Skip to Main content Skip to Navigation
Conference papers

Force Banner for the recognition of spatial relations

Abstract : Studying the spatial organization of objects in images is fundamental to increase both the understanding of a sensed scene and the explainability of the perceived similarity between images. This leads to the fundamental problem of handling spatial relations: given two objects depicted in an image, or two parts in an object, how to extract and describe efficiently their spatial configuration? Dedicated descriptors already exist for this task, like the efficient force histogram. In this article, we introduce the Force Banner, which extends it to two dimensions by using a panel of forces (attraction and repulsion), so as to benefit from more expressiveness and to model rich spatial information. This descriptor can be used as an intermediate representation of the image dedicated to the spatial configuration, and feed a classical 2D Convolutional Neural Network (CNN) to benefit from their powerful performances. As an illustration of this, we used it to solve a classification problem aiming to discriminate simple spatial relations, but with variable configuration complexities. Experimental results obtained on datasets of images with various shapes highlight the interest of this approach, in particular for complex spatial configurations.
Document type :
Conference papers
Complete list of metadata

https://hal-univ-paris.archives-ouvertes.fr/hal-03409527
Contributor : Robin Deléarde Connect in order to contact the contributor
Submitted on : Friday, October 29, 2021 - 5:34:15 PM
Last modification on : Thursday, November 4, 2021 - 12:50:02 PM

File

ICPR20_RD_final.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

Robin Deléarde, Camille Kurtz, Philippe Dejean, Laurent Wendling. Force Banner for the recognition of spatial relations. 2020 25th International Conference on Pattern Recognition (ICPR), Jan 2021, online, Italy. pp.6065-6072, ⟨10.1109/ICPR48806.2021.9412316⟩. ⟨hal-03409527⟩

Share

Metrics

Record views

12

Files downloads

8