search

UZ-SLAMLab / ORB_SLAM3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
GNU General Public License v3.0
6.69k stars 2.57k forks source link

errors: ORB-SLAM3 seems not work well with an RGB-D mode? #8

Closed cnqiangfu closed 4 years ago

SquirminatorHotHead commented 4 years ago

Do you mean core dumped error?

cnqiangfu commented 4 years ago

Do you mean core dumped error?

ORB-SLAM3 Copyright (C) 2017-2020 Carlos Campos, Richard Elvira, Juan J. Gómez, José M.M. Montiel and Juan D. Tardós, University of Zaragoza. ORB-SLAM2 Copyright (C) 2014-2016 Raúl Mur-Artal, José M.M. Montiel and Juan D. Tardós, University of Zaragoza. This program comes with ABSOLUTELY NO WARRANTY; This is free software, and you are welcome to redistribute it under certain conditions. See LICENSE.txt.

Input sensor was set to: RGB-D

Loading ORB Vocabulary. This could take a while... Vocabulary loaded!

Creation of new map with id: 0 Creation of new map with last KF id: 0 Seq. Name:

Camera Parameters:

ORB Extractor Parameters:

Depth Threshold (Close/Far Points): 3.07156

Start processing sequence ... Images in the sequence: 5057

./runtum.sh: line 2: 16582 Segmentation fault ../Examples/RGB-D/rgbd_tum ../Vocabulary/ORBvoc.txt ../Examples/RGB-D/TUM2.yaml /home/healer/TUM-RGBD/rgbd_dataset_freiburg2_large_with_loop /home/healer/TUM-RGBD/rgbd_dataset_freiburg2_large_with_loop/associations.txt

Just error when run RGB-D example.

SquirminatorHotHead commented 4 years ago

Do you mean core dumped error?

ORB-SLAM3 Copyright (C) 2017-2020 Carlos Campos, Richard Elvira, Juan J. Gómez, José M.M. Montiel and Juan D. Tardós, University of Zaragoza. ORB-SLAM2 Copyright (C) 2014-2016 Raúl Mur-Artal, José M.M. Montiel and Juan D. Tardós, University of Zaragoza. This program comes with ABSOLUTELY NO WARRANTY; This is free software, and you are welcome to redistribute it under certain conditions. See LICENSE.txt.

Input sensor was set to: RGB-D

Loading ORB Vocabulary. This could take a while... Vocabulary loaded!

Creation of new map with id: 0 Creation of new map with last KF id: 0 Seq. Name:

Camera Parameters:

  • fx: 520.909
  • fy: 521.007
  • cx: 325.141
  • cy: 249.702
  • bf: 40
  • k1: 0
  • k2: 0
  • p1: 0
  • p2: 0
  • k3: 0.917205
  • 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): 3.07156

Start processing sequence ... Images in the sequence: 5057

./runtum.sh: line 2: 16582 Segmentation fault ../Examples/RGB-D/rgbd_tum ../Vocabulary/ORBvoc.txt ../Examples/RGB-D/TUM2.yaml /home/healer/TUM-RGBD/rgbd_dataset_freiburg2_large_with_loop /home/healer/TUM-RGBD/rgbd_dataset_freiburg2_large_with_loop/associations.txt

Just error when run RGB-D example.

Looks like the same error.

aiyouaiyouhehehe commented 4 years ago

the same error. T_T

richard-elvira commented 4 years ago

ORB-SLAM3 Beta version has been only tested in Monocular, Monocular-Inertial, Stereo, and Stereo-Inertial sensors, which are the sensors that we report in the article. RGB-D sensor may not work properly, we will provide complete support to all sensor in future versions.

yan99033 commented 4 years ago

Hi @cnqiangfu, while RGB-D may not work properly, feel free to try my posted solution in #3, i.e., adding Camera.type: "PinHole" in the yaml file and see if it helps.

cnqiangfu commented 4 years ago

Hi @cnqiangfu, while RGB-D may not work properly, feel free to try my posted solution in #3, i.e., adding Camera.type: "PinHole" in the yaml file and see if it helps.

Hi Shing, that is so nice of you. I tried it, but it still didn't work. It does not matter, because I have turned attention to VIO ~~~

aiyouaiyouhehehe commented 4 years ago

It still can not run tum1 and tum2. Could anyone tell me how to fix it？Thanks very much！

aiyouaiyouhehehe commented 4 years ago

ORB-SLAM3 Beta version has been only tested in Monocular, Monocular-Inertial, Stereo, and Stereo-Inertial sensors, which are the sensors that we report in the article. RGB-D sensor may not work properly, we will provide complete support to all sensor in future versions.

Hi,@richard-elvira. tum3 runs successfully. I tried tum1 and tum2 dataset in RGB-D mode but it still has an error with core dumped. Could you please tell me how to fix it? Thanks very much!!!

niumaoyihao commented 7 months ago

ORB-SLAM3 Beta version has been only tested in Monocular, Monocular-Inertial, Stereo, and Stereo-Inertial sensors, which are the sensors that we report in the article. RGB-D sensor may not work properly, we will provide complete support to all sensor in future versions.

You can read the TUM1.yaml and your own TUMxxx.yaml，maybe some parameters' names are different. I run successful after changing my own TUMxxx.yaml using the same param name as TUM1.yaml.