HKUST-Aerial-Robotics / DenseSurfelMapping

This is the open-source version of ICRA 2019 submission "Real-time Scalable Dense Surfel Mapping"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Having trouble running TUM dataset

qq1962572025 opened this issue · comments

I want to run program on an indoor dataset to observe the result of the reconstruction. I modify the camera Intrinsic in the launch file for node surfer_fusion, and rewrite the node that sends the picture like this:
depth = cv::imread(PATH+s1, -1);
left = cv::imread(PATH+s2,-1);
cvtColor( left, left, CV_BGR2GRAY );
depth.convertTo(depth,CV_32F);
sensor_msgs::ImagePtr msg_1 = cv_bridge::CvImage(std_msgs::Header(), "mono8", left).toImageMsg();
sensor_msgs::ImagePtr msg_2 = cv_bridge::CvImage(std_msgs::Header(), "32FC1", depth).toImageMsg();
ORB-SLAM2 runs well as usual,but surfer_fusion cannot create any surfel,is there other part of the program that should be modified?
image

The unit of the depth map in the code is meter, so TUM data needs to be divided by factor.

can you give more details about the factor about TUM dataset, thank you

The unit of the depth map in the code is meter, so TUM data needs to be divided by factor.

您好,我也在尝试运行TUM的数据集。我没有写数据的发布节点,而是直接使用tum 的rosbag直接发布数据,我的运行结果如下:
image
image
但是orb的点云在rviz中显示不出来,显示为:
image
运行surfel_fusion节点时,rviz没有出现任何surfel,我的几个终端显示:
image
按您说的,我在surfel_map.cpp文件中把深度图的单位进行了转换:
image.convertTo(image,CV_32F,mDepthMapFactor);
mDepthMapFactor 应该是取0.0002吧(5000我也试过),我看TUM的5000值对应距离1米,但还是不行,请问您有什么建议吗?