Landscape units estimation in WorldView-2 images by using segmented urban areas, green areas and water bodies for monitoring variation/evolution of cities

Alejandro Ramirez, Erwin Dianderas, Guillermo Kemper

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

2 Scopus citations

Abstract

This work proposes a method to estimate landscape units contained in a region (using satellite WorldView-2 imagery as input) for urban planning. Number of landscape units contained in a region and their extension are estimated by a graph-based segmentation algorithm while the composition of each landscape unit is estimated by a modular neural network. The proposed method, despite of the subjectivity of what represents a landscape unit, achieves the following results: vegetation estimation accuracy: 99.58%, water estimation accuracy: 98.08%, urban area estimation accuracy: 90.38% and soil estimation accuracy: 90.25%, over 2400 testing pixels (600 pixels/image-4 satellite images).

Original languageEnglish
Title of host publication2015 20th Symposium on Signal Processing, Images and Computer Vision, STSIVA 2015 - Conference Proceedings
EditorsPedro Vizcaya Guarin, Lorena Garcia Posada
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467394611
DOIs
StatePublished - 16 Nov 2015
Externally publishedYes
Event20th Symposium on Signal Processing, Images and Computer Vision, STSIVA 2015 - Bogota, Colombia
Duration: 2 Sep 20154 Sep 2015

Publication series

Name2015 20th Symposium on Signal Processing, Images and Computer Vision, STSIVA 2015 - Conference Proceedings

Conference

Conference20th Symposium on Signal Processing, Images and Computer Vision, STSIVA 2015
Country/TerritoryColombia
CityBogota
Period2/09/154/09/15

Fingerprint

Dive into the research topics of 'Landscape units estimation in WorldView-2 images by using segmented urban areas, green areas and water bodies for monitoring variation/evolution of cities'. Together they form a unique fingerprint.

Cite this