Generic and attribute-specific deep representations for maritime vessels

Berkan Solmaz, Erhan Gundogdu, Veysel Yucesoy, Aykut Koc

Research output: Contribution to journalArticle

Abstract

Fine-grained visual categorization has recently received great attention as the volumes of labeled datasets for classification of specific objects, such as cars, bird species, and air-crafts, have been increasing. The availability of large datasets led to significant performance improvements in several vision-based classification tasks. Visual classification of maritime vessels is another important task, assisting naval security and surveillance applications. We introduced, MARVEL, a large-scale image dataset for maritime vessels, consisting of 2 million user-uploaded images and their various attributes, including vessel identity, type, category, year built, length, and tonnage, collected from a community website. The images were categorized into vessel type classes and also into superclasses defined by combining semantically similar classes, following a semi-automatic clustering scheme. For the analysis of the presented dataset, extensive experiments have been performed, involving several potentially useful applications: vessel type classification, identity verification, retrieval, and identity recognition with and without prior vessel type knowledge. Furthermore, we attempted interesting problems of visual marine surveillance such as predicting and classifying maritime vessel attributes such as length, summer deadweight, draught, and gross tonnage by solely interpreting the visual content in the wild, where no additional cues such as scale, orientation, or location are provided. By utilizing generic and attribute-specific deep representations for maritime vessels, we obtained promising results for the aforementioned applications.

Original languageEnglish (US)
Article number22
JournalIPSJ Transactions on Computer Vision and Applications
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2017
Externally publishedYes

Fingerprint

Birds
Websites
Railroad cars
Availability
Air
Experiments

Keywords

  • Convolutional neural networks
  • Deep learning
  • Deep representations for maritime vessels
  • Fine-grained object categorization
  • Maritime vessel attributes
  • Naval surveillance

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Generic and attribute-specific deep representations for maritime vessels. / Solmaz, Berkan; Gundogdu, Erhan; Yucesoy, Veysel; Koc, Aykut.

In: IPSJ Transactions on Computer Vision and Applications, Vol. 9, No. 1, 22, 01.12.2017.

Research output: Contribution to journalArticle

@article{3c258e699b4f4ee5b67bf62f220a910e,
title = "Generic and attribute-specific deep representations for maritime vessels",
abstract = "Fine-grained visual categorization has recently received great attention as the volumes of labeled datasets for classification of specific objects, such as cars, bird species, and air-crafts, have been increasing. The availability of large datasets led to significant performance improvements in several vision-based classification tasks. Visual classification of maritime vessels is another important task, assisting naval security and surveillance applications. We introduced, MARVEL, a large-scale image dataset for maritime vessels, consisting of 2 million user-uploaded images and their various attributes, including vessel identity, type, category, year built, length, and tonnage, collected from a community website. The images were categorized into vessel type classes and also into superclasses defined by combining semantically similar classes, following a semi-automatic clustering scheme. For the analysis of the presented dataset, extensive experiments have been performed, involving several potentially useful applications: vessel type classification, identity verification, retrieval, and identity recognition with and without prior vessel type knowledge. Furthermore, we attempted interesting problems of visual marine surveillance such as predicting and classifying maritime vessel attributes such as length, summer deadweight, draught, and gross tonnage by solely interpreting the visual content in the wild, where no additional cues such as scale, orientation, or location are provided. By utilizing generic and attribute-specific deep representations for maritime vessels, we obtained promising results for the aforementioned applications.",
keywords = "Convolutional neural networks, Deep learning, Deep representations for maritime vessels, Fine-grained object categorization, Maritime vessel attributes, Naval surveillance",
author = "Berkan Solmaz and Erhan Gundogdu and Veysel Yucesoy and Aykut Koc",
year = "2017",
month = "12",
day = "1",
doi = "10.1186/s41074-017-0033-4",
language = "English (US)",
volume = "9",
journal = "IPSJ Transactions on Computer Vision and Applications",
issn = "1882-6695",
publisher = "Information Processing Society of Japan",
number = "1",

}

TY - JOUR

T1 - Generic and attribute-specific deep representations for maritime vessels

AU - Solmaz, Berkan

AU - Gundogdu, Erhan

AU - Yucesoy, Veysel

AU - Koc, Aykut

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Fine-grained visual categorization has recently received great attention as the volumes of labeled datasets for classification of specific objects, such as cars, bird species, and air-crafts, have been increasing. The availability of large datasets led to significant performance improvements in several vision-based classification tasks. Visual classification of maritime vessels is another important task, assisting naval security and surveillance applications. We introduced, MARVEL, a large-scale image dataset for maritime vessels, consisting of 2 million user-uploaded images and their various attributes, including vessel identity, type, category, year built, length, and tonnage, collected from a community website. The images were categorized into vessel type classes and also into superclasses defined by combining semantically similar classes, following a semi-automatic clustering scheme. For the analysis of the presented dataset, extensive experiments have been performed, involving several potentially useful applications: vessel type classification, identity verification, retrieval, and identity recognition with and without prior vessel type knowledge. Furthermore, we attempted interesting problems of visual marine surveillance such as predicting and classifying maritime vessel attributes such as length, summer deadweight, draught, and gross tonnage by solely interpreting the visual content in the wild, where no additional cues such as scale, orientation, or location are provided. By utilizing generic and attribute-specific deep representations for maritime vessels, we obtained promising results for the aforementioned applications.

AB - Fine-grained visual categorization has recently received great attention as the volumes of labeled datasets for classification of specific objects, such as cars, bird species, and air-crafts, have been increasing. The availability of large datasets led to significant performance improvements in several vision-based classification tasks. Visual classification of maritime vessels is another important task, assisting naval security and surveillance applications. We introduced, MARVEL, a large-scale image dataset for maritime vessels, consisting of 2 million user-uploaded images and their various attributes, including vessel identity, type, category, year built, length, and tonnage, collected from a community website. The images were categorized into vessel type classes and also into superclasses defined by combining semantically similar classes, following a semi-automatic clustering scheme. For the analysis of the presented dataset, extensive experiments have been performed, involving several potentially useful applications: vessel type classification, identity verification, retrieval, and identity recognition with and without prior vessel type knowledge. Furthermore, we attempted interesting problems of visual marine surveillance such as predicting and classifying maritime vessel attributes such as length, summer deadweight, draught, and gross tonnage by solely interpreting the visual content in the wild, where no additional cues such as scale, orientation, or location are provided. By utilizing generic and attribute-specific deep representations for maritime vessels, we obtained promising results for the aforementioned applications.

KW - Convolutional neural networks

KW - Deep learning

KW - Deep representations for maritime vessels

KW - Fine-grained object categorization

KW - Maritime vessel attributes

KW - Naval surveillance

UR - http://www.scopus.com/inward/record.url?scp=85042782387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042782387&partnerID=8YFLogxK

U2 - 10.1186/s41074-017-0033-4

DO - 10.1186/s41074-017-0033-4

M3 - Article

AN - SCOPUS:85042782387

VL - 9

JO - IPSJ Transactions on Computer Vision and Applications

JF - IPSJ Transactions on Computer Vision and Applications

SN - 1882-6695

IS - 1

M1 - 22

ER -