Deep Learning and Spatial Analysis Based Port Detection

被引：3

作者：

Li Zeming ^{[1
]}

Cheng Liang ^{[2
,3
,4
,5
]}

Zhu Daming ^{[1
]}

Yan Zhaojin ^{[2
,3
]}

Ji Chen ^{[2
,3
]}

Duan Zhixin ^{[2
,3
]}

Jing Min ^{[2
]}

Li Ning ^{[2
]}

Dongye Shengkun ^{[1
]}

Song Yanruo ^{[1
]}

Liu Jiahui ^{[6
]}

机构：

[1] Kunming Univ Sci & Technol, Fac Land & Resources Engn, Kunming 650093, Yunnan, Peoples R China

[2] Nanjing Univ, Sch Geog & Ocean Sci, Nanjing 210023, Jiangsu, Peoples R China

[3] Collaborat Innovat Ctr South China Sea Studies, Nanjing 210023, Jiangsu, Peoples R China

[4] Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Jiangsu, Peoples R China

[5] Jiangsu Ctr Collaborat Innovat Novel Software Tec, Nanjing 210023, Jiangsu, Peoples R China

[6] Southwest Forestry Univ, Sch Geog & Ecotourism, Kunming 650051, Yunnan, Peoples R China

来源：

LASER & OPTOELECTRONICS PROGRESS | 2021年 / 58卷 / 20期

关键词：

remote sensing; optical remote sensing image; target detection; port; wharf; Yolo v3; sliding window;

D O I：

10.3788/LOP202158.2028002

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In view of the difficulty of automatic port recognition, the ship-wharf-port progressive recognition model is proposed by combining deep learning and geospatial analysis on high-resolution visible light remote sensing images. Firstly, the constructed wharf sample data set is enhanced, and the enhanced data set is used to train the YOLO v3 algorithm. Then, the multi-scale recognition is carried out by the sliding window on the large remote sensing images, and the underlying features of the images are obtained to calculate the wharf categories and pixel coordinates. Finally, the locations of wharves are transformed into geographical coordinates, and the Getis-Ord Gi* statistical method is used to analyze the hot spots. The classical density clustering method is used to identify and extract the locations and ranges of ports. The recognition comparison results in the experimental area show that the proportion of port basin recognition by improved model reaches 82.79% at aggregated threshold of 1000 m.

引用

页数：9

共 24 条

[1]

[Anonymous], 2018, GUANGDIAN GONGCHENG

[2] Cascade R-CNN: Delving into High Quality Object Detection [J].

Cai, Zhaowei ;

Vasconcelos, Nuno .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :6154-6162

[3] Fast Automatic Airport Detection in Remote Sensing Images Using Convolutional Neural Networks [J].

Chen, Fen ;

Ren, Ruilong ;

Van de Voorde, Tim ;

Xu, Wenbo ;

Zhou, Guiyun ;

Zhou, Yan .

REMOTE SENSING, 2018, 10 (03)

[4]

Chen Q, 2010, 2010 2 INT C FUT COM, pV1

[5]

Dai J, 2016, PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), P1796, DOI 10.1109/ICIT.2016.7475036

[6] Airplane Detection of Optical Remote Sensing Images Based on Deep Learning [J].

Dong Yongfeng ;

Zhang Changtao ;

Wang Peng ;

Feng Zhe .

LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (04)

[7] Review of Deep Learning Based Object Detection Methods and Their Mainstream Frameworks [J].

Duan Zhongjing ;

Li Shaobo ;

Hu Jianjun ;

Yang Jing ;

Wang Zheng .

LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (12)

[8] NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection [J].

Ghiasi, Golnaz ;

Lin, Tsung-Yi ;

Le, Quoc V. .

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :7029-7038

[9]

Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1

[10] Airport Scene Aircraft Detection Method Based on YOLO v3 [J].

Guo Jinxiang ;

Liu Libo ;

Xu Feng ;

Zheng Bin .

LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (19)

← 1 2 3 →