An Extension of the Radial Line Model to Predict Spatial Relations

Logan Servant, Camille Kurtz, Laurent Wendling

2023

Abstract

Analysing the spatial organization of objects in images is fundamental to increasing both the understanding of a scene and the explicability of perceived similarity between images. In this article, we propose to describe the spatial positioning of objects by an extension of the original Radial Line Model to any pair of objects present in an image, by defining a reference point from the convex hulls and not the enclosing rectangles, as done in the initial version of this descriptor. The recognition of spatial configurations is then considered as a classification task where the achieved descriptors can be embedded in a neural learning mechanism to predict from object pairs their directional spatial relationships. An experimental study, carried out on different image datasets, highlights the interest of this approach and also shows that such a representation makes it possible to automatically correct or denoise datasets whose construction has been rendered ambiguous by the human evaluation of 2D/3D views. Source code: https://github.com/Logan-wilson/extendedRLM.

Paper Citation

in Harvard Style

Servant L., Kurtz C. and Wendling L. (2023). An Extension of the Radial Line Model to Predict Spatial Relations. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 187-195. DOI: 10.5220/0011644300003417

in Bibtex Style

@conference{visapp23,
author={Logan Servant and Camille Kurtz and Laurent Wendling},
title={An Extension of the Radial Line Model to Predict Spatial Relations},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={187-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011644300003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - An Extension of the Radial Line Model to Predict Spatial Relations
SN - 978-989-758-634-7
AU - Servant L.
AU - Kurtz C.
AU - Wendling L.
PY - 2023
SP - 187
EP - 195
DO - 10.5220/0011644300003417
PB - SciTePress