U rban C lip A tlas : A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos
Computer Graphics Forum · 02.06.2026
DOI: 10.1111/cgf.70431 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 02.06.2026. Verfasst von Joel Perca und 5 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro, Fundação de Amparo à Pesquisa do Estado de São Paulo.
Abstract (Originalsprache)
Extracting actionable insights from long‐duration urban videos is often labor‐intensive: analysts must manually sift through raw footage to pinpoint target events or uncover broader behavioral trends. In this work, we present U rban C lip A tlas , a visual analytics system for exploring long urban videos recorded at street intersections. U rban C lip A tlas combines retrieval‐augmented generation (RAG), taxonomy‐aware entity extraction, and video grounding to support event retrieval and interpretation. The system segments extended recordings into short clips, generates textual descriptions with a vision–language model, and indexes them for semantic retrieval. A knowledge graph maps entities and relations from LLM answers onto a domain‐specific taxonomy and aligns them with detected objects and trajectories to support visual grounding and verification. U rban C lip A tlas supports scene retrieval through an augmented chat‐based interface and improves scene interpretation by tightly aligning textual outputs with video evidence. This design strengthens the connection between textual reasoning and visual evidence, reducing the effort required to validate model outputs and refine hypotheses. We demonstrate the usefulness of U rban C lip A tlas on the StreetAware dataset through two case studies involving hazardous scenarios and crossing dynamics at street intersections. U rban C lip A tlas helps analysts reason about safety‐ and mobility‐related patterns across large urban video collections.
Förderung
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- National Science Foundation
- U.S. Department of Transportation
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
Zitieren
APA
Perca, J., Sante, L., Heredia, J., Rulff, J., Silva, C., & Poco, J. (2026). U rban C lip A tlas : A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos. Computer Graphics Forum. https://doi.org/10.1111/cgf.70431
Vancouver
Perca J, Sante L, Heredia J, Rulff J, Silva C, Poco J. U rban C lip A tlas : A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos. Computer Graphics Forum. 2026. doi:10.1111/cgf.70431
BibTeX
@article{Perca2026,
author = {Perca, Joel and Sante, Luis and Heredia, Juanpablo and Rulff, Joao and Silva, Claudio and Poco, Jorge},
title = {U rban C lip A tlas : A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70431}
}
EUVIMED