oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python

We present oflibnumpy and oflibpytorch, an optical flow library based on NumPy arrays and PyTorch tensors, respectively. It provides a structured approach to the representation of optical flow, i.e '2'D vector fields, as a custom class offering a number of methods to apply, manipulate, ana...

Full description

Bibliographic Details
Main Authors: Claudio S. Ravasio, Lyndon Da Cruz, Christos Bergeles
Format: Article
Language:English
Published: Ubiquity Press 2021-11-01
Series:Journal of Open Research Software
Subjects:
Online Access:https://openresearchsoftware.metajnl.com/articles/380
_version_ 1830508920333926400
author Claudio S. Ravasio
Lyndon Da Cruz
Christos Bergeles
author_facet Claudio S. Ravasio
Lyndon Da Cruz
Christos Bergeles
author_sort Claudio S. Ravasio
collection DOAJ
description We present oflibnumpy and oflibpytorch, an optical flow library based on NumPy arrays and PyTorch tensors, respectively. It provides a structured approach to the representation of optical flow, i.e '2'D vector fields, as a custom class offering a number of methods to apply, manipulate, analyse, and visualise the flow. The library takes into account the two possible frames of reference in optical flow calculation, namely the source (first frame) and target (second frame). The collection of methods and their rigorous mathematical underpinning makes the library broadly applicable to any project that uses flow fields. It is implemented as a Python 3 package whose source can be found on GitHub, and which can be installed either from the git repository or the Python Package Index (PyPI).
first_indexed 2024-12-22T01:25:25Z
format Article
id doaj.art-20f08fc2042a4bd3ad859f5af744a5e8
institution Directory Open Access Journal
issn 2049-9647
language English
last_indexed 2024-12-22T01:25:25Z
publishDate 2021-11-01
publisher Ubiquity Press
record_format Article
series Journal of Open Research Software
spelling doaj.art-20f08fc2042a4bd3ad859f5af744a5e82022-12-21T18:43:37ZengUbiquity PressJournal of Open Research Software2049-96472021-11-019110.5334/jors.380261oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in PythonClaudio S. Ravasio0Lyndon Da Cruz1Christos Bergeles2Research Assistant, King’s College London/PhD student, University College LondonConsultant Ophthalmic Surgeon, Moorfields Eye Hospital, LondonAssociate Professor, King’s College LondonWe present oflibnumpy and oflibpytorch, an optical flow library based on NumPy arrays and PyTorch tensors, respectively. It provides a structured approach to the representation of optical flow, i.e '2'D vector fields, as a custom class offering a number of methods to apply, manipulate, analyse, and visualise the flow. The library takes into account the two possible frames of reference in optical flow calculation, namely the source (first frame) and target (second frame). The collection of methods and their rigorous mathematical underpinning makes the library broadly applicable to any project that uses flow fields. It is implemented as a Python 3 package whose source can be found on GitHub, and which can be installed either from the git repository or the Python Package Index (PyPI).https://openresearchsoftware.metajnl.com/articles/380optical flowflow fieldflow vectorflow compositionpythonnumpypytorch
spellingShingle Claudio S. Ravasio
Lyndon Da Cruz
Christos Bergeles
oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python
Journal of Open Research Software
optical flow
flow field
flow vector
flow composition
python
numpy
pytorch
title oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python
title_full oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python
title_fullStr oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python
title_full_unstemmed oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python
title_short oflibnumpy & oflibpytorch: Optical Flow Handling and Manipulation in Python
title_sort oflibnumpy oflibpytorch optical flow handling and manipulation in python
topic optical flow
flow field
flow vector
flow composition
python
numpy
pytorch
url https://openresearchsoftware.metajnl.com/articles/380
work_keys_str_mv AT claudiosravasio oflibnumpyoflibpytorchopticalflowhandlingandmanipulationinpython
AT lyndondacruz oflibnumpyoflibpytorchopticalflowhandlingandmanipulationinpython
AT christosbergeles oflibnumpyoflibpytorchopticalflowhandlingandmanipulationinpython