Large Scale Asset Extraction for Urban Images

Handle URI:
http://hdl.handle.net/10754/622212
Title:
Large Scale Asset Extraction for Urban Images
Authors:
Affara, Lama Ahmed; Nan, Liangliang ( 0000-0002-5629-9975 ) ; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Wonka, Peter ( 0000-0003-0627-9746 )
Abstract:
Object proposals are currently used for increasing the computational efficiency of object detection. We propose a novel adaptive pipeline for interleaving object proposals with object classification and use it as a formulation for asset detection. We first preprocess the images using a novel and efficient rectification technique. We then employ a particle filter approach to keep track of three priors, which guide proposed samples and get updated using classifier output. Tests performed on over 1000 urban images demonstrate that our rectification method is faster than existing methods without loss in quality, and that our interleaved proposal method outperforms current state-of-the-art. We further demonstrate that other methods can be improved by incorporating our interleaved proposals. © Springer International Publishing AG 2016.
KAUST Department:
King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
Citation:
Affara L, Nan L, Ghanem B, Wonka P (2016) Large Scale Asset Extraction for Urban Images. Lecture Notes in Computer Science: 437–452. Available: http://dx.doi.org/10.1007/978-3-319-46487-9_27.
Publisher:
Springer Nature
Journal:
Lecture Notes in Computer Science
Issue Date:
16-Sep-2016
DOI:
10.1007/978-3-319-46487-9_27
Type:
Book Chapter
ISSN:
0302-9743; 1611-3349
Sponsors:
This research work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-319-46466-4_25
Appears in Collections:
Book Chapters

Full metadata record

DC FieldValue Language
dc.contributor.authorAffara, Lama Ahmeden
dc.contributor.authorNan, Liangliangen
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorWonka, Peteren
dc.date.accessioned2017-01-02T08:42:38Z-
dc.date.available2017-01-02T08:42:38Z-
dc.date.issued2016-09-16en
dc.identifier.citationAffara L, Nan L, Ghanem B, Wonka P (2016) Large Scale Asset Extraction for Urban Images. Lecture Notes in Computer Science: 437–452. Available: http://dx.doi.org/10.1007/978-3-319-46487-9_27.en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.doi10.1007/978-3-319-46487-9_27en
dc.identifier.urihttp://hdl.handle.net/10754/622212-
dc.description.abstractObject proposals are currently used for increasing the computational efficiency of object detection. We propose a novel adaptive pipeline for interleaving object proposals with object classification and use it as a formulation for asset detection. We first preprocess the images using a novel and efficient rectification technique. We then employ a particle filter approach to keep track of three priors, which guide proposed samples and get updated using classifier output. Tests performed on over 1000 urban images demonstrate that our rectification method is faster than existing methods without loss in quality, and that our interleaved proposal method outperforms current state-of-the-art. We further demonstrate that other methods can be improved by incorporating our interleaved proposals. © Springer International Publishing AG 2016.en
dc.description.sponsorshipThis research work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-46466-4_25en
dc.titleLarge Scale Asset Extraction for Urban Imagesen
dc.typeBook Chapteren
dc.contributor.departmentKing Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabiaen
dc.identifier.journalLecture Notes in Computer Scienceen
kaust.authorAffara, Lama Ahmeden
kaust.authorNan, Liangliangen
kaust.authorGhanem, Bernarden
kaust.authorWonka, Peteren
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.