• 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.) | Shen, Haijian (Shen, Haijian.) | Rehman, Sadaqat Ur (Rehman, Sadaqat Ur.) | Liu, Zhaoying (Liu, Zhaoying.) | Li, Yujian (Li, Yujian.) | Rehman, Obaid Ur (Rehman, Obaid Ur.)

收录:

EI Scopus SCIE

摘要:

Ship target segmentation in infrared scenes has always been a hot topic, since it is an important basis and prerequisite for infrared-guided weapons to reliably capture and recognize ship targets in the sea-level background. However, given the small target and fuzzy boundary characteristics of infrared ship images, obtaining accurate pixel-level labels for them is hardly achievable, which brings difficulty to train segmentation networks. To improve the segmentation accuracy of infrared ship images, we propose a two-stage domain adaptation method for infrared ship target segmentation (T-DANet), where the segmentation model is trained using visible ship images with clear target boundaries. In this case, the source domain is the labeled visible ship images, while the target domain is the unlabeled infrared ship images. Specifically, in the first stage, we use an image style transfer network to convert the infrared ship images into those with visible light style, so that the visual disparity between the two domain images can be reduced. Next, the visible, infrared, and converted infrared images are input into the Deeplab-v2 segmentation network for training, thereby obtaining the initial network weights. At this time, random attention modules are added separately to the low- and high-level spaces of Deeplab-v2, in order to improve its feature extraction capability. In the second stage, we mix the visible and infrared images through region mixing to acquire the mixed domain images, as well as their corresponding labels. Subsequently, Deeplab-v2 is further trained using the mixed domain images to attain better segmentation accuracy. Experimental results on both the home-made visible-infrared ship (VI-Ship) image dataset and the public infrared image dataset are superior to those existing mainstream methods, demonstrating its effectiveness.

关键词:

style transfer two-stage ship target segmentation Attention mechanism domain adaptation

作者机构:

  • [ 1 ] [Zhang, Ting]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Shen, Haijian]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 ] [Rehman, Sadaqat Ur]Univ Salford, Sch Sci Engn & Environm, Manchester M5 4WT, England
  • [ 5 ] [Liu, Zhaoying]Guilin Univ Elect Technol, Sch Artificial Intelligence, Guilin 541004, Peoples R China
  • [ 6 ] [Rehman, Obaid Ur]Sarhad Univ Sci & IT, Dept Elect Engn, Peshawar 25000, Pakistan

通讯作者信息:

查看成果更多字段

相关关键词:

来源 :

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

ISSN: 0196-2892

年份: 2023

卷: 61

8 . 2 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 9

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:464/4944096
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