Fast and Accurate Sea-Land Segmentation based on Improved SeNet and Coastline Database for Large-Scale Image

Longyuan He, Qizhi Xu, Haimiao Hu, Jing Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Sea-land segmentation is an important and key procedure for the ocean target detection. Owing to complex coastline environment, the existing sea-land segmentation algorithms are difficult to extract helpful features while dealing with large-scale satellite remote sensing images. The paper presents a coarse-to-fine sea-land segmentation approach by combining the improved structured edge network (SeNet) and the coastline database. First of all the coarse latitude and longitude of the segmentation points between sea and land is obtained through applying coastline database to remote sensing images. Secondly on the basis of segmentation point, the region around coastline is divided into a group of blocks with 800×800 pixels. Finally SeNet is improved to separate the sea and land of the region. Experiential results on a large data set demonstrated that the proposed method achieved better accuracy and running time than the other methods.

Original languageEnglish
Title of host publication5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018 - Proceedings
EditorsQihao Weng, Paolo Gamba, Ni-Bin Chang, Guangxing Wang, Wanqiang Yao
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538666425
DOIs
Publication statusPublished - 31 Dec 2018
Externally publishedYes
Event5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018 - Xi'an, China
Duration: 18 Jun 201820 Jun 2018

Publication series

Name5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018 - Proceedings

Conference

Conference5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018
Country/TerritoryChina
CityXi'an
Period18/06/1820/06/18

Keywords

  • coastline database
  • sea-land segmentation
  • structured edge network

Fingerprint

Dive into the research topics of 'Fast and Accurate Sea-Land Segmentation based on Improved SeNet and Coastline Database for Large-Scale Image'. Together they form a unique fingerprint.

Cite this