ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging
Mixture of Manhattan Frames

how can i fix this?please help me!

Thank you for your great job. When I perform test on 'rgbd_dataset_freiburg3_structure_texture_far', "double free or corruption (out) Signal: SIGABRT (Aborted)" appears. Details can be found in the attached pictures.
My configure is:
Ubuntu18.04
PCL1.9.0
Opencv3.4.0
Eigen3.3.4
Look forward to hearing you.
Best regards.

您好，请问在编译时为什么会出现这种fatal error呢，不是没有用到GPU吗？如果我在CMakeLists中添加了cuda_runtime.h的路径后，编译就会卡住，请问这是什么原因呢？感谢解答。

How can I modify the source code if I want to get a point cloud image with rgb information of each point? Thank you very much for your work, and hope to restore my question.

Hello, my version of OpenCV is 3.4.9. I don't know why the following error occurs. Hope to get your reply!

作者您好，我在阅读LineExtractor.cpp中的代码时无法看明白其中的函数作用，请问相关的参考论文可以分享下吗？

Hello, when I run PlanarSLAM on the freiburg3_structure_texture_far dataset, I am getting the following error:

PlanarSLAM Printer: This is the 1th image
ERROR: In /build/vtk6-VHOYAG/vtk6-6.3.0+dfsg1/IO/Image/vtkPNGWriter.cxx, line 260
vtkPNGWriter (0x7f5d80348240): Unable to open file mesh/000000.png
ERROR: In /build/vtk6-VHOYAG/vtk6-6.3.0+dfsg1/IO/Image/vtkImageWriter.cxx, line 505
vtkPNGWriter (0x7f5d80348240): Ran out of disk space; deleting file(s) already written
Segmentation fault (core dumped)

Compilation is passed. After checking, it seems that it is not the reason for insufficient disk space, because there are more than 10 G free spaces.

The versions of some third-party libraries I use are as follows：

1. Pangolin = 0.5
2. OpenCV & OpenCV_Contrib = 3.4.5
3. Eigen3 = 3.3.7
4. PCL = 1.8 (coming with ROS Melodic )

Is it caused by the incompatibility of PCL and VTK versions? Whether the version of PCL must be 1.7 or 1.9? Can you give me some advice? or which version are you using？Best regards.

Excuse me，
Why are the displayed keypoints so small, did you use an algorithm to improve the feature points? If not, can you tell me how to set it up? I want him to be as big as the key point of ORB-SLAM2. Thank you very much!

Hi there,

I followed the similar issue and commented
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wall -O3 -march=native ")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall -O3 -march=native")
as described in #3

But then the system dead after the 0th image, as shown below:

__PlanarSLAM Copyright (C) 2021 Yanyan Li, Technical University of Munich (TUM).
This program comes with ABSOLUTELY NO WARRANTY;
This is free software based on ORB-SLAM2, and you are welcome to redistribute it
under certain conditions. See LICENSE.txt.

Loading ORB Vocabulary. This could take a while...
Vocabulary loaded in 5.67s
Vocabulary loaded!

img_width = 640
img_height = 480
mUndistX size = 480 x 640mUndistY size = 480 x 640

Camera Parameters:

• fx: 481.2
• fy: -480
• cx: 319.5
• cy: 239.5
• k1: 0
• k2: 0
• p1: 0
• p2: 0
• fps: 30
• color order: RGB (ignored if grayscale)

ORB Extractor Parameters:

• Number of Features: 1000
• Scale Levels: 8
• Scale Factor: 1.2
• Initial Fast Threshold: 20
• Minimum Fast Threshold: 7

Depth Threshold (Close/Far Points): 3.32502
PlanarSLAM Printer: This is the 0th image
Matching planes...
plane 0:
p1 [-0.00024552766, -0.99999911, -0.0013000764, 0.90096229]:
1, p2 : [-0.0001090349, -0.00013670312, -1, 3.9469013]
1, angle : 0.00143681
vertical!
plane 1:
p1 [-0.0001090349, -0.00013670312, -1, 3.9469013]:
Matching done
p1: [0.00024552766;
0.99999911;
0.0013000764]
p2: [0.0001090349;
0.00013670312;
1]
p3: [0.99999893;
-0.00024538589;
-0.00010900124]
PlanarSLAM Printer: This is the 1th image
Segmentation fault (core dumped)__

any hints for this?
thanks in advance

Hello,
I have only tried some datasets (OF_KT0, LR_KT2, and the rgbd_dataset_freiburg3_long_office_household) with segmentation fault result. It is produced in:

Thanks in advance.

When I run the ICL NUIM or TUM rgdb datasets, the following error will be reported.

我在ubuntu18运行，运行数据集显示段错误，这个为啥，安装编译都没问题

请问使用实际相机测试发现平面上的点不如论文中的密集。这种情况应该怎么调节参数？

环境：ubuntu16.04
相机：奥比中光astrapro 深度相机

Hi. First, thank you for the great work. I run it on my own rgb-d dataset, which img size is 480x640. It takes approximately 2-3 seconds to track a frame. I cannot understand the reason why it works so slowly. Can you suggest anything to improve the speed? Thanks in regard.