Visual Agentic System for Spatial Metric Query Answering in Remote Sensing Images

Simple item page
dc.contributor.authorWang, Yinghaoen_US
dc.contributor.authorWang, Chengen_US
dc.contributor.editorGünther, Tobiasen_US
dc.contributor.editorMontazeri, Zahraen_US
dc.date.accessioned2025-05-09T09:31:46Z
dc.date.available2025-05-09T09:31:46Z
dc.date.issued2025
dc.description.abstractAccurately measuring real-world object dimensions from Remote Sensing (RS) images is crucial for applications in geospatial analysis and urban planning. Traditional Vision-Language Models (VLMs) struggle with spatial reasoning, while end-to-end remote sensing VLMs are often limited to predefined tasks such as image captioning. In this paper, we propose a visual agentic system for spatial metric query answering, dynamically integrating code-generation agents with a grounded remote sensing VLM and a Vision Specialist. Our system autonomously identifies reference objects, infers scale factors, and performs spatial measurements through structured subroutines. Experiments demonstrate that our approach achieves higher accuracy in footprint area estimation compared to state-of-the-art large language models with vision capabilities.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEurographics 2025 - Posters
dc.identifier.doi10.2312/egp.20251028
dc.identifier.isbn978-3-03868-269-1
dc.identifier.issn1017-4656
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/egp.20251028
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egp20251028
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Scene Understanding; Image Segmentation; Object Identification
dc.subjectComputing methodologies → Scene Understanding
dc.subjectImage Segmentation
dc.subjectObject Identification
dc.titleVisual Agentic System for Spatial Metric Query Answering in Remote Sensing Imagesen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
egp20251028.pdf
Size:
659.23 KB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
poster1020_poster_pdf.pdf
Size:
1.33 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Posters