Artificial Intelligence for Querying Land and Property Data from Cadastral Plans (13013) |
| Hamid Hosseini, Behnam Atazadeh and Abbas Rajabifard (Australia) |
Mr Hamid Hosseini
Graduate Researcher
The University of Melbourne
Department of Infrastructure Engineering
CSDILA
Carlton
Australia
|
| |
| Corresponding author Mr Hamid Hosseini (email: hamid.hosseini[at]student.unimelb.edu.au, tel.: +61450678201) |
| |
|
| [ abstract ] [ paper ] [ handouts ] |
|
Published on the web 2025-03-16
Received 2024-12-02 / Accepted n/a |
| This paper is one of selection of papers published for the FIG Working Week 2025 in Brisbane, Australia PEER REVIEW in Brisbane, Australia and has undergone the FIG Peer Review Process. |
FIG Working Week 2025 in Brisbane, Australia PEER REVIEW
ISBN n/a ISSN 2307-4086
URL n/a
|
Abstract |
| Cadastral plans are used in land registration systems for defining legal boundaries of land parcels and properties as well as their associated rights, restrictions, and responsibilities (RRRs). However, existing registered cadastral plans are in 2D non-machine-readable formats and data within these plans are not easily accessible and readily usable, leading to unnecessary delays, disruptions, and costs within land development projects. Artificial intelligence (AI) as an emerging technology has been recognized as one of the operational parameters for advancing land administration systems (LASs) which can offer transformative solutions to overcome traditional approaches. This paper presents a new approach to efficiently retrieve land and property information from cadastral plans, reducing the high cognitive load associated with manual approaches. Our approach’s two core functionalities are data extraction from plans using computer vision and communication with plans using natural language processing (NLP). To demonstrate our approach, a prototype chatbot employing generative pretrained transformer (GPT) as the core large language model (LLM) was developed for data querying from plans. Initial testing shows effective handling of semantic queries, while highlighting the need for further refinement and development in handling more specific queries within land administration domain and complex spatial queries. |
| |
| Keywords: Geoinformation/GI; e-Governance; Digital cadastre; Engineering survey; Tunnel surveying; Cadastre; Land management; Quantity surveying; Keyword 1; Keyword 2; Keyword 3 |
