ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding

arXiv cs.AI / 4/27/2026

💬 OpinionDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces ChangeQuery, a unified multimodal framework aimed at improving remote-sensing change analysis for both natural and human-induced disasters with actionable, semantic-level situational awareness.
It addresses key limitations of prior vision-language approaches—such as over-reliance on optical imagery, bias toward natural disasters, and insufficient grounded interactivity—by incorporating post-event SAR structural information alongside pre-event optical semantics.
The authors build the Disaster-Induced Change Query (DICQ) dataset, a large benchmark that pairs pre-event optical semantics with post-event SAR features across a balanced mix of natural catastrophes and armed conflicts.
To enable high-quality supervision for interactive reasoning, they propose an Automated Semantic Annotation Pipeline that converts raw segmentation masks into grounded, hierarchical instruction sets using a “statistics-first, generation-later” approach.
Experiments claim ChangeQuery achieves state-of-the-art performance and provides interpretable results for complex disaster monitoring tasks including damage quantification, region-specific descriptions, and overall summaries, with code released publicly.

Abstract

Rapid situational awareness is critical in post-disaster response. While remote sensing damage assessment is evolving from pixel-level change detection to high-level semantic analysis, existing vision-language methodologies still struggle to provide actionable intelligence for complex strategic queries. They remain severely constrained by unimodal optical dependence, a prevailing bias towards natural disasters, and a fundamental lack of grounded interactivity. To address these limitations, we present ChangeQuery, a unified multimodal framework designed for comprehensive, all-weather disaster situation awareness. To overcome modality constraints and scenario biases, we construct the Disaster-Induced Change Query (DICQ) dataset, a large-scale benchmark coupling pre-event optical semantics with post-event SAR structural features across a balanced distribution of natural catastrophes and armed conflicts. Furthermore, to provide the high-quality supervision required for interactive reasoning, we propose a novel Automated Semantic Annotation Pipeline. Adhering to a ``statistics-first, generation-later'' paradigm, this engine automatically transforms raw segmentation masks into grounded, hierarchical instruction sets, effectively equipping the model with fine-grained spatial and quantitative awareness. Trained on this structured data, the ChangeQuery architecture operates as an interactive disaster analyst. It supports multi-task reasoning driven by diverse user queries, delivering precise damage quantification, region-specific descriptions, and holistic post-disaster summaries. Extensive experiments demonstrate that ChangeQuery establishes a new state-of-the-art, providing a robust and interpretable solution for complex disaster monitoring. The code is available at \href{https://sundongwei.github.io/changequery/}{https://sundongwei.github.io/changequery/}.