34th Annual Conference of the International Group for Lean Construction (IGLC 34) - Singapore, Singapore - 2026

https://doi.org/10.24928/2026/0151

The Lean Construction Visual Taxonomy (LCVT): bridging the semantic gap

Mohamed Sabek1, Qipei Mei2, Gaang Lee3, Ali Golabchi4 & Vicente Gonzalez5

1PhD Candidate, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, [email protected], orcid.org/0009-0005-2906-9874
2Assistant Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, [email protected],
3Assistant Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, [email protected],
4Adjunct Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, [email protected],
5Professor, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada, [email protected], orcid.org/0000-0003-3408-3863

Abstract

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.

Keywords

AI, transformation-flow-value, computer vision, taxonomy, visual management.

Files


Full Text
 

Reference

Download: BibTeX | RIS Format

Reference in APA 7th edition format:

Sabek, M., Mei, Q., Lee, G., Golabchi, A. & Gonzalez, V.. (2026). The Lean Construction Visual Taxonomy (LCVT): bridging the semantic gap. In Hamzeh, F., Poshdar, M., & Garcia-Lopez,, N. P. (Eds.), Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34) (pp. 14–25). https://doi.org/10.24928/2026/0151

Shortened reference for use in IGLC papers:

Sabek, M., Mei, Q., Lee, G., Golabchi, A. & Gonzalez, V.. (2026). The Lean Construction Visual Taxonomy (LCVT): bridging the semantic gap. IGLC34. https://doi.org/10.24928/2026/0151

 

Founded in 1993, the IGLC is an international network of researchers from practice and academia in architecture, engineering, and construction (AEC) who feel that the practice, education, and research of the AEC industry have to be radically renewed in order to respond to the global challenges ahead.

2015 © All Rights Reserved.