Comparing Human Versus Machine-Driven Cadastral Boundary Feature Extraction

Emmanuel Nyandwi,Divyani Kohli,Mila Koeva,Rohan Bennett

doi:10.3390/rs11141662

Abstract

The objective to fast-track the mapping and registration of large numbers of unrecorded land rights globally has led 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 images, 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 the machine compared to 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. Thus, these could neither be geometrically compared with human digitisation, nor actual cadastral data from the field. The results of this study provide an updated snapshot with regards to the performance of contemporary machine-driven 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-parcel and inter-parcel variability, when using segmentation approaches for cadastral feature delineation. We also demonstrated how we can easily implement a geometric comparison framework within the Esri’s ArcGIS software environment and firmly believe the developed methodology can be reproduced.

Highlights

The emergence of artificial intelligence (AI) concepts, methods and techniques ushered in a new era of the longstanding philosophical debate and technical competition between the merits of ‘human’ versus ‘machine’
Considering that only ~30% of land ownership units worldwide are captured in formal cadastres and land registration systems [2,3], automation techniques could be a supportive tool for the generation of digital parcel boundaries, enabling faster registration and mapping of land rights
Our results show that automation was able to correctly extract 47.4% of visible rural parcels and achieved 45% of completeness, whereas in urban areas, it failed to generate explicit polygons owing to urban complexities and spectral reflectance confusion of cadastral features

Summary

Introduction

The emergence of artificial intelligence (AI) concepts, methods and techniques ushered in a new era of the longstanding philosophical debate and technical competition between the merits of ‘human’ versus ‘machine’. Machine-based techniques exhibit computation capabilities capable of handling complex issues not quickly solved by humans [1]. As people become more intelligent, they can prescribe precision and program performance of a high quantity task to a machine, such as the extraction of cadastral features from images. Considering that only ~30% of land ownership units worldwide are captured in formal cadastres and land registration systems [2,3], automation techniques could be a supportive tool for the generation of digital parcel boundaries, enabling faster registration and mapping of land rights. In light of the recent enhancement to machine-driven feature extraction techniques, the current study aims to measure the ability of machine-based image analysis algorithms, against manual digitising, in extracting cadastral parcel boundaries from very high-resolution remotely sensed images

Methods

Findings

Discussion

Conclusion