A Systematic Review of Ontology–AI Integration for Construction Image Recognition

This study presents a systematic review of ontology–AI integration for construction image understanding, aiming to clarify how ontologies enhance semantic consistency, interpretability, and reasoning in AI-based visual analysis. Construction sites involve highly dynamic and unstructured conditions, making image-based hazard detection and situation assessment both essential and challenging. Ontology-based frameworks offer a structured semantic layer that can complement deep learning models; however, most existing studies adopt ontologies only as post-processing mechanisms rather than embedding them within model training or inference workflows. Following PRISMA 2020 guidelines, a comprehensive search of the Web of Science Core Collection (2014–2025) identified 587 publications, of which 152 met the eligibility criteria, and 16 explicitly addressed construction image data. Topic modeling revealed five functional objectives—regulatory compliance, hazard reasoning, decision support, knowledge reuse, and sustainability—and four primary data modalities: BIM, text, image, and sensor data. Two dominant integration patterns were observed: training-stage and output-stage enhancement. While quantitative performance improvements were modest, qualitative gains were consistent across studies, including reduced false positives, improved interpretability, and enhanced situational understanding. Persistent gaps were identified in standardization, scalability, and real-world validation. This review provides the first structured synthesis of ontology–AI research for construction image understanding and offers an evidence-based research agenda that links observed limitations to actionable directions for semantic AI in construction.