A new region growing based method for ship detection in high-resolution SAR images

Chonglei Wang, Chen Li, Fukun Bi, Liang Chen*

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)

Abstract

High-resolution SAR are of great value in remote sensing nowadays. To make good use of the characteristics of high-resolution SAR images to detect targets, we present here a region growing method. First, we calculate a threshold according to the given PFA to pick up bright pixels as the seeds. Second, we define the criteria which is mainly based on the relationship between pixels in a high-resolution SAR image and then execute the growing process. Finally, we exclude false alarms according to some geometry features. The experiments and results show that it is a constructive and effective way using region growing algorithm to detect ships in high-resolution SAR images.

Original languageEnglish
Publication statusPublished - 2015
EventIET International Radar Conference 2015 - Hangzhou, China
Duration: 14 Oct 201516 Oct 2015

Conference

ConferenceIET International Radar Conference 2015
Country/TerritoryChina
CityHangzhou
Period14/10/1516/10/15

Keywords

  • Region growing
  • SAR
  • Target detection

Fingerprint

Dive into the research topics of 'A new region growing based method for ship detection in high-resolution SAR images'. Together they form a unique fingerprint.

Cite this