@inproceedings{Sabek2026_2468,
  author = {Sabek, Mohamed and Mei, Qipei and Lee, Gaang and Golabchi, Ali and Gonzalez, Vicente},
  editor = {Hamzeh, Farook and Poshdar, Mani and Garcia-Lopez,, Nelly P. and Gan, Vincent},
  title = {The Lean Construction Visual Taxonomy (LCVT): bridging the semantic gap},
  booktitle = {Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34)},
  year = {2026},
  pages = {14--25},
  address = {Singapore, Singapore},
  issn = {2789-0015},
  doi = {10.24928/2026/0151},
  url = {https://www.iglc.net/papers/details/2468},
  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.},
}