Deakin University
Browse

Urban zoning using higher-order Markov random fields on multi-view imagery data

Version 2 2024-06-06, 02:45
Version 1 2019-04-08, 13:16
conference contribution
posted on 2024-06-06, 02:45 authored by T Feng, QT Truong, Duc Thanh NguyenDuc Thanh Nguyen, JY Koh, LF Yu, A Binder, SK Yeung
Urban zoning enables various applications in land use analysis and urban planning. As cities evolve, it is important to constantly update the zoning maps of cities to reflect urban pattern changes. This paper proposes a method for automatic urban zoning using higher-order Markov random fields (HO-MRF) built on multi-view imagery data including street-view photos and top-view satellite images. In the proposed HO-MRF, top-view satellite data is segmented via a multi-scale deep convolutional neural network (MS-CNN) and used in lower-order potentials. Street-view data with geo-tagged information is augmented in higher-order potentials. Various feature types for classifying street-view images were also investigated in our work. We evaluated the proposed method on a number of famous metropolises and provided in-depth analysis on technical issues.

History

Volume

11212

Pagination

627-644

Location

Munich, Germany

Start date

2018-09-08

End date

2018-09-14

ISSN

0302-9743

eISSN

1611-3349

ISBN-13

9783030012366

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2018, Springer Nature Switzerland AG

Editor/Contributor(s)

Ferrari V, Hebert M, Sminchisescu C, Weiss Y

Title of proceedings

ECCV 2018 : Proceedings of the European Conference on Computer Vision

Event

Computer Vision Foundation. Conference (2018 : Munich, Germany)

Publisher

Springer

Place of publication

Cham, Switzerland

Series

Computer Vision Foundation Conference

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC