LLM Agent Framework for Intelligent Change Analysis in Urban Environment using Remote Sensing Imagery

TL;DR

This paper introduces ChangeGPT, an LLM-based agent framework that enhances urban change detection in remote sensing imagery through hierarchical structure and multi-step reasoning, achieving high accuracy and practical utility.

Contribution

The paper presents a novel hierarchical agent framework combining LLMs and vision models for versatile, intelligent change analysis in urban environments, addressing hallucination and multi-query handling.

Findings

Achieved 90.71% query match rate with GPT-4-turbo.

Demonstrated effectiveness in real-world urban change monitoring.

Excelled in multi-step reasoning and tool selection accuracy.

Abstract

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.