kapture-localization 0.0b0

kapture-localization: localization pipelines based on kapture.

Overview

kapture-localization is a toolbox in which you will find implementations for various localization related algorithms. It strongly relies on the kapture package for data representation and manipulation.

The localization algorithms aims to do:

1. mapping,

2. localization and

3. benchmarking (image retrieval for visual localization).

It works on Ubuntu, Windows and MacOS.

structure

The directories are organised as follow:

├── kapture_localization/  # package (library)
├── pipeline/              # main programs scheduling all steps needed in localization pipelines
├── samples/               # some sample data
├── tests/                 # unit tests
└── tools/                 # sub programs involved in the pipeline

The kapture-localization toolbox provides both :

• Python package (kapture_localization/),

• Python executable scripts (pipeline/ & tools/).

There is basically 3 pipelines, for:

1. mapping,

2. localization and

3. image retrieval benchmark (global sfm, local sfm, pose approximation).

Installation

You can either install using docker, pip or from the source code manually. Basically, you will need python (>=3.6) and Colmap (>=3.6) to be installed, and then you can

pip install kapture-localization

See doc/installation.adoc for more details.

Tutorial

See the doc/tutorial for a short introduction to:

• mapping pipeline

• localization pipeline

• image retrieval benchmark (global sfm, local sfm, pose approximation)

Contributing

There are many ways to contribute to the kapture-localization project:

• provide feedback and suggestions of improvements,

• submit bug reports in the project bug tracker,

• implement a feature or bug-fix for an outstanding issue,

• provide scripts to create data in kapture format (e.g. local/global feature extraction),

• propose a new feature and implement it.

If you wish to contribute, please refer to the CONTRIBUTING page.

License

Software license is detailed in the LICENSE file.