Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/aakarsh/pf-localization

Localization using a Particle Filter (and random walk model)

https://github.com/aakarsh/pf-localization

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 5 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.5%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Localization using a Particle Filter (and random walk model)

Basic Info
  • Host: GitHub
  • Owner: aakarsh
  • License: lgpl-3.0
  • Default Branch: master
  • Size: 13.8 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of 3p3r/pf-localization
Created about 4 years ago · Last pushed over 8 years ago

https://github.com/aakarsh/pf-localization/blob/master/ 

# pf-localization
Localization using a Particle Filter (and random walk model)
![Localization demo](data/demo.gif?raw=true)

## What is this?
This is a Cuda-C++ library to localize a camera, pointed at a checkerboard pattern without solving the [PnP problem](https://en.wikipedia.org/wiki/Perspective-n-Point) and using a particle filter. Solving the PnP problem is not always feasible (specifically in case of real-time SLAM), therefore this project aims at localizing the camera rotation and translation with a [Random Walk model](https://en.wikipedia.org/wiki/Random_walk).

## Building
In order to build this library, you need a system with CMake and Cuda SDK 7+ installed.

```bash
cd 
mkdir build;
cd build;
cmake .. -G "Visual Studio 14 Win64"
cmake --build . --config Release
cmake --build . --target INSTALL
```

## Running
Matlab is required (but not necessary) to run this library with a sample dataset (in `data/board.mp4`). The Matlab script that uses this library is `main.m`. The first time you run the Matlab file, it'll take some time to build a cache of video's ground truth data using PnP solver of Matlab.

Matlab code also ships with a Matlab implementation of the project. However, If you like to run this code with Cuda, you must have a Nvidia Cuda-capable graphics card.


## Reference
This code is an adaptation of the theories provided in the following paper:

```
@article{doi: 10.1117/1.JEI.23.1.013029,
author = { Seok-Han  Lee},
title = {Real-time camera tracking using a particle filter combined with unscented Kalman filters},
journal = {Journal of Electronic Imaging},
volume = {23},
number = {},
pages = {23 - 23 - 19},
year = {2014},
doi = {10.1117/1.JEI.23.1.013029},
URL = {http://dx.doi.org/10.1117/1.JEI.23.1.013029},
eprint = {}
}
```

Owner

  • Name: Aakarsh Nair
  • Login: aakarsh
  • Kind: user
  • Location: Portland, OR
  • Company: www.nentei.com

“The present moment is the only moment available to us and it is the door to all other moments.” ~TNH

GitHub Events

Total
Last Year