Comparing Human Versus Machine-Driven Cadastral Boundary Feature Extraction

Emmanuel Nyandwi (Corresponding Author), M.N. Koeva, D. Kohli, Rohan Bennett

Research output: Contribution to journalArticleAcademicpeer-review

8 Downloads (Pure)

Abstract

The objective to fast-track the mapping and registration of large numbers of unrecorded land rights globally, leads to the experimental application of Artificial Intelligence in the domain of land administration, and specifically the application of automated visual cognition techniques for cadastral mapping tasks. In this research, we applied and compared the ability of rule-based systems within Object Based Image Analysis (OBIA), as opposed to human analysis, to extract visible cadastral boundaries from very high-resolution World View-2 image, in both rural and urban settings. From our experiments, machine-based techniques were able to automatically delineate a good proportion of rural parcels with explicit polygons where the correctness of the automatically extracted boundaries was 47.4% against 74.24% for humans and the completeness of 45% for machine, as against 70.4% for humans. On the contrary, in the urban area, automatic results were counterintuitive: even though urban plots and buildings are clearly marked with visible features such as fences, roads and tacitly perceptible to eyes, automation resulted in geometrically and topologically poorly structured data, that could neither be geometrically compared with human digitisationed, nor actual cadastral data from the field. These results provide an updated snapshot with regards to the performance of contemporary machine-drive feature extraction techniques compared to conventional manual digitising. In our methodology, using an iterative approach of segmentation and classification, we demonstrated how to overcome the weaknesses of having undesirable segments due to intra-parcels and inter-parcels variability, when using segmentation approaches for cadastral feature delineation. We also demonstrated how we can easily implement a geometric comparison framework within the ArcGIS environment and firmly believe the developed methodology can be reproduced.
Original languageEnglish
Number of pages27
JournalRemote sensing
Volume11
Issue number14
DOIs
Publication statusPublished - 12 Jul 2019

Fingerprint

segmentation
land rights
methodology
artificial intelligence
cognition
polygon
automation
image analysis
urban area
road
experiment
analysis
registration
applied research
land
comparison
digitising

Keywords

  • Cadastral intelligence; Manual digitisation; Expert parameterisation; Land administration; Land Management; Automatic Feature Extraction; Object Based Image Analysis.
  • cadastral intelligence; manual digitisation; expert parameterisation; land administration; land management; automatic feature extraction; Object-Based Image Analysis
  • ITC-ISI-JOURNAL-ARTICLE
  • ITC-GOLD

Cite this

@article{9e70d9f4d639490483b49daf994aef54,
title = "Comparing Human Versus Machine-Driven Cadastral Boundary Feature Extraction",
abstract = "The objective to fast-track the mapping and registration of large numbers of unrecorded land rights globally, leads to the experimental application of Artificial Intelligence in the domain of land administration, and specifically the application of automated visual cognition techniques for cadastral mapping tasks. In this research, we applied and compared the ability of rule-based systems within Object Based Image Analysis (OBIA), as opposed to human analysis, to extract visible cadastral boundaries from very high-resolution World View-2 image, in both rural and urban settings. From our experiments, machine-based techniques were able to automatically delineate a good proportion of rural parcels with explicit polygons where the correctness of the automatically extracted boundaries was 47.4{\%} against 74.24{\%} for humans and the completeness of 45{\%} for machine, as against 70.4{\%} for humans. On the contrary, in the urban area, automatic results were counterintuitive: even though urban plots and buildings are clearly marked with visible features such as fences, roads and tacitly perceptible to eyes, automation resulted in geometrically and topologically poorly structured data, that could neither be geometrically compared with human digitisationed, nor actual cadastral data from the field. These results provide an updated snapshot with regards to the performance of contemporary machine-drive feature extraction techniques compared to conventional manual digitising. In our methodology, using an iterative approach of segmentation and classification, we demonstrated how to overcome the weaknesses of having undesirable segments due to intra-parcels and inter-parcels variability, when using segmentation approaches for cadastral feature delineation. We also demonstrated how we can easily implement a geometric comparison framework within the ArcGIS environment and firmly believe the developed methodology can be reproduced.",
keywords = "Cadastral intelligence; Manual digitisation; Expert parameterisation; Land administration; Land Management; Automatic Feature Extraction; Object Based Image Analysis., cadastral intelligence; manual digitisation; expert parameterisation; land administration; land management; automatic feature extraction; Object-Based Image Analysis, ITC-ISI-JOURNAL-ARTICLE, ITC-GOLD",
author = "Emmanuel Nyandwi and M.N. Koeva and D. Kohli and Rohan Bennett",
year = "2019",
month = "7",
day = "12",
doi = "10.3390/rs11141662",
language = "English",
volume = "11",
journal = "Remote sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "14",

}

Comparing Human Versus Machine-Driven Cadastral Boundary Feature Extraction. / Nyandwi, Emmanuel (Corresponding Author); Koeva, M.N.; Kohli, D.; Bennett, Rohan.

In: Remote sensing, Vol. 11, No. 14, 12.07.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Comparing Human Versus Machine-Driven Cadastral Boundary Feature Extraction

AU - Nyandwi, Emmanuel

AU - Koeva, M.N.

AU - Kohli, D.

AU - Bennett, Rohan

PY - 2019/7/12

Y1 - 2019/7/12

N2 - The objective to fast-track the mapping and registration of large numbers of unrecorded land rights globally, leads to the experimental application of Artificial Intelligence in the domain of land administration, and specifically the application of automated visual cognition techniques for cadastral mapping tasks. In this research, we applied and compared the ability of rule-based systems within Object Based Image Analysis (OBIA), as opposed to human analysis, to extract visible cadastral boundaries from very high-resolution World View-2 image, in both rural and urban settings. From our experiments, machine-based techniques were able to automatically delineate a good proportion of rural parcels with explicit polygons where the correctness of the automatically extracted boundaries was 47.4% against 74.24% for humans and the completeness of 45% for machine, as against 70.4% for humans. On the contrary, in the urban area, automatic results were counterintuitive: even though urban plots and buildings are clearly marked with visible features such as fences, roads and tacitly perceptible to eyes, automation resulted in geometrically and topologically poorly structured data, that could neither be geometrically compared with human digitisationed, nor actual cadastral data from the field. These results provide an updated snapshot with regards to the performance of contemporary machine-drive feature extraction techniques compared to conventional manual digitising. In our methodology, using an iterative approach of segmentation and classification, we demonstrated how to overcome the weaknesses of having undesirable segments due to intra-parcels and inter-parcels variability, when using segmentation approaches for cadastral feature delineation. We also demonstrated how we can easily implement a geometric comparison framework within the ArcGIS environment and firmly believe the developed methodology can be reproduced.

AB - The objective to fast-track the mapping and registration of large numbers of unrecorded land rights globally, leads to the experimental application of Artificial Intelligence in the domain of land administration, and specifically the application of automated visual cognition techniques for cadastral mapping tasks. In this research, we applied and compared the ability of rule-based systems within Object Based Image Analysis (OBIA), as opposed to human analysis, to extract visible cadastral boundaries from very high-resolution World View-2 image, in both rural and urban settings. From our experiments, machine-based techniques were able to automatically delineate a good proportion of rural parcels with explicit polygons where the correctness of the automatically extracted boundaries was 47.4% against 74.24% for humans and the completeness of 45% for machine, as against 70.4% for humans. On the contrary, in the urban area, automatic results were counterintuitive: even though urban plots and buildings are clearly marked with visible features such as fences, roads and tacitly perceptible to eyes, automation resulted in geometrically and topologically poorly structured data, that could neither be geometrically compared with human digitisationed, nor actual cadastral data from the field. These results provide an updated snapshot with regards to the performance of contemporary machine-drive feature extraction techniques compared to conventional manual digitising. In our methodology, using an iterative approach of segmentation and classification, we demonstrated how to overcome the weaknesses of having undesirable segments due to intra-parcels and inter-parcels variability, when using segmentation approaches for cadastral feature delineation. We also demonstrated how we can easily implement a geometric comparison framework within the ArcGIS environment and firmly believe the developed methodology can be reproduced.

KW - Cadastral intelligence; Manual digitisation; Expert parameterisation; Land administration; Land Management; Automatic Feature Extraction; Object Based Image Analysis.

KW - cadastral intelligence; manual digitisation; expert parameterisation; land administration; land management; automatic feature extraction; Object-Based Image Analysis

KW - ITC-ISI-JOURNAL-ARTICLE

KW - ITC-GOLD

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

U2 - 10.3390/rs11141662

DO - 10.3390/rs11141662

M3 - Article

VL - 11

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 14

ER -