orb-slam2_with_semantic_label
orb-slam2_with_semantic_label copied to clipboard
qixuxiang
orb-slam2 with semantic label
Great Job! I have run your project successfully with CUDA8.0 + opencv3.4 + pcl1.8 and got the point cloud with semantic label, but how can I get the segment result...
是orb-slam2_with_semantic_label还是orb-slam2_with_semantic_labeling？我不太理解您移动到orb-slam2_with_semantic_labeling的意思，所以我配置的时候应该用哪个包？
[100%] Linking CXX executable ../bin/rgbd_tum ../lib/libORB_SLAM2.so：对‘pcl::SupervoxelClustering::SupervoxelClustering(float, float)’未定义的引用 ../lib/libORB_SLAM2.so：对‘pcl::SupervoxelClustering::setUseSingleCameraTransform(bool)’未定义的引用
CMakeFiles/Makefile2:72: recipe for target 'CMakeFiles/ORB_SLAM2.dir/all' failed make[1]: *** [CMakeFiles/ORB_SLAM2.dir/all] Error 2 Makefile:83: recipe for target 'all' failed make: *** [all] Error 2 Converting vocabulary to binary BoW load/save benchmark ./tools/bin_vocabulary:...
  In segmentation.cc at lines 211, "Eigen::MatrixXf normals_mat(num_planes, num_super_voxels);" by num_planes and num_super_voxels. the num_super_voxels is not equal to 3.but at lines 268...
`poisson_reconstruction(globalMap);` 我把泊松重建这一行解注释之后得到了重建的ply文件，然后在python里用open3d库可视化了出来，发现还是一些离散的点，请问作者大佬有没有什么办法可以根据点云重建出曲面？
1. 在进行"Converting vocabulary to binary"时 ， 出现文件不存在。 2.在最后运行代码时出现./rgbd_tum:段错误（核心已转储） @qixuxiang 帮忙看看，谢谢。
在63３至637行 sor.setInputCloud(input_cloud_ptr); sor.setLeafSize (0.005f, 0.005f, 0.005f); sor.filter(*cloud_filtered); std::cerr
