BASS

Boundary-Aware Superpixel Segmentation

Antonio Rubio, Longlong Yu, Edgar Simo Serra, Francesc Moreno-Noguer

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

6 Citations (Scopus)

Abstract

We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2824-2829
Number of pages6
ISBN (Electronic)9781509048472
DOIs
Publication statusPublished - 2017 Apr 13
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: 2016 Dec 42016 Dec 8

Other

Other23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period16/12/416/12/8

Fingerprint

Seed
Color

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Rubio, A., Yu, L., Simo Serra, E., & Moreno-Noguer, F. (2017). BASS: Boundary-Aware Superpixel Segmentation. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016 (pp. 2824-2829). [7900064] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2016.7900064

BASS : Boundary-Aware Superpixel Segmentation. / Rubio, Antonio; Yu, Longlong; Simo Serra, Edgar; Moreno-Noguer, Francesc.

2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2824-2829 7900064.

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

Rubio, A, Yu, L, Simo Serra, E & Moreno-Noguer, F 2017, BASS: Boundary-Aware Superpixel Segmentation. in 2016 23rd International Conference on Pattern Recognition, ICPR 2016., 7900064, Institute of Electrical and Electronics Engineers Inc., pp. 2824-2829, 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, Mexico, 16/12/4. https://doi.org/10.1109/ICPR.2016.7900064
Rubio A, Yu L, Simo Serra E, Moreno-Noguer F. BASS: Boundary-Aware Superpixel Segmentation. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2824-2829. 7900064 https://doi.org/10.1109/ICPR.2016.7900064
Rubio, Antonio ; Yu, Longlong ; Simo Serra, Edgar ; Moreno-Noguer, Francesc. / BASS : Boundary-Aware Superpixel Segmentation. 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2824-2829
@inproceedings{d9f95d67b4374aaf97298e6c7732bf00,
title = "BASS: Boundary-Aware Superpixel Segmentation",
abstract = "We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods.",
author = "Antonio Rubio and Longlong Yu and {Simo Serra}, Edgar and Francesc Moreno-Noguer",
year = "2017",
month = "4",
day = "13",
doi = "10.1109/ICPR.2016.7900064",
language = "English",
pages = "2824--2829",
booktitle = "2016 23rd International Conference on Pattern Recognition, ICPR 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - BASS

T2 - Boundary-Aware Superpixel Segmentation

AU - Rubio, Antonio

AU - Yu, Longlong

AU - Simo Serra, Edgar

AU - Moreno-Noguer, Francesc

PY - 2017/4/13

Y1 - 2017/4/13

N2 - We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods.

AB - We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85019163173&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019163173&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2016.7900064

DO - 10.1109/ICPR.2016.7900064

M3 - Conference contribution

SP - 2824

EP - 2829

BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -