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
APA
Vancouver
Author
Bibtex
}
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