Ship detection based on spatio-temporal features

Satoru Suzuki, Yasue Mitsukura, Tadasuke Furuya

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

1 Citation (Scopus)

Abstract

The paper proposes the ship detection method based on Spatio-temporal Histograms of Oriented Gradients (STHOG) feature and Support Vector Machine (SVM). STHOG feature, which is the extension version of HOG feature, enables extract spatial and temporal features of an object. The ship detector based on HOG feature can wrongly detect the similar shape objects with ships. On the other hand, the ship detector based on STHOG feature can identify them successfully by utilizing temporal feature of an object. To extract temporal feature of an object, image registration is implemented and an image displacement by camera motion is corrected. Due to high dimensionality of STHOG feature, it requires high computational cost to scan entire image and find ship regions. Principal Component Analysis (PCA) is applied to STHOG feature to compress the dimension. In the computer simulations, the ship detection performance of the proposed method was evaluated. From the simulation results, our proposed method exhibited better results than ship detector based on PCA+HOG feature.

Original languageEnglish
Title of host publication10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages93-98
Number of pages6
ISBN (Print)9781479957170
DOIs
Publication statusPublished - 2014 Jan 22
Event10th France-Japan/8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014 - Tokyo, Japan
Duration: 2014 Nov 272014 Nov 29

Other

Other10th France-Japan/8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014
CountryJapan
CityTokyo
Period14/11/2714/11/29

Fingerprint

Ships
Detectors
Principal component analysis
Image registration
Support vector machines
Cameras
Computer simulation
Costs

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Suzuki, S., Mitsukura, Y., & Furuya, T. (2014). Ship detection based on spatio-temporal features. In 10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014 (pp. 93-98). [7018610] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MECATRONICS.2014.7018610

Ship detection based on spatio-temporal features. / Suzuki, Satoru; Mitsukura, Yasue; Furuya, Tadasuke.

10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 93-98 7018610.

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

Suzuki, S, Mitsukura, Y & Furuya, T 2014, Ship detection based on spatio-temporal features. in 10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014., 7018610, Institute of Electrical and Electronics Engineers Inc., pp. 93-98, 10th France-Japan/8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014, Tokyo, Japan, 14/11/27. https://doi.org/10.1109/MECATRONICS.2014.7018610
Suzuki S, Mitsukura Y, Furuya T. Ship detection based on spatio-temporal features. In 10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 93-98. 7018610 https://doi.org/10.1109/MECATRONICS.2014.7018610
Suzuki, Satoru ; Mitsukura, Yasue ; Furuya, Tadasuke. / Ship detection based on spatio-temporal features. 10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 93-98
@inproceedings{5d3d647c96f646ce89a4bb1506ae5e57,
title = "Ship detection based on spatio-temporal features",
abstract = "The paper proposes the ship detection method based on Spatio-temporal Histograms of Oriented Gradients (STHOG) feature and Support Vector Machine (SVM). STHOG feature, which is the extension version of HOG feature, enables extract spatial and temporal features of an object. The ship detector based on HOG feature can wrongly detect the similar shape objects with ships. On the other hand, the ship detector based on STHOG feature can identify them successfully by utilizing temporal feature of an object. To extract temporal feature of an object, image registration is implemented and an image displacement by camera motion is corrected. Due to high dimensionality of STHOG feature, it requires high computational cost to scan entire image and find ship regions. Principal Component Analysis (PCA) is applied to STHOG feature to compress the dimension. In the computer simulations, the ship detection performance of the proposed method was evaluated. From the simulation results, our proposed method exhibited better results than ship detector based on PCA+HOG feature.",
author = "Satoru Suzuki and Yasue Mitsukura and Tadasuke Furuya",
year = "2014",
month = "1",
day = "22",
doi = "10.1109/MECATRONICS.2014.7018610",
language = "English",
isbn = "9781479957170",
pages = "93--98",
booktitle = "10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Ship detection based on spatio-temporal features

AU - Suzuki, Satoru

AU - Mitsukura, Yasue

AU - Furuya, Tadasuke

PY - 2014/1/22

Y1 - 2014/1/22

N2 - The paper proposes the ship detection method based on Spatio-temporal Histograms of Oriented Gradients (STHOG) feature and Support Vector Machine (SVM). STHOG feature, which is the extension version of HOG feature, enables extract spatial and temporal features of an object. The ship detector based on HOG feature can wrongly detect the similar shape objects with ships. On the other hand, the ship detector based on STHOG feature can identify them successfully by utilizing temporal feature of an object. To extract temporal feature of an object, image registration is implemented and an image displacement by camera motion is corrected. Due to high dimensionality of STHOG feature, it requires high computational cost to scan entire image and find ship regions. Principal Component Analysis (PCA) is applied to STHOG feature to compress the dimension. In the computer simulations, the ship detection performance of the proposed method was evaluated. From the simulation results, our proposed method exhibited better results than ship detector based on PCA+HOG feature.

AB - The paper proposes the ship detection method based on Spatio-temporal Histograms of Oriented Gradients (STHOG) feature and Support Vector Machine (SVM). STHOG feature, which is the extension version of HOG feature, enables extract spatial and temporal features of an object. The ship detector based on HOG feature can wrongly detect the similar shape objects with ships. On the other hand, the ship detector based on STHOG feature can identify them successfully by utilizing temporal feature of an object. To extract temporal feature of an object, image registration is implemented and an image displacement by camera motion is corrected. Due to high dimensionality of STHOG feature, it requires high computational cost to scan entire image and find ship regions. Principal Component Analysis (PCA) is applied to STHOG feature to compress the dimension. In the computer simulations, the ship detection performance of the proposed method was evaluated. From the simulation results, our proposed method exhibited better results than ship detector based on PCA+HOG feature.

UR - http://www.scopus.com/inward/record.url?scp=84949922983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949922983&partnerID=8YFLogxK

U2 - 10.1109/MECATRONICS.2014.7018610

DO - 10.1109/MECATRONICS.2014.7018610

M3 - Conference contribution

SN - 9781479957170

SP - 93

EP - 98

BT - 10th France-Japan Congress, 8th Europe-Asia Congress on Mecatronics, MECATRONICS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -