• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Zhang, Ting (Zhang, Ting.) | Gao, Zihang (Gao, Zihang.) | Liu, Zhaoying (Liu, Zhaoying.) | Hussain, Syed Fawad (Hussain, Syed Fawad.) | Waqas, Muhammad (Waqas, Muhammad.) | Halim, Zahid (Halim, Zahid.) | Li, Yujian (Li, Yujian.)

收录:

EI Scopus SCIE

摘要:

Infrared ship target segmentation is one of the key technologies for automatically detecting ship targets in ocean monitoring. However, it is a challenging work to achieve accurate target segmentation from the infrared ship image. To improve its segmentation performance, we present an Adversarial Domain Adaptation Network (ADANet) for infrared ship target segmentation, where the labeled visible ship images are used as the source domain and the unlabeled infrared ship images are as the target domain. To address the issue of style difference between the two domains, we preprocess the visible images of the source domain in turn with graying and whitening to convert them into the images with the style of the target domain. For the infrared images in the target domain, we optimize them with a denoising network. Furthermore, to solve the matter of limited receptive field of the discriminator, we design a discriminator based on atrous convolution to improve its discriminative ability. Finally, for the issue of low confidence of the target domain predicted images, we add the information entropy of the target domain predicted images to the adversarial loss. Experimental results on the home-made dataset as well as a public dataset show that infrared ship target segmentation achieves higher mean intersection over union than the state-of-the-art methods without significantly increase of parameters, demonstrating its effectiveness.(c) 2023 Elsevier B.V. All rights reserved.

关键词:

Adversarial learning Domain adaptation Information entropy Infrared ship images Object segmentation

作者机构:

  • [ 1 ] [Zhang, Ting]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Gao, Zihang]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Liu, Zhaoying]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Li, Yujian]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Hussain, Syed Fawad]Univ Birmingham, Sch Comp Sci, Dubai Int Acad City, Dubai 341799, U Arab Emirates
  • [ 6 ] [Waqas, Muhammad]Univ Bahrain, Coll Informat Technol, Comp Engn Dept, Zallaq 32038, Bahrain
  • [ 7 ] [Waqas, Muhammad]Edith Cowan Univ, Sch Engn, Joondalup, WA 6027, Australia
  • [ 8 ] [Halim, Zahid]Ghulam Ishaq Khan Inst Engn Sci & Technol, Fac Comp Sci & Engn, Swabi 23640, Pakistan
  • [ 9 ] [Li, Yujian]Guilin Univ Elect Technol, Sch Artificial Intelligence, Guilin 541004, Peoples R China

通讯作者信息:

  • [Liu, Zhaoying]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;;

查看成果更多字段

相关关键词:

来源 :

KNOWLEDGE-BASED SYSTEMS

ISSN: 0950-7051

年份: 2023

卷: 265

8 . 8 0 0

JCR@2022

ESI学科: COMPUTER SCIENCE;

ESI高被引阀值:19

被引次数:

WoS核心集被引频次: 6

SCOPUS被引频次: 8

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:547/4937289
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司