Deep Fully Convolutional Networks for Cadastral Boundary Detection from UAV Images

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

There is a growing demand for cheap and fast cadastral mapping methods to face the challenge of 70% global unregistered land rights. As traditional on-site field surveying is time-consuming and labor intensive, imagery-based cadastral mapping has in recent years been advocated by fit-for-purpose (FFP) land administration. However, owing to the semantic gap between the high-level cadastral boundary concept and low-level visual cues in the imagery, improving the accuracy of automatic boundary delineation remains a major challenge. In this research, we use imageries acquired by Unmanned Aerial Vehicles (UAV) to explore the potential of deep Fully Convolutional Networks (FCNs) for cadastral boundary detection in urban and semi-urban areas. We test the performance of FCNs against other state-of-the-art techniques, including Multi-Resolution Segmentation (MRS) and Globalized Probability of Boundary (gPb) in two case study sites in Rwanda. Experimental results show that FCNs outperformed MRS and gPb in both study areas and achieved an average accuracy of 0.79 in precision, 0.37 in recall and 0.50 in F-score. In conclusion, FCNs are able to effectively extract cadastral boundaries, especially when a large proportion of cadastral boundaries are visible. This automated method could minimize manual digitization and reduce field work, thus facilitating the current cadastral mapping and updating practices.
Original languageEnglish
Article number1725
JournalRemote sensing
Volume11
Issue number14
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

imagery
segmentation
land rights
digitization
mapping method
visual cue
detection
vehicle
surveying
fieldwork
urban area
labor
method
demand
test
land
state of the art

Keywords

  • ITC-ISI-JOURNAL-ARTICLE
  • ITC-GOLD

Cite this

@article{a4e6a109bd304b2a876592c4e657bbbf,
title = "Deep Fully Convolutional Networks for Cadastral Boundary Detection from UAV Images",
abstract = "There is a growing demand for cheap and fast cadastral mapping methods to face the challenge of 70{\%} global unregistered land rights. As traditional on-site field surveying is time-consuming and labor intensive, imagery-based cadastral mapping has in recent years been advocated by fit-for-purpose (FFP) land administration. However, owing to the semantic gap between the high-level cadastral boundary concept and low-level visual cues in the imagery, improving the accuracy of automatic boundary delineation remains a major challenge. In this research, we use imageries acquired by Unmanned Aerial Vehicles (UAV) to explore the potential of deep Fully Convolutional Networks (FCNs) for cadastral boundary detection in urban and semi-urban areas. We test the performance of FCNs against other state-of-the-art techniques, including Multi-Resolution Segmentation (MRS) and Globalized Probability of Boundary (gPb) in two case study sites in Rwanda. Experimental results show that FCNs outperformed MRS and gPb in both study areas and achieved an average accuracy of 0.79 in precision, 0.37 in recall and 0.50 in F-score. In conclusion, FCNs are able to effectively extract cadastral boundaries, especially when a large proportion of cadastral boundaries are visible. This automated method could minimize manual digitization and reduce field work, thus facilitating the current cadastral mapping and updating practices.",
keywords = "ITC-ISI-JOURNAL-ARTICLE, ITC-GOLD",
author = "Xue Xia and C. Persello and M.N. Koeva",
year = "2019",
month = "1",
day = "1",
doi = "10.3390/rs11141725",
language = "English",
volume = "11",
journal = "Remote sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "14",

}

Deep Fully Convolutional Networks for Cadastral Boundary Detection from UAV Images. / Xia, Xue; Persello, C.; Koeva, M.N.

In: Remote sensing, Vol. 11, No. 14, 1725, 01.01.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Deep Fully Convolutional Networks for Cadastral Boundary Detection from UAV Images

AU - Xia, Xue

AU - Persello, C.

AU - Koeva, M.N.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - There is a growing demand for cheap and fast cadastral mapping methods to face the challenge of 70% global unregistered land rights. As traditional on-site field surveying is time-consuming and labor intensive, imagery-based cadastral mapping has in recent years been advocated by fit-for-purpose (FFP) land administration. However, owing to the semantic gap between the high-level cadastral boundary concept and low-level visual cues in the imagery, improving the accuracy of automatic boundary delineation remains a major challenge. In this research, we use imageries acquired by Unmanned Aerial Vehicles (UAV) to explore the potential of deep Fully Convolutional Networks (FCNs) for cadastral boundary detection in urban and semi-urban areas. We test the performance of FCNs against other state-of-the-art techniques, including Multi-Resolution Segmentation (MRS) and Globalized Probability of Boundary (gPb) in two case study sites in Rwanda. Experimental results show that FCNs outperformed MRS and gPb in both study areas and achieved an average accuracy of 0.79 in precision, 0.37 in recall and 0.50 in F-score. In conclusion, FCNs are able to effectively extract cadastral boundaries, especially when a large proportion of cadastral boundaries are visible. This automated method could minimize manual digitization and reduce field work, thus facilitating the current cadastral mapping and updating practices.

AB - There is a growing demand for cheap and fast cadastral mapping methods to face the challenge of 70% global unregistered land rights. As traditional on-site field surveying is time-consuming and labor intensive, imagery-based cadastral mapping has in recent years been advocated by fit-for-purpose (FFP) land administration. However, owing to the semantic gap between the high-level cadastral boundary concept and low-level visual cues in the imagery, improving the accuracy of automatic boundary delineation remains a major challenge. In this research, we use imageries acquired by Unmanned Aerial Vehicles (UAV) to explore the potential of deep Fully Convolutional Networks (FCNs) for cadastral boundary detection in urban and semi-urban areas. We test the performance of FCNs against other state-of-the-art techniques, including Multi-Resolution Segmentation (MRS) and Globalized Probability of Boundary (gPb) in two case study sites in Rwanda. Experimental results show that FCNs outperformed MRS and gPb in both study areas and achieved an average accuracy of 0.79 in precision, 0.37 in recall and 0.50 in F-score. In conclusion, FCNs are able to effectively extract cadastral boundaries, especially when a large proportion of cadastral boundaries are visible. This automated method could minimize manual digitization and reduce field work, thus facilitating the current cadastral mapping and updating practices.

KW - ITC-ISI-JOURNAL-ARTICLE

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2019/isi/percello_dee.pdf

U2 - 10.3390/rs11141725

DO - 10.3390/rs11141725

M3 - Article

VL - 11

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 14

M1 - 1725

ER -