• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Fu, Kun (Fu, Kun.) | Li, Yang (Li, Yang.) | Sun, Hao (Sun, Hao.) | Yang, Xue (Yang, Xue.) | Xu, Guangluan (Xu, Guangluan.) | Li, Yuting (Li, Yuting.) | Sun, Xian (Sun, Xian.)

Indexed by:

EI Scopus SCIE

Abstract:

Ship detection plays an important role in automatic remote sensing image interpretation. The scale difference, large aspect ratio of ship, complex remote sensing image background and ship dense parking scene make the detection task difficult. To handle the challenging problems above, we propose a ship rotation detection model based on a Feature Fusion Pyramid Network and deep reinforcement learning (FFPN-RL) in this paper. The detection network can efficiently generate the inclined rectangular box for ship. First, we propose the Feature Fusion Pyramid Network (FFPN) that strengthens the reuse of different scales features, and FFPN can extract the low level location and high level semantic information that has an important impact on multi-scale ship detection and precise location of dense parking ships. Second, in order to get accurate ship angle information, we apply deep reinforcement learning to the inclined ship detection task for the first time. In addition, we put forward prior policy guidance and a long-term training method to train an angle prediction agent constructed through a dueling structure Q network, which is able to iteratively and accurately obtain the ship angle. In addition, we design soft rotation non-maximum suppression to reduce the missed ship detection while suppressing the redundant detection boxes. We carry out detailed experiments on the remote sensing ship image dataset, and the experiments validate that our FFPN-RL ship detection model has efficient detection performance.

Keyword:

ship detection feature map fusion convolution neural network deep reinforcement learning

Author Community:

  • [ 1 ] [Fu, Kun]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China
  • [ 2 ] [Li, Yang]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China
  • [ 3 ] [Sun, Hao]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China
  • [ 4 ] [Yang, Xue]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China
  • [ 5 ] [Xu, Guangluan]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China
  • [ 6 ] [Sun, Xian]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China
  • [ 7 ] [Fu, Kun]Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
  • [ 8 ] [Li, Yang]Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
  • [ 9 ] [Yang, Xue]Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
  • [ 10 ] [Xu, Guangluan]Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
  • [ 11 ] [Sun, Xian]Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
  • [ 12 ] [Li, Yuting]Beijing Univ Technol, Coll Life Sci & Bioengn, Beijing 100124, Peoples R China

Reprint Author's Address:

  • [Li, Yang]Chinese Acad Sci, Inst Elect, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China;;[Li, Yang]Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

REMOTE SENSING

Year: 2018

Issue: 12

Volume: 10

5 . 0 0 0

JCR@2022

ESI Discipline: GEOSCIENCES;

ESI HC Threshold:139

JCR Journal Grade:1

Cited Count:

WoS CC Cited Count: 39

SCOPUS Cited Count: 45

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Online/Total:513/5317111
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.