Egocentric Point of Interest Recognition in Cultural Sites

Francesco Ragusa, Antonino Furnari, Sebastiano Battiato, Giovanni Signorello, Giovanni Farinella

Abstract

We consider the problem of the detection and recognition of points of interest in cultural sites. We observe that a “point of interest” in a cultural site may be either an object or an environment and highlight that the use of an object detector is beneficial to recognize points of interest which occupy a small part of the frame. To study the role of objects in the recognition of points of interest, we augment the labelling of the UNICT-VEDI dataset to include bounding box annotations for 57 points of interest. We hence compare two approaches to perform the recognition of points of interest. The first method is based on the processing of the whole frame during recognition. The second method employs a YOLO object detector and a selection procedure to determine the currently observed point of interest. Our experiments suggest that further improvements on point of interest recognition can be achieved fusing the two methodologies. Indeed, the results show the complementarity of the two approaches on the UNICT-VEDI dataset.

Download


Paper Citation


in Harvard Style

Ragusa F., Furnari A., Battiato S., Signorello G. and Farinella G. (2019). Egocentric Point of Interest Recognition in Cultural Sites.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-354-4, pages 381-392. DOI: 10.5220/0007365503810392


in Bibtex Style

@conference{visapp19,
author={Francesco Ragusa and Antonino Furnari and Sebastiano Battiato and Giovanni Signorello and Giovanni Farinella},
title={Egocentric Point of Interest Recognition in Cultural Sites},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2019},
pages={381-392},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007365503810392},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Egocentric Point of Interest Recognition in Cultural Sites
SN - 978-989-758-354-4
AU - Ragusa F.
AU - Furnari A.
AU - Battiato S.
AU - Signorello G.
AU - Farinella G.
PY - 2019
SP - 381
EP - 392
DO - 10.5220/0007365503810392