Semisynthetic versus real-world sonar training data for the classification of mine-like objects

Research output: Contribution to journal › Review › Research › peer-review

Standard

Semisynthetic versus real-world sonar training data for the classification of mine-like objects. / Barngrover, Christopher; Kastner, Ryan; Belongie, Serge.

In: IEEE Journal of Oceanic Engineering, Vol. 40, No. 1, 6716087, 01.01.2015, p. 48-56.

Research output: Contribution to journal › Review › Research › peer-review

Harvard

Barngrover, C, Kastner, R & Belongie, S 2015, 'Semisynthetic versus real-world sonar training data for the classification of mine-like objects', IEEE Journal of Oceanic Engineering, vol. 40, no. 1, 6716087, pp. 48-56. https://doi.org/10.1109/JOE.2013.2291634

APA

Barngrover, C., Kastner, R., & Belongie, S. (2015). Semisynthetic versus real-world sonar training data for the classification of mine-like objects. IEEE Journal of Oceanic Engineering, 40(1), 48-56. [6716087]. https://doi.org/10.1109/JOE.2013.2291634

Vancouver

Barngrover C, Kastner R, Belongie S. Semisynthetic versus real-world sonar training data for the classification of mine-like objects. IEEE Journal of Oceanic Engineering. 2015 Jan 1;40(1):48-56. 6716087. https://doi.org/10.1109/JOE.2013.2291634

Author

Barngrover, Christopher ; Kastner, Ryan ; Belongie, Serge. / Semisynthetic versus real-world sonar training data for the classification of mine-like objects. In: IEEE Journal of Oceanic Engineering. 2015 ; Vol. 40, No. 1. pp. 48-56.

Bibtex

@article{024b855622fb4b029c0aa0e477aea5d4,
title = "Semisynthetic versus real-world sonar training data for the classification of mine-like objects",
abstract = "The detection of mine-like objects (MLOs) in sidescan sonar (SSS) imagery continues to be a challenging task. In practice, subject matter experts tediously analyze images searching for MLOs. In the literature, there are many attempts at automated target recognition (ATR) to detect the MLOs. This paper focuses on the classifiers that use computer vision and machine learning approaches. These techniques require large amounts of data, which is often prohibitive. For this reason, the use of synthetic and semisynthetic data sets for training and testing is commonplace. This paper shows how a simple semisynthetic data creation scheme can be used to pretest these data-hungry training algorithms to determine what features are of value. The paper provides real-world testing and training data sets in addition to the semisynthetic training and testing data sets. The paper considers the Haar-like and local binary pattern (LBP) features with boosting, showing improvements in performance with real classifiers over semisynthetic classifiers and improvements in performance as semisynthetic data set size increases.",
keywords = "Haar-like feature, local binary pattern (LBP), mine-like object (MLO), object detection, sidescan sonar (SSS), synthetic",
author = "Christopher Barngrover and Ryan Kastner and Serge Belongie",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.",
year = "2015",
month = jan,
day = "1",
doi = "10.1109/JOE.2013.2291634",
language = "English",
volume = "40",
pages = "48--56",
journal = "IEEE Journal of Oceanic Engineering",
issn = "0364-9059",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

RIS

TY - JOUR

T1 - Semisynthetic versus real-world sonar training data for the classification of mine-like objects

AU - Barngrover, Christopher

AU - Kastner, Ryan

AU - Belongie, Serge

N1 - Publisher Copyright: © 2015 IEEE.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The detection of mine-like objects (MLOs) in sidescan sonar (SSS) imagery continues to be a challenging task. In practice, subject matter experts tediously analyze images searching for MLOs. In the literature, there are many attempts at automated target recognition (ATR) to detect the MLOs. This paper focuses on the classifiers that use computer vision and machine learning approaches. These techniques require large amounts of data, which is often prohibitive. For this reason, the use of synthetic and semisynthetic data sets for training and testing is commonplace. This paper shows how a simple semisynthetic data creation scheme can be used to pretest these data-hungry training algorithms to determine what features are of value. The paper provides real-world testing and training data sets in addition to the semisynthetic training and testing data sets. The paper considers the Haar-like and local binary pattern (LBP) features with boosting, showing improvements in performance with real classifiers over semisynthetic classifiers and improvements in performance as semisynthetic data set size increases.

AB - The detection of mine-like objects (MLOs) in sidescan sonar (SSS) imagery continues to be a challenging task. In practice, subject matter experts tediously analyze images searching for MLOs. In the literature, there are many attempts at automated target recognition (ATR) to detect the MLOs. This paper focuses on the classifiers that use computer vision and machine learning approaches. These techniques require large amounts of data, which is often prohibitive. For this reason, the use of synthetic and semisynthetic data sets for training and testing is commonplace. This paper shows how a simple semisynthetic data creation scheme can be used to pretest these data-hungry training algorithms to determine what features are of value. The paper provides real-world testing and training data sets in addition to the semisynthetic training and testing data sets. The paper considers the Haar-like and local binary pattern (LBP) features with boosting, showing improvements in performance with real classifiers over semisynthetic classifiers and improvements in performance as semisynthetic data set size increases.

KW - Haar-like feature

KW - local binary pattern (LBP)

KW - mine-like object (MLO)

KW - object detection

KW - sidescan sonar (SSS)

KW - synthetic

UR - http://www.scopus.com/inward/record.url?scp=84920940328&partnerID=8YFLogxK

U2 - 10.1109/JOE.2013.2291634

DO - 10.1109/JOE.2013.2291634

M3 - Review

AN - SCOPUS:84920940328

VL - 40

SP - 48

EP - 56

JO - IEEE Journal of Oceanic Engineering

JF - IEEE Journal of Oceanic Engineering

SN - 0364-9059

IS - 1

M1 - 6716087

ER -

ID: 301829839