bool poseEstimationDirect ( const vector<Measurement>& measurements, cv::Mat* gray, Eigen::Matrix3f& intrinsics, Eigen::Isometry3d& Tcw );


// project a 3d point into an image plane, the error is photometric error
// an unary edge with one vertex SE3Expmap (the pose of camera)
class EdgeSE3ProjectDirect: public BaseUnaryEdge< 1, double, VertexSE3Expmap>
{
public:
    EIGEN_MAKE_ALIGNED_OPERATOR_NEW

    EdgeSE3ProjectDirect() {}

    EdgeSE3ProjectDirect ( Eigen::Vector3d point, float fx, float fy, float cx, float cy, cv::Mat* image )
        : x_world_ ( point ), fx_ ( fx ), fy_ ( fy ), cx_ ( cx ), cy_ ( cy ), image_ ( image )
    {}

    virtual void computeError()
    {
        const VertexSE3Expmap* v  =static_cast<const VertexSE3Expmap*> ( _vertices[0] );
        Eigen::Vector3d x_local = v->estimate().map ( x_world_ );
        float x = x_local[0]*fx_/x_local[2] + cx_;
        float y = x_local[1]*fy_/x_local[2] + cy_;
        // check x,y is in the image
        if ( x-4<0 || ( x+4 ) >image_->cols || ( y-4 ) <0 || ( y+4 ) >image_->rows )
        {
            _error ( 0,0 ) = 0.0;
            this->setLevel ( 1 );
        }
        else
        {
            _error ( 0,0 ) = getPixelValue ( x,y ) - _measurement;
        }
    }

    // plus in manifold
    virtual void linearizeOplus( )
    {
        if ( level() == 1 )
        {
            _jacobianOplusXi = Eigen::Matrix<double, 1, 6>::Zero();
            return;
        }
        VertexSE3Expmap* vtx = static_cast<VertexSE3Expmap*> ( _vertices[0] );
        Eigen::Vector3d xyz_trans = vtx->estimate().map ( x_world_ );   // q in book

        double x = xyz_trans[0];
        double y = xyz_trans[1];
        double invz = 1.0/xyz_trans[2];
        double invz_2 = invz*invz;

        float u = x*fx_*invz + cx_;
        float v = y*fy_*invz + cy_;

        // jacobian from se3 to u,v
        // NOTE that in g2o the Lie algebra is (\omega, \epsilon), where \omega is so(3) and \epsilon the translation
        Eigen::Matrix<double, 2, 6> jacobian_uv_ksai;

        jacobian_uv_ksai ( 0,0 ) = - x*y*invz_2 *fx_;
        jacobian_uv_ksai ( 0,1 ) = ( 1+ ( x*x*invz_2 ) ) *fx_;
        jacobian_uv_ksai ( 0,2 ) = - y*invz *fx_;
        jacobian_uv_ksai ( 0,3 ) = invz *fx_;
        jacobian_uv_ksai ( 0,4 ) = 0;
        jacobian_uv_ksai ( 0,5 ) = -x*invz_2 *fx_;

        jacobian_uv_ksai ( 1,0 ) = - ( 1+y*y*invz_2 ) *fy_;
        jacobian_uv_ksai ( 1,1 ) = x*y*invz_2 *fy_;
        jacobian_uv_ksai ( 1,2 ) = x*invz *fy_;
        jacobian_uv_ksai ( 1,3 ) = 0;
        jacobian_uv_ksai ( 1,4 ) = invz *fy_;
        jacobian_uv_ksai ( 1,5 ) = -y*invz_2 *fy_;

        Eigen::Matrix<double, 1, 2> jacobian_pixel_uv;

        jacobian_pixel_uv ( 0,0 ) = ( getPixelValue ( u+1,v )-getPixelValue ( u-1,v ) ) /2;
        jacobian_pixel_uv ( 0,1 ) = ( getPixelValue ( u,v+1 )-getPixelValue ( u,v-1 ) ) /2;

        _jacobianOplusXi = jacobian_pixel_uv*jacobian_uv_ksai;
    }

    // dummy read and write functions because we don't care...
    virtual bool read ( std::istream& in ) {}
    virtual bool write ( std::ostream& out ) const {}

protected:
    // get a gray scale value from reference image (bilinear interpolated)
    inline float getPixelValue ( float x, float y )
    {
        uchar* data = & image_->data[ int ( y ) * image_->step + int ( x ) ];
        float xx = x - floor ( x );
        float yy = y - floor ( y );
        return float (
                   ( 1-xx ) * ( 1-yy ) * data[0] +
                   xx* ( 1-yy ) * data[1] +
                   ( 1-xx ) *yy*data[ image_->step ] +
                   xx*yy*data[image_->step+1]
               );
    }
public:
    Eigen::Vector3d x_world_;   // 3D point in world frame
    float cx_=0, cy_=0, fx_=0, fy_=0; // Camera intrinsics
    cv::Mat* image_=nullptr;    // reference image
};

int main ( int argc, char** argv )
{
    if ( argc != 2 )
    {
        cout<<"usage: useLK path_to_dataset"<<endl;
        return 1;
    }
    srand ( ( unsigned int ) time ( 0 ) );
    string path_to_dataset = argv[1];
    string associate_file = path_to_dataset + "/associate.txt";

    ifstream fin ( associate_file );

    string rgb_file, depth_file, time_rgb, time_depth;
    cv::Mat color, depth, gray;
    vector<Measurement> measurements;
    // 相机内参
    float cx = 325.5;
    float cy = 253.5;
    float fx = 518.0;
    float fy = 519.0;
    float depth_scale = 1000.0;
    Eigen::Matrix3f K;
    K<<fx,0.f,cx,0.f,fy,cy,0.f,0.f,1.0f;

    Eigen::Isometry3d Tcw = Eigen::Isometry3d::Identity();

    cv::Mat prev_color;
    // 我们以第一个图像为参考,对后续图像和参考图像做直接法
    for ( int index=0; index<10; index++ )
    {
        cout<<"*********** loop "<<index<<" ************"<<endl;
        fin>>time_rgb>>rgb_file>>time_depth>>depth_file;
        color = cv::imread ( path_to_dataset+"/"+rgb_file );
        depth = cv::imread ( path_to_dataset+"/"+depth_file, -1 );
        if ( color.data==nullptr || depth.data==nullptr )
            continue; 
        cv::cvtColor ( color, gray, cv::COLOR_BGR2GRAY );
        if ( index ==0 )
        {
            // 对第一帧提取FAST特征点
            vector<cv::KeyPoint> keypoints;
            cv::Ptr<cv::FastFeatureDetector> detector = cv::FastFeatureDetector::create();
            detector->detect ( color, keypoints );
            for ( auto kp:keypoints )
            {
                // 去掉邻近边缘处的点
                if ( kp.pt.x < 20 || kp.pt.y < 20 || ( kp.pt.x+20 ) >color.cols || ( kp.pt.y+20 ) >color.rows )
                    continue;
                ushort d = depth.ptr<ushort> ( cvRound ( kp.pt.y ) ) [ cvRound ( kp.pt.x ) ];
                if ( d==0 )
                    continue;
                Eigen::Vector3d p3d = project2Dto3D ( kp.pt.x, kp.pt.y, d, fx, fy, cx, cy, depth_scale );
                float grayscale = float ( gray.ptr<uchar> ( cvRound ( kp.pt.y ) ) [ cvRound ( kp.pt.x ) ] );
                measurements.push_back ( Measurement ( p3d, grayscale ) );
            }
            prev_color = color.clone();
            continue;
        }
        // 使用直接法计算相机运动
        chrono::steady_clock::time_point t1 = chrono::steady_clock::now();
        poseEstimationDirect ( measurements, &gray, K, Tcw );
        chrono::steady_clock::time_point t2 = chrono::steady_clock::now();
        chrono::duration<double> time_used = chrono::duration_cast<chrono::duration<double>> ( t2-t1 );
        cout<<"direct method costs time: "<<time_used.count() <<" seconds."<<endl;
        cout<<"Tcw="<<Tcw.matrix() <<endl;

        // plot the feature points
        cv::Mat img_show ( color.rows*2, color.cols, CV_8UC3 );
        prev_color.copyTo ( img_show ( cv::Rect ( 0,0,color.cols, color.rows ) ) );
        color.copyTo ( img_show ( cv::Rect ( 0,color.rows,color.cols, color.rows ) ) );
        for ( Measurement m:measurements )
        {
            if ( rand() > RAND_MAX/5 )
                continue;
            Eigen::Vector3d p = m.pos_world;
            Eigen::Vector2d pixel_prev = project3Dto2D ( p ( 0,0 ), p ( 1,0 ), p ( 2,0 ), fx, fy, cx, cy );
            Eigen::Vector3d p2 = Tcw*m.pos_world;
            Eigen::Vector2d pixel_now = project3Dto2D ( p2 ( 0,0 ), p2 ( 1,0 ), p2 ( 2,0 ), fx, fy, cx, cy );
            if ( pixel_now(0,0)<0 || pixel_now(0,0)>=color.cols || pixel_now(1,0)<0 || pixel_now(1,0)>=color.rows )
                continue;

            float b = 255*float ( rand() ) /RAND_MAX;
            float g = 255*float ( rand() ) /RAND_MAX;
            float r = 255*float ( rand() ) /RAND_MAX;
            cv::circle ( img_show, cv::Point2d ( pixel_prev ( 0,0 ), pixel_prev ( 1,0 ) ), 8, cv::Scalar ( b,g,r ), 2 );
            cv::circle ( img_show, cv::Point2d ( pixel_now ( 0,0 ), pixel_now ( 1,0 ) +color.rows ), 8, cv::Scalar ( b,g,r ), 2 );
            cv::line ( img_show, cv::Point2d ( pixel_prev ( 0,0 ), pixel_prev ( 1,0 ) ), cv::Point2d ( pixel_now ( 0,0 ), pixel_now ( 1,0 ) +color.rows ), cv::Scalar ( b,g,r ), 1 );
        }
        cv::imshow ( "result", img_show );
        cv::waitKey ( 0 );

    }
    return 0;
}

bool poseEstimationDirect ( const vector< Measurement >& measurements, cv::Mat* gray, Eigen::Matrix3f& K, Eigen::Isometry3d& Tcw )
{
    // 初始化g2o
    typedef g2o::BlockSolver<g2o::BlockSolverTraits<6,1>> DirectBlock;  // 求解的向量是6*1的
    DirectBlock::LinearSolverType* linearSolver = new g2o::LinearSolverDense< DirectBlock::PoseMatrixType > ();
    DirectBlock* solver_ptr = new DirectBlock ( linearSolver );
    // g2o::OptimizationAlgorithmGaussNewton* solver = new g2o::OptimizationAlgorithmGaussNewton( solver_ptr ); // G-N
    g2o::OptimizationAlgorithmLevenberg* solver = new g2o::OptimizationAlgorithmLevenberg ( solver_ptr ); // L-M
    g2o::SparseOptimizer optimizer;
    optimizer.setAlgorithm ( solver );
    optimizer.setVerbose( true );

    g2o::VertexSE3Expmap* pose = new g2o::VertexSE3Expmap();
    pose->setEstimate ( g2o::SE3Quat ( Tcw.rotation(), Tcw.translation() ) );
    pose->setId ( 0 );
    optimizer.addVertex ( pose );

    // 添加边
    int id=1;
    for ( Measurement m: measurements )
    {
        EdgeSE3ProjectDirect* edge = new EdgeSE3ProjectDirect (
            m.pos_world,
            K ( 0,0 ), K ( 1,1 ), K ( 0,2 ), K ( 1,2 ), gray
        );
        edge->setVertex ( 0, pose );
        edge->setMeasurement ( m.grayscale );
        edge->setInformation ( Eigen::Matrix<double,1,1>::Identity() );
        edge->setId ( id++ );
        optimizer.addEdge ( edge );
    }
    cout<<"edges in graph: "<<optimizer.edges().size() <<endl;
    optimizer.initializeOptimization();
    optimizer.optimize ( 30 );
    Tcw = pose->estimate();
}

CMakeLists.txt

cmake_minimum_required( VERSION 2.8 )
project( directMethod )

set( CMAKE_BUILD_TYPE Release )
set( CMAKE_CXX_FLAGS "-std=c++11 -O3" )

# 添加cmake模块路径
list( APPEND CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake_modules )

find_package( OpenCV )
include_directories( ${OpenCV_INCLUDE_DIRS} )

find_package( G2O )
include_directories( ${G2O_INCLUDE_DIRS} ) 

include_directories( "/usr/include/eigen3" )

set( G2O_LIBS 
    g2o_core g2o_types_sba g2o_solver_csparse g2o_stuff g2o_csparse_extension 
)

add_executable( direct_sparse direct_sparse.cpp )
target_link_libraries( direct_sparse ${OpenCV_LIBS} ${G2O_LIBS} )

add_executable( direct_semidense direct_semidense.cpp )
target_link_libraries( direct_semidense ${OpenCV_LIBS} ${G2O_LIBS} )

Bash指令:

 cd code/slambook/ch8/directMethod
mkdir build
cd build
cmake ..
make

到make这一步会报错
RGB-D直接法_第3张图片
对原代码做如下修改:

 /*
    // 初始化g2o
    typedef g2o::BlockSolver> DirectBlock;  // 求解的向量是6*1的
    DirectBlock::LinearSolverType* linearSolver = new g2o::LinearSolverDense< DirectBlock::PoseMatrixType > ();
    DirectBlock* solver_ptr = new DirectBlock ( linearSolver );
    // g2o::OptimizationAlgorithmGaussNewton* solver = new g2o::OptimizationAlgorithmGaussNewton( solver_ptr ); // G-N
    g2o::OptimizationAlgorithmLevenberg* solver = new g2o::OptimizationAlgorithmLevenberg ( solver_ptr ); // L-M
    */
    typedef g2o::BlockSolver<g2o::BlockSolverTraits<6,1>> DirectBlock;  // 求解的向量是6*1的
    std::unique_ptr<DirectBlock::LinearSolverType> linearSolver ( new g2o::LinearSolverDense<DirectBlock::PoseMatrixType>());
    std::unique_ptr<DirectBlock> solver_ptr ( new DirectBlock ( std::move(linearSolver)));
    g2o::OptimizationAlgorithmLevenberg* solver = new g2o::OptimizationAlgorithmLevenberg ( std::move(solver_ptr));

然后再次make
RGB-D直接法_第4张图片
开始执行生成的exe文件

./direct_sparse ../../data

RGB-D直接法_第5张图片
RGB-D直接法_第6张图片
上方是迭代过程,下方是估计出来的T矩阵,使用的优化器是LM算法

半稠密直接法的实验
数据类型和算法都与稀疏直接法一样,所不同的只是我们感兴趣的P点,对P点选取算法更改如下:

// select the pixels with high gradiants
for ( int x=10; x<gray.cols-10; x++ )
for ( int y=10; y<gray.rows-10; y++ )
{
Eigen::Vector2d delta (
gray.ptr<uchar>(y)[x+1] - gray.ptr<uchar>(y)[x-1],
gray.ptr<uchar>(y+1)[x] - gray.ptr<uchar>(y-1)[x]
);
if ( delta.norm() < 50 )
continue;
ushort d = depth.ptr<ushort> (y)[x];
if ( d==0 )
continue;
Eigen::Vector3d p3d = project2Dto3D ( x, y, d, fx, fy, cx, cy, depth_scale );
float grayscale = float ( gray.ptr<uchar> (y) [x] );
measurements.push_back ( Measurement ( p3d, grayscale ) );
}

同样修正编译错误:

 /*
    // 初始化g2o
    typedef g2o::BlockSolver> DirectBlock;  // 求解的向量是6*1的
    DirectBlock::LinearSolverType* linearSolver = new g2o::LinearSolverDense< DirectBlock::PoseMatrixType > ();
    DirectBlock* solver_ptr = new DirectBlock ( linearSolver );
    // g2o::OptimizationAlgorithmGaussNewton* solver = new g2o::OptimizationAlgorithmGaussNewton( solver_ptr ); // G-N
    g2o::OptimizationAlgorithmLevenberg* solver = new g2o::OptimizationAlgorithmLevenberg ( solver_ptr ); // L-M
    */
    typedef g2o::BlockSolver<g2o::BlockSolverTraits<6,1>> DirectBlock;  // 求解的向量是6*1的
    std::unique_ptr<DirectBlock::LinearSolverType> linearSolver ( new g2o::LinearSolverDense<DirectBlock::PoseMatrixType>());
    std::unique_ptr<DirectBlock> solver_ptr ( new DirectBlock ( std::move(linearSolver)));
    g2o::OptimizationAlgorithmLevenberg* solver = new g2o::OptimizationAlgorithmLevenberg ( std::move(solver_ptr));

Bash执行:

./direct_semidense ../../data

RGB-D直接法_第7张图片
RGB-D直接法_第8张图片
可以比较一下稀疏直接法和半稠密直接法的估计时间,13ms和141ms,对应76帧和7帧,正常实时的在线估计要求在60帧左右,所以如果用一般的CPU去计算,半稠密直接法无法用于实时估计

讨论
实际的图像往往具有很强的非凸性,利用梯度下降原理的凸优化算法往往达不到全局最小值。有时会使用小的图像块patch去做整体梯度,并且使用更加复杂的差异度量方法,比如说归一化相关性NCC
优点:
1.省去计算特征点和描述子的计算时间
2.只需要梯度,不需要特征点,可以在特征缺失的场景下使用
3.可以构建稠密地图
缺点:
1.非凸性容易导致局部最优
2.单个像素没有区分度
3.灰度值不变是很强的假设,需要使用更细致的光度模型标定相机

你可能感兴趣的:(SLAM十四讲,计算机视觉,slam)