https://github.com/hpennington/mono-visual-odometry

Monocular Visual Odometry in NumPy
https://github.com/hpennington/mono-visual-odometry

computer-vision numpy opencv python

Last synced: about 2 months ago
JSON representation

Monocular Visual Odometry in NumPy

• Host: GitHub
• URL: https://github.com/hpennington/mono-visual-odometry
• Owner: hpennington
• License: mit
• Created: 2022-11-13T02:28:11.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-12-25T19:39:46.000Z (over 2 years ago)
• Last Synced: 2025-03-13T08:27:12.267Z (over 1 year ago)
• Topics: computer-vision, numpy, opencv, python
• Language: Jupyter Notebook
• Homepage:
• Size: 87.2 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

          

![](https://github.com/hpennington/mono-visual-odometry/raw/main/point_cloud.gif)

# Monocular visual odometry

A Work in Progress implementation of visual odometry in numpy. Currently aided by some opencv functions. The plan is to remove these and implement with purely numpy.

#### Functions to implement in native numpy

  - [ ] goodFeaturesToTrack

  - [x] ransac

  - [x] FundamentalMatrixTransform

  - [ ] Brute-Force Matcher (BFMatcher)

  - [ ] Compute ORB feature descriptors

  - [x] triangulate

  - [x] extract_pose (Needs refactoring for deciding ambiguities)

  - [x] fundamentalToEssential

  - [x] make_homogeneous

## Setup

```bash

conda env create -f environment.yml

conda activate pyvo

```

My suggestion is to open src/visual_odometry.ipynb in VS Code.

Any web browser and jupyter notebook will work, but I find that VS Code make the nicest notebook environment.

## Demo

Press 'q' to end the demo sooner than the full duration.

### Feature matches

The red and green points represent the detected feature in the current and previous frame. A blue line is draw between these points.

![](https://github.com/hpennington/mono-visual-odometry/raw/main/features.jpeg)

### Integrated pose plot

Red is the ground truth and green is the predicted pose

![](https://github.com/hpennington/mono-visual-odometry/raw/main/vo.png)

### Point cloud

Open the point cloud in the open3d app. http://www.open3d.org/download/

![](https://github.com/hpennington/mono-visual-odometry/raw/triangulation/point_cloud.png)