EUVIMEDEUVIMED entdecken
Crossref

LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery

Zixuan Xiao, Jun Ma

Automation in Construction · 2025-09 · 177 · 106341

DOI: 10.1016/j.autcon.2025.106341 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Automation in Construction, 2025-09. Verfasst von Zixuan Xiao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 58 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing change detection methods often lack the versatility to handle diverse real-world queries and the intelligence for comprehensive analysis. This paper presents a general agent framework, integrating Large Language Models (LLM) with vision foundation models to form ChangeGPT. A hierarchical structure is employed to mitigate hallucination. The agent was evaluated on a curated dataset of 140 questions categorized by real-world scenarios, encompassing various question types (e.g., Size, Class, Number) and complexities. The evaluation assessed the agent's tool selection ability (Precision/Recall) and overall query accuracy (Match). ChangeGPT, especially with a GPT-4-turbo backend, demonstrated superior performance, achieving a 90.71 % Match rate. Its strength lies particularly in handling change-related queries requiring multi-step reasoning and robust tool selection. Practical effectiveness was further validated through a real-world urban change monitoring case study in Qianhai Bay, Shenzhen. By providing intelligence, adaptability, and multi-type change analysis, ChangeGPT offers a powerful solution for decision-making in remote sensing applications.

Zitieren

APA

Xiao, Z., & Ma, J. (2025). LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery. Automation in Construction, 177, 106341. https://doi.org/10.1016/j.autcon.2025.106341

Vancouver

Xiao Z, Ma J. LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery. Automation in Construction. 2025;177:106341. doi:10.1016/j.autcon.2025.106341

BibTeX
@article{Xiao2025,
  author = {Xiao, Zixuan and Ma, Jun},
  title = {LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery},
  journal = {Automation in Construction},
  year = {2025},
  volume = {177},
  pages = {106341},
  doi = {10.1016/j.autcon.2025.106341}
}
Kostenlos starten →