Generalized Boundaries from Multiple Image Interpretations
(2014) In IEEE Transactions on Pattern Analysis and Machine Intelligence 36(7). p.1312-1324- Abstract
- Boundary detection is a fundamental computer vision problem that is essential for a variety of tasks, such as contour and region segmentation, symmetry detection and object recognition and categorization. We propose a generalized formulation for boundary detection, with closed-form solution, applicable to the localization of different types of boundaries, such as object edges in natural images and occlusion boundaries from video. Our generalized boundary detection method (Gb) simultaneously combines low-level and mid-level image representations in a single eigenvalue problem and solves for the optimal continuous boundary orientation and strength. The closed-form solution to boundary detection enables our algorithm to achieve... (More)
- Boundary detection is a fundamental computer vision problem that is essential for a variety of tasks, such as contour and region segmentation, symmetry detection and object recognition and categorization. We propose a generalized formulation for boundary detection, with closed-form solution, applicable to the localization of different types of boundaries, such as object edges in natural images and occlusion boundaries from video. Our generalized boundary detection method (Gb) simultaneously combines low-level and mid-level image representations in a single eigenvalue problem and solves for the optimal continuous boundary orientation and strength. The closed-form solution to boundary detection enables our algorithm to achieve state-of-the-art results at a significantly lower computational cost than current methods. We also propose two complementary novel components that can seamlessly be combined with Gb: first, we introduce a soft-segmentation procedure that provides region input layers to our boundary detection algorithm for a significant improvement in accuracy, at negligible computational cost; second, we present an efficient method for contour grouping and reasoning, which when applied as a final post-processing stage, further increases the boundary detection performance. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4602780
- author
- Leordeanu, Marius ; Sukthankar, Rahul and Sminchisescu, Cristian LU
- organization
- publishing date
- 2014
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Edge, boundary and contour detection, occlusion boundaries, soft image, segmentation, computer vision
- in
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- volume
- 36
- issue
- 7
- pages
- 1312 - 1324
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- wos:000338209900003
- scopus:84903157998
- pmid:26353305
- ISSN
- 1939-3539
- DOI
- 10.1109/TPAMI.2014.17
- language
- English
- LU publication?
- yes
- id
- d8441854-8519-4970-aed3-e95f45f76f81 (old id 4602780)
- date added to LUP
- 2016-04-01 13:44:06
- date last changed
- 2022-05-15 06:47:10
@article{d8441854-8519-4970-aed3-e95f45f76f81,
abstract = {{Boundary detection is a fundamental computer vision problem that is essential for a variety of tasks, such as contour and region segmentation, symmetry detection and object recognition and categorization. We propose a generalized formulation for boundary detection, with closed-form solution, applicable to the localization of different types of boundaries, such as object edges in natural images and occlusion boundaries from video. Our generalized boundary detection method (Gb) simultaneously combines low-level and mid-level image representations in a single eigenvalue problem and solves for the optimal continuous boundary orientation and strength. The closed-form solution to boundary detection enables our algorithm to achieve state-of-the-art results at a significantly lower computational cost than current methods. We also propose two complementary novel components that can seamlessly be combined with Gb: first, we introduce a soft-segmentation procedure that provides region input layers to our boundary detection algorithm for a significant improvement in accuracy, at negligible computational cost; second, we present an efficient method for contour grouping and reasoning, which when applied as a final post-processing stage, further increases the boundary detection performance.}},
author = {{Leordeanu, Marius and Sukthankar, Rahul and Sminchisescu, Cristian}},
issn = {{1939-3539}},
keywords = {{Edge; boundary and contour detection; occlusion boundaries; soft image; segmentation; computer vision}},
language = {{eng}},
number = {{7}},
pages = {{1312--1324}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}},
title = {{Generalized Boundaries from Multiple Image Interpretations}},
url = {{http://dx.doi.org/10.1109/TPAMI.2014.17}},
doi = {{10.1109/TPAMI.2014.17}},
volume = {{36}},
year = {{2014}},
}