leixu1999 / eplf-vins Goto Github PK

/home/kk/catkin_eplfvins/src/EPLF-VINS/linefeature_tracker/src/linefeature_tracker.cpp:811:23: error: ‘EdgeDrawing’ is not a member of ‘cv::ximgproc’
Ptrcv::ximgproc::EdgeDrawing ed = cv::ximgproc::createEdgeDrawing();
^~~~~~~~~~~
/home/kk/catkin_eplfvins/src/EPLF-VINS/linefeature_tracker/src/linefeature_tracker.cpp:811:23: error: ‘EdgeDrawing’ is not a member of ‘cv::ximgproc’

1.图像分辨率1280 720显示线特征太多，这个要如何调参，640*480我可以运行；
2.开启外参自动标定，标定结果不如原始vins，应该是没有调好参数，这个应该怎么调；
3.初始化旋转参数用到线特征了吗
4.代码中去掉了时间偏差估计吗
非常感谢

error: invalid initialization of reference of type ‘cv::InputArray {aka const cv::_InputArray&}’ from expression of type ‘std::vector::iterator {aka __gnu_cxx::__normal_iterator<float*, std::vector >}’
float sum = accumulate(sampleMagnitude.begin(), sampleMagnitude.end(), 0.0);

In the function Line::extendLine(), you use the following code to compute the std. of the gradient magnitude

        std::for_each(sampleMagnitude.begin(), sampleMagnitude.end(), [&](const float d)
                      { accum += (d - accum) * (d + accum); });

It seems strange, maybe it should be modified as follows?

        std::for_each(sampleMagnitude.begin(), sampleMagnitude.end(), [&](const float d)
                      { accum += pow(d - mean, 2); });

为什么对线特征边缘化是采用 ResidualBlockInfo *residual_block_info = new ResidualBlockInfo(f, loss_function,vector<double *>{para_Pose[imu_j], para_Ex_Pose[0], para_LineFeature[linefeature_index]},drop_set); drop_set = vector{2}; 而不是像点特征一样边缘化滑窗中第0帧，drop_set = {0,2}

Hi.
I did not find the line reprojection error mentioned in the paper.
It still is the original implementation of PL-VINS (line_projection_factor.cpp)

Hi, thanks for your great work.
May I ask when will the source code be released?

Thank you for your excellent work. I have a question. Does the line feature extraction and matching in this project support fisheye images?