Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/gaoxiang12/ORBSLAM2_with_pointcloud_map

Last synced: 26 days ago
JSON representation

Host: GitHub
URL: https://github.com/gaoxiang12/ORBSLAM2_with_pointcloud_map
Owner: gaoxiang12
Created: 2016-05-26T09:02:22.000Z (about 8 years ago)
Default Branch: master
Last Pushed: 2022-08-17T06:26:52.000Z (almost 2 years ago)
Last Synced: 2024-02-10T05:01:17.461Z (4 months ago)
Language: C++
Size: 7.8 MB
Stars: 790
Watchers: 22
Forks: 339
Open Issues: 34
Metadata Files:
- Readme: README.md

Lists

Awesome-SLAM - ORBSLAM2_with_pointcloud_map
awesome-mobile-robotics - ORB-SLAM2 Point Cloud - D mode (Softwares and Libraries)

README

# ORBSLAM2_with_pointcloud_map
This is a modified ORB_SLAM2 (from https://github.com/raulmur/ORB_SLAM2, thanks for Raul's great work!) with a online point cloud map module running in RGB-D mode. You can visualize your point cloud map during the SLAM process.

# How to Install
Unzip the file you will find two directories. First compile the modified g2o:

```
cd g2o_with_orbslam2
mkdir build
cd build
cmake ..
make
```

Following the instructions from the original g2o library: [https://github.com/RainerKuemmerle/g2o] if you have dependency problems. I just add the extra vertecies and edges provided in ORB_SLAM2 into g2o.

Then compile the ORB_SLAM2. You need firstly to compile the DBoW2 in ORB_SLAM2_modified/Thirdpary, and then the Pangolin module (https://github.com/stevenlovegrove/Pangolin). Finally, build ORB_SLAM2:

```
cd ORB_SLAM2_modified
mkdir build
cd build
cmake ..
make
```

To run the program you also need to download the ORB vocabulary (which is a large file so I don't upload it) in the original ORB_SLAM2 repository.

# Run examples
Prepare a RGBD camera or dataset, give the correct parameters and you can get a ORB SLAM with point cloud maps like the example.jpg in this repo.

# Build the unpacked modified repo

please see this [README](./ORB_SLAM2_modified/README.md)