Segmentation of occluded sidewalks in satellite images

Turgay Senlet; Ahmed Elgammal

Segmentation of occluded sidewalks in satellite images

Turgay Senlet, Ahmed Elgammal

SAS - Computer Science

Rutgers, The State University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Scopus citations

Abstract

Accurate segmentation of sidewalks from satellite images can be required in various applications, for example giving walking directions to pedestrians and robot navigation. We propose a framework to construct sidewalk and crosswalk maps from satellite images. This is a challenging task, since typically sidewalks in satellite images are highly occluded by trees and their shadows and also there can be several objects on maps that have similar appearance with sidewalks. In our framework, we initially segment visible sidewalks by their appearance and then complete the tree-occluded areas by posing the problem as an image-inpainting task with multiple priors, which fuses the knowledge about roads, occluders and sidewalk structures. We present successful sidewalk segmentation results from satellite images, where sidewalks are highly occluded by trees.

Original language	English (US)
Title of host publication	ICPR 2012 - 21st International Conference on Pattern Recognition
Pages	805-808
Number of pages	4
State	Published - 2012
Event	21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan Duration: Nov 11 2012 → Nov 15 2012

Publication series

Name	Proceedings - International Conference on Pattern Recognition

Other

Other	21st International Conference on Pattern Recognition, ICPR 2012
Country/Territory	Japan
City	Tsukuba
Period	11/11/12 → 11/15/12

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

@inproceedings{304c8354f6254b5fb4fbfe65575775a5,

title = "Segmentation of occluded sidewalks in satellite images",

abstract = "Accurate segmentation of sidewalks from satellite images can be required in various applications, for example giving walking directions to pedestrians and robot navigation. We propose a framework to construct sidewalk and crosswalk maps from satellite images. This is a challenging task, since typically sidewalks in satellite images are highly occluded by trees and their shadows and also there can be several objects on maps that have similar appearance with sidewalks. In our framework, we initially segment visible sidewalks by their appearance and then complete the tree-occluded areas by posing the problem as an image-inpainting task with multiple priors, which fuses the knowledge about roads, occluders and sidewalk structures. We present successful sidewalk segmentation results from satellite images, where sidewalks are highly occluded by trees.",

author = "Turgay Senlet and Ahmed Elgammal",

year = "2012",

language = "English (US)",

isbn = "9784990644109",

series = "Proceedings - International Conference on Pattern Recognition",

pages = "805--808",

booktitle = "ICPR 2012 - 21st International Conference on Pattern Recognition",

note = "21st International Conference on Pattern Recognition, ICPR 2012 ; Conference date: 11-11-2012 Through 15-11-2012",

}

TY - GEN

T1 - Segmentation of occluded sidewalks in satellite images

AU - Senlet, Turgay

AU - Elgammal, Ahmed

PY - 2012

Y1 - 2012

N2 - Accurate segmentation of sidewalks from satellite images can be required in various applications, for example giving walking directions to pedestrians and robot navigation. We propose a framework to construct sidewalk and crosswalk maps from satellite images. This is a challenging task, since typically sidewalks in satellite images are highly occluded by trees and their shadows and also there can be several objects on maps that have similar appearance with sidewalks. In our framework, we initially segment visible sidewalks by their appearance and then complete the tree-occluded areas by posing the problem as an image-inpainting task with multiple priors, which fuses the knowledge about roads, occluders and sidewalk structures. We present successful sidewalk segmentation results from satellite images, where sidewalks are highly occluded by trees.

AB - Accurate segmentation of sidewalks from satellite images can be required in various applications, for example giving walking directions to pedestrians and robot navigation. We propose a framework to construct sidewalk and crosswalk maps from satellite images. This is a challenging task, since typically sidewalks in satellite images are highly occluded by trees and their shadows and also there can be several objects on maps that have similar appearance with sidewalks. In our framework, we initially segment visible sidewalks by their appearance and then complete the tree-occluded areas by posing the problem as an image-inpainting task with multiple priors, which fuses the knowledge about roads, occluders and sidewalk structures. We present successful sidewalk segmentation results from satellite images, where sidewalks are highly occluded by trees.

UR - http://www.scopus.com/inward/record.url?scp=84874558735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874558735&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9784990644109

T3 - Proceedings - International Conference on Pattern Recognition

SP - 805

EP - 808

BT - ICPR 2012 - 21st International Conference on Pattern Recognition

T2 - 21st International Conference on Pattern Recognition, ICPR 2012

Y2 - 11 November 2012 through 15 November 2012

ER -

Segmentation of occluded sidewalks in satellite images

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this