# stereoVO

**Repository Path**: sdkmsdn_admin/stereoVO

## Basic Information

- **Project Name**: stereoVO
- **Description**: A Simple Stereo Visual Odometery
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-03-17
- **Last Updated**: 2023-04-02

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# stereoVO
A Simple Stereo Visual Odometery


StereoVO is a real-time stereo visual odometry based part of ORB-SLAM2 and slambook/project.It is developed for the final project of SLAM course.It runs on laptops with CPU and only provides localization services for self-driving cars.

### Authors: Xiaoqiang JIANG

### 1 Installation

#### 1.1 Required Dependencies

- OpenCV3.x:  sudo apt-get install libopencv-dev(or from source)
- g2o  :sudo apt-get install libcxsparse-dev libqt4-dev libcholmod3.0.6 libsuitesparse-dev qt4-qmake
- eigen3  :sudo apt-get install libeigen3-dev
- Pangolin(for visualization): <https://github.com/stevenlovegrove/Pangolin>

Please follow  :   <https://github.com/raulmur/ORB_SLAM2>

#### 1.2 Build

> cd stereoVO
>
> mkdir build
>
> cd build 
>
> cmake ..
>
> make -j



### 2 Usage

Run on kitti dataset from:  <http://www.cvlibs.net/datasets/kitti/eval_object.php>

You should modify the dataset _dir in KITTI xx-xx.yaml in the source directory

And run ./vo_pangolin under bin.

### 3 Experiments

It is evaluated by evo tools(<https://github.com/MichaelGrupp/evo>)


![trajectory](https://github.com/SiuKeungm/stereoVO/blob/master/2018-05-18%2019_42_48____________.png)