Ship Detection from Remote Sensing Images Based on Deep Learning

Ziqiang Yuan; Jing Geng; Tianru Dai

doi:10.1007/978-981-13-0893-2_36

Ship Detection from Remote Sensing Images Based on Deep Learning

Ziqiang Yuan, Jing Geng^*, Tianru Dai

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Due to the complicated maritime climate environment, the detection of marine Ship by using Remote sensing images is faced with many challenges in the field of object detection. In this paper, a ship detection method based on dark channel priority haze removal and Faster RCNN is proposed to solve this problem. We label and experiment with thousands of ships images on the sea. Compared with the using of object detection model directly and some traditional methods, the detection accuracy of the new method is obviously improved.

Original language	English
Title of host publication	Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers
Editors	Fuling Bian, Hanning Yuan, Jing Geng, Chuanlu Liu, Tisinee Surapunt
Publisher	Springer Verlag
Pages	336-344
Number of pages	9
ISBN (Print)	9789811308925
DOIs	https://doi.org/10.1007/978-981-13-0893-2_36
Publication status	Published - 2018
Externally published	Yes
Event	5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017 - Chiang Mai, Thailand Duration: 8 Dec 2017 → 10 Dec 2017

Publication series

Name	Communications in Computer and Information Science
Volume	848
ISSN (Print)	1865-0929

Conference

Conference	5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017
Country/Territory	Thailand
City	Chiang Mai
Period	8/12/17 → 10/12/17

Keywords

Deep learn
Faster RCNN
Haze removal
Remote sensing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-13-0893-2_36

Cite this

Yuan, Z., Geng, J., & Dai, T. (2018). Ship Detection from Remote Sensing Images Based on Deep Learning. In F. Bian, H. Yuan, J. Geng, C. Liu, & T. Surapunt (Eds.), Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers (pp. 336-344). (Communications in Computer and Information Science; Vol. 848). Springer Verlag. https://doi.org/10.1007/978-981-13-0893-2_36

Yuan, Ziqiang ; Geng, Jing ; Dai, Tianru. / Ship Detection from Remote Sensing Images Based on Deep Learning. Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers. editor / Fuling Bian ; Hanning Yuan ; Jing Geng ; Chuanlu Liu ; Tisinee Surapunt. Springer Verlag, 2018. pp. 336-344 (Communications in Computer and Information Science).

@inproceedings{81d452e181fb4ce099c130dff3cf9e14,

title = "Ship Detection from Remote Sensing Images Based on Deep Learning",

abstract = "Due to the complicated maritime climate environment, the detection of marine Ship by using Remote sensing images is faced with many challenges in the field of object detection. In this paper, a ship detection method based on dark channel priority haze removal and Faster RCNN is proposed to solve this problem. We label and experiment with thousands of ships images on the sea. Compared with the using of object detection model directly and some traditional methods, the detection accuracy of the new method is obviously improved.",

keywords = "Deep learn, Faster RCNN, Haze removal, Remote sensing",

author = "Ziqiang Yuan and Jing Geng and Tianru Dai",

note = "Publisher Copyright: {\textcopyright} 2018, Springer Nature Singapore Pte Ltd.; 5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017 ; Conference date: 08-12-2017 Through 10-12-2017",

year = "2018",

doi = "10.1007/978-981-13-0893-2_36",

language = "English",

isbn = "9789811308925",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "336--344",

editor = "Fuling Bian and Hanning Yuan and Jing Geng and Chuanlu Liu and Tisinee Surapunt",

booktitle = "Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers",

address = "Germany",

}

Yuan, Z, Geng, J & Dai, T 2018, Ship Detection from Remote Sensing Images Based on Deep Learning. in F Bian, H Yuan, J Geng, C Liu & T Surapunt (eds), Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers. Communications in Computer and Information Science, vol. 848, Springer Verlag, pp. 336-344, 5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017, Chiang Mai, Thailand, 8/12/17. https://doi.org/10.1007/978-981-13-0893-2_36

Ship Detection from Remote Sensing Images Based on Deep Learning. / Yuan, Ziqiang; Geng, Jing; Dai, Tianru.
Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers. ed. / Fuling Bian; Hanning Yuan; Jing Geng; Chuanlu Liu; Tisinee Surapunt. Springer Verlag, 2018. p. 336-344 (Communications in Computer and Information Science; Vol. 848).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Ship Detection from Remote Sensing Images Based on Deep Learning

AU - Yuan, Ziqiang

AU - Geng, Jing

AU - Dai, Tianru

PY - 2018

Y1 - 2018

N2 - Due to the complicated maritime climate environment, the detection of marine Ship by using Remote sensing images is faced with many challenges in the field of object detection. In this paper, a ship detection method based on dark channel priority haze removal and Faster RCNN is proposed to solve this problem. We label and experiment with thousands of ships images on the sea. Compared with the using of object detection model directly and some traditional methods, the detection accuracy of the new method is obviously improved.

AB - Due to the complicated maritime climate environment, the detection of marine Ship by using Remote sensing images is faced with many challenges in the field of object detection. In this paper, a ship detection method based on dark channel priority haze removal and Faster RCNN is proposed to solve this problem. We label and experiment with thousands of ships images on the sea. Compared with the using of object detection model directly and some traditional methods, the detection accuracy of the new method is obviously improved.

KW - Deep learn

KW - Faster RCNN

KW - Haze removal

KW - Remote sensing

UR - http://www.scopus.com/inward/record.url?scp=85049026186&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-0893-2_36

DO - 10.1007/978-981-13-0893-2_36

M3 - Conference contribution

AN - SCOPUS:85049026186

SN - 9789811308925

T3 - Communications in Computer and Information Science

SP - 336

EP - 344

BT - Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers

A2 - Bian, Fuling

A2 - Yuan, Hanning

A2 - Geng, Jing

A2 - Liu, Chuanlu

A2 - Surapunt, Tisinee

PB - Springer Verlag

T2 - 5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017

Y2 - 8 December 2017 through 10 December 2017

ER -

Yuan Z, Geng J, Dai T. Ship Detection from Remote Sensing Images Based on Deep Learning. In Bian F, Yuan H, Geng J, Liu C, Surapunt T, editors, Geo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers. Springer Verlag. 2018. p. 336-344. (Communications in Computer and Information Science). doi: 10.1007/978-981-13-0893-2_36

Ship Detection from Remote Sensing Images Based on Deep Learning

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this