https://github.com/heisenberg141/visual-odometry

This repository contains of an implementation of a ORB descriptor based monocular visual odometry approach.
https://github.com/heisenberg141/visual-odometry

computer-vision fundamental-matrix opencv python3 structure-from-motion visual-odometry

Last synced: about 2 months ago
JSON representation

This repository contains of an implementation of a ORB descriptor based monocular visual odometry approach.

• Host: GitHub
• URL: https://github.com/heisenberg141/visual-odometry
• Owner: heisenberg141
• Created: 2020-09-08T15:19:45.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2022-08-09T13:41:36.000Z (almost 4 years ago)
• Last Synced: 2025-03-26T15:48:14.953Z (over 1 year ago)
• Topics: computer-vision, fundamental-matrix, opencv, python3, structure-from-motion, visual-odometry
• Language: Python
• Homepage:
• Size: 1.94 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Prerequisites:

1. Download the Visual Odometry dataset from Kitti Vision Benchmark Suite

  http://www.cvlibs.net/download.php?file=data_odometry_gray.zip

2. Download the Visual Odometry poses data

http://www.cvlibs.net/download.php?file=data_odometry_poses.zip

3. Download the repository and extract it.

4. Download and install opencv (with opencv_contrib) with python 3.5+

5. Extract the dataset and poses data in the repository folder

# Testing the code 

Run test.py

# Results:

![illustration](Features.png) \

\

Blue: Ground Truth \

Red: Experimental Results \

![illustration](VO.png)