A saliency-based approach to boost trail detection

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper presents a saliency-based solution to boost trail detection. The proposed model builds on the empirical observation that trails are usually conspicuous structures in natural environments. This hypothesis is confirmed by the experimental results, where a strong positive correlation between trail location and visual saliency has been observed. These results are due in part to the proposed extensions to a well known visual saliency computational model. This paper goes further and shows that, with a proper analysis of the saliency information alone, the ambiguity regarding both trail's position and approximate skeleton is reduced to three hypotheses in 98% of the tested natural images. This analysis is performed by a set of agents inhabiting the saliency and feature specific intermediate maps. These agents' behaviours exploit implicit, top-down knowledge about the object being sought in an active way. With the proposed model, computationally demanding accurate trail detectors are able to focus their activity in a fraction of the input image, thus promoting robustness and real-time performance.
Original languageUnknown
Title of host publicationIEEE Conference Proceedings
Pages1426-1431
DOIs
Publication statusPublished - 1 Jan 2010
Event2010 IEEE International Conference on Robotics and Automation (ICRA) -
Duration: 1 Jan 2010 → …

Conference

Conference2010 IEEE International Conference on Robotics and Automation (ICRA)
Period1/01/10 → …

Cite this

Barata Oliveira, J. A., & DEE Group Author (2010). A saliency-based approach to boost trail detection. In IEEE Conference Proceedings (pp. 1426-1431) https://doi.org/10.1109/ROBOT.2010.5509929
Barata Oliveira, José António ; DEE Group Author. / A saliency-based approach to boost trail detection. IEEE Conference Proceedings. 2010. pp. 1426-1431
@inproceedings{7dbc7bb365eb425c83d008abfb86c122,
title = "A saliency-based approach to boost trail detection",
abstract = "This paper presents a saliency-based solution to boost trail detection. The proposed model builds on the empirical observation that trails are usually conspicuous structures in natural environments. This hypothesis is confirmed by the experimental results, where a strong positive correlation between trail location and visual saliency has been observed. These results are due in part to the proposed extensions to a well known visual saliency computational model. This paper goes further and shows that, with a proper analysis of the saliency information alone, the ambiguity regarding both trail's position and approximate skeleton is reduced to three hypotheses in 98{\%} of the tested natural images. This analysis is performed by a set of agents inhabiting the saliency and feature specific intermediate maps. These agents' behaviours exploit implicit, top-down knowledge about the object being sought in an active way. With the proposed model, computationally demanding accurate trail detectors are able to focus their activity in a fraction of the input image, thus promoting robustness and real-time performance.",
author = "{Barata Oliveira}, {Jos{\'e} Ant{\'o}nio} and {DEE Group Author}",
year = "2010",
month = "1",
day = "1",
doi = "10.1109/ROBOT.2010.5509929",
language = "Unknown",
pages = "1426--1431",
booktitle = "IEEE Conference Proceedings",

}

Barata Oliveira, JA & DEE Group Author 2010, A saliency-based approach to boost trail detection. in IEEE Conference Proceedings. pp. 1426-1431, 2010 IEEE International Conference on Robotics and Automation (ICRA), 1/01/10. https://doi.org/10.1109/ROBOT.2010.5509929

A saliency-based approach to boost trail detection. / Barata Oliveira, José António; DEE Group Author.

IEEE Conference Proceedings. 2010. p. 1426-1431.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A saliency-based approach to boost trail detection

AU - Barata Oliveira, José António

AU - DEE Group Author

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This paper presents a saliency-based solution to boost trail detection. The proposed model builds on the empirical observation that trails are usually conspicuous structures in natural environments. This hypothesis is confirmed by the experimental results, where a strong positive correlation between trail location and visual saliency has been observed. These results are due in part to the proposed extensions to a well known visual saliency computational model. This paper goes further and shows that, with a proper analysis of the saliency information alone, the ambiguity regarding both trail's position and approximate skeleton is reduced to three hypotheses in 98% of the tested natural images. This analysis is performed by a set of agents inhabiting the saliency and feature specific intermediate maps. These agents' behaviours exploit implicit, top-down knowledge about the object being sought in an active way. With the proposed model, computationally demanding accurate trail detectors are able to focus their activity in a fraction of the input image, thus promoting robustness and real-time performance.

AB - This paper presents a saliency-based solution to boost trail detection. The proposed model builds on the empirical observation that trails are usually conspicuous structures in natural environments. This hypothesis is confirmed by the experimental results, where a strong positive correlation between trail location and visual saliency has been observed. These results are due in part to the proposed extensions to a well known visual saliency computational model. This paper goes further and shows that, with a proper analysis of the saliency information alone, the ambiguity regarding both trail's position and approximate skeleton is reduced to three hypotheses in 98% of the tested natural images. This analysis is performed by a set of agents inhabiting the saliency and feature specific intermediate maps. These agents' behaviours exploit implicit, top-down knowledge about the object being sought in an active way. With the proposed model, computationally demanding accurate trail detectors are able to focus their activity in a fraction of the input image, thus promoting robustness and real-time performance.

U2 - 10.1109/ROBOT.2010.5509929

DO - 10.1109/ROBOT.2010.5509929

M3 - Conference contribution

SP - 1426

EP - 1431

BT - IEEE Conference Proceedings

ER -