The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A detecção de limites é um dos problemas mais estudados em visão computacional. É a base do agrupamento de contornos e inicialmente afeta o desempenho dos algoritmos de agrupamento. Neste artigo, propomos um novo algoritmo de detecção de limites para agrupamento de contornos, que é um modelo de pirâmide em escala grossa a fina guiado por atenção seletiva. Nosso algoritmo avalia cada aresta em vez de cada localização de pixel, que é diferente dos outros e adequado para agrupamento de contornos. A atenção seletiva concentra-se em todos os objetos salientes, em vez de nos detalhes locais, e fornece uma prioridade espacial global para a existência de limites dos objetos. O processo de evolução das arestas, da escala mais grosseira até a escala mais fina, reflete a importância e a energia das arestas. A combinação dessas duas pistas produz os limites mais salientes. Mostramos aplicações para detecção de limites em imagens naturais. Também testamos nossa abordagem no conjunto de dados de Berkeley e a usamos para agrupamento de contornos. Os resultados obtidos são muito bons.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Jingjing ZHONG, Siwei LUO, Qi ZOU, "Visual Attention Guided Multi-Scale Boundary Detection in Natural Images for Contour Grouping" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 3, pp. 555-558, March 2009, doi: 10.1587/transinf.E92.D.555.
Abstract: Boundary detection is one of the most studied problems in computer vision. It is the foundation of contour grouping, and initially affects the performance of grouping algorithms. In this paper we propose a novel boundary detection algorithm for contour grouping, which is a selective attention guided coarse-to-fine scale pyramid model. Our algorithm evaluates each edge instead of each pixel location, which is different from others and suitable for contour grouping. Selective attention focuses on the whole saliency objects instead of local details, and gives global spatial prior for boundary existence of objects. The evolving process of edges through the coarsest scale to the finest scale reflects the importance and energy of edges. The combination of these two cues produces the most saliency boundaries. We show applications for boundary detection on natural images. We also test our approach on the Berkeley dataset and use it for contour grouping. The results obtained are pretty good.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.555/_p
Copiar
@ARTICLE{e92-d_3_555,
author={Jingjing ZHONG, Siwei LUO, Qi ZOU, },
journal={IEICE TRANSACTIONS on Information},
title={Visual Attention Guided Multi-Scale Boundary Detection in Natural Images for Contour Grouping},
year={2009},
volume={E92-D},
number={3},
pages={555-558},
abstract={Boundary detection is one of the most studied problems in computer vision. It is the foundation of contour grouping, and initially affects the performance of grouping algorithms. In this paper we propose a novel boundary detection algorithm for contour grouping, which is a selective attention guided coarse-to-fine scale pyramid model. Our algorithm evaluates each edge instead of each pixel location, which is different from others and suitable for contour grouping. Selective attention focuses on the whole saliency objects instead of local details, and gives global spatial prior for boundary existence of objects. The evolving process of edges through the coarsest scale to the finest scale reflects the importance and energy of edges. The combination of these two cues produces the most saliency boundaries. We show applications for boundary detection on natural images. We also test our approach on the Berkeley dataset and use it for contour grouping. The results obtained are pretty good.},
keywords={},
doi={10.1587/transinf.E92.D.555},
ISSN={1745-1361},
month={March},}
Copiar
TY - JOUR
TI - Visual Attention Guided Multi-Scale Boundary Detection in Natural Images for Contour Grouping
T2 - IEICE TRANSACTIONS on Information
SP - 555
EP - 558
AU - Jingjing ZHONG
AU - Siwei LUO
AU - Qi ZOU
PY - 2009
DO - 10.1587/transinf.E92.D.555
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2009
AB - Boundary detection is one of the most studied problems in computer vision. It is the foundation of contour grouping, and initially affects the performance of grouping algorithms. In this paper we propose a novel boundary detection algorithm for contour grouping, which is a selective attention guided coarse-to-fine scale pyramid model. Our algorithm evaluates each edge instead of each pixel location, which is different from others and suitable for contour grouping. Selective attention focuses on the whole saliency objects instead of local details, and gives global spatial prior for boundary existence of objects. The evolving process of edges through the coarsest scale to the finest scale reflects the importance and energy of edges. The combination of these two cues produces the most saliency boundaries. We show applications for boundary detection on natural images. We also test our approach on the Berkeley dataset and use it for contour grouping. The results obtained are pretty good.
ER -