TY - CONF TI - The Lean Construction Visual Taxonomy (LCVT): bridging the semantic gap AU - Sabek, Mohamed AU - Mei, Qipei AU - Lee, Gaang AU - Golabchi, Ali AU - Gonzalez, Vicente AD - PhD Candidate, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, sabek@ualberta.ca, orcid.org/0009-0005-2906-9874 AD - Assistant Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, qipei@ualberta.ca, AD - Assistant Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, gaang@ualberta.ca, AD - Adjunct Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, alireza1@ualberta.ca, AD - Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, vagonzal@ualberta.ca, orcid.org/0000-0003-3408-3863 ED - Hamzeh, Farook ED - Poshdar, Mani ED - Garcia-Lopez,, Nelly P. ED - Gan, Vincent PY - 2026 DA - 2026/06/22 T2 - Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34) C3 - Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34) CY - Singapore, Singapore SP - 14 EP - 25 DO - 10.24928/2026/0151 SN - 2789-0015 (ISSN) AB - The architecture, engineering, and construction (AEC) industry faces productivity stagnation due to ineffective production flow management. Although Lean Construction (LC) aims to minimize waste, manual monitoring lacks the high-frequency data required for timely control. Computer Vision (CV) offers automated monitoring but suffers from a "Semantic Gap," where models detect low-level objects but fail to interpret high-level Lean states (e.g., "waiting"). This study proposes the Lean Construction Visual Taxonomy (LCVT), a three-level hierarchical framework–Category, Indicator, Visual Definition grounded in Transformation-Flow-Value (TFV) theory. Crucially, the LCVT provides standardized class definitions to guide "zero-shot" prompt engineering in Vision-Language Models (VLMs). By injecting formal L3 definitions that address entity types, temporal thresholds (e.g., stationary >60 s), and spatial context into VLM models such as GPT-4o and Gemini 2.5, the framework enables sophisticated, lean reasoning without the need for massive custom-labeled datasets. Pilot validation achieved a 0.946 mAP in distinguishing state-dependent equipment loads. By formalizing the visual signatures of waste, the LCVT establishes the data infrastructure necessary for proactive, VLM-driven decision support in construction AI. KW - AI KW - transformation-flow-value KW - computer vision KW - taxonomy KW - visual management. L1 - https://www.iglc.net/papers/details/2468/pdf UR - https://www.iglc.net/papers/details/2468 DB - IGLC.net LA - English N1 - Export date: 04 October 2026 ER -