Embedded Files
Computer Vision Systems in Construction
Computer Vision Systems in Construction
Computer vision is rapidly transforming the construction industry through digitalization and robotic automation, yet its full potential remains limited by longstanding challenges in achieving robust, deployable performance across diverse environments. At the HCI, we lead research that addresses a fundamental question: How can high-performing computer vision models be developed to adapt seamlessly to diverse and dynamic construction settings with minimal effort? To this end, our team pioneers advancements in visual foundation model development, model architecture design, training dataset optimization, and pre-deployment performance evaluation. By bridging the gap between algorithmic innovation and field applicability, our research drives the next generation of reliable and scalable vision-based systems for construction.
Language Models and Construction Documents
Language Models and Construction Documents
Language models have emerged as powerful tools for assisting construction professionals in retrieving, analyzing, and interpreting complex, long-context regulatory documents. However, most existing general-purpose language models lack construction-specific terminology and domain knowledge, often leading to hallucinations or inaccurate reasoning. Besides, their large size and heavy computational demands limit their practicality for real-world construction applications. To tackle these challenges, our research explores how to build a construction-specialized language model that integrates industry-specific terminology and knowledge while remaining lightweight, efficient, and adaptable to diverse practical conditions. We also investigate methods to transform and structure complex construction documents so that language models can better comprehend and utilize their content. Through this research, we aim to advance AI adoption in the construction industry, enabling more accurate information retrieval, regulatory compliance, and decision support.
Generative AI-powered Design in Construction
Generative AI-powered Design in Construction
Generative AI (GenAI) holds tremendous potential for exploring and producing creative, high-performing design alternatives. However, current GenAI systems face inherent limitations in comprehending the complex interplay among designers’ intentions, performance requirements, constraints, and regulatory conditions. At HCI, we strive to bridge this gap by developing human-centered generative design systems that seamlessly integrate intent understanding, regulatory reasoning, and performance-driven optimization. Our goal is to transform GenAI from a mere creative assistant into a collaborative design partne—one that co-evolves ideas with humans while ensuring compliance, constructability, and meaningful alignment with real-world needs.
Hanyang University (2024 - Present)
Hanyang University (2024 - Present)
Construction-specialized Foundational Language Model for Digital and Robotic Transformation (PI, 09/2025 - 08/2026)
Sponsor: National Research Foundation of Korea
Developing a Team Response using Digital Construction to Mitigate Disasters related to Climate Change (Co-PI, 07/2025 - 08/2027)
Sponsor: National Research Foundation of Korea
AI-Based CCTV Analytics for Mining Operations and Productivity Monitoring (PI, 11/2025 - 12/2025)
Sponsor: Korea Institute of Geoscience and Mineral Resources
Analysis of High-Risk Activities and Feasibility Evaluation of Robotic Technologies for Express Road Maintenance (Co-PI, 07/2025 - 12/2025)
Sponsor: Korea Expressway Corporation
Assessment and Improvement of Construction Quality Management Practices and Regulations (Co-PI, 05/2025 - 01/2026)
Sponsor: Ministry of Land, Infrastructure and Transport, Korea
Optimizing a Training Image Dataset for Adaptive Computer Vision AI in Dynamic Construction Workplaces (PI, 03/2024 - 02/2025)
Sponsor: Hanyang University
Nanyang Technological University (2022 - 2024)
Nanyang Technological University (2022 - 2024)
Safety 4.0: AI-Driven Ship Safety Management System (Co-PI, 07/2023 - 02/2024)
Sponsor: Singapore Maritime Institute
Visual AI Training with Synthetic and Real Construction Images for Construction Digitalisation and Robotic Automation (PI, 05/2023 - 02/2024)
Sponsor: Ministry of Education, Singapore (MOE AcRF Tier 1)
Integrating Computer Vision and Natural Language Processing for Construction Project Document Digitalisation (PI, 03/2023 - 02/2024)
Sponsor: Ministry of Education, Singapore (MOE AcRF Tier 1)
Synthetizing Virtual Construction Images to Overcome Real Training Data Shortage for DNN-Powered Visual Scene Understanding (PI, 07/2022 - 02/2024)
Sponsor: Nanyang Technological University
University of Michigan (2020 - 2022, Participating Researcher)
University of Michigan (2020 - 2022, Participating Researcher)
AI-Based Environment, Health, and Safety Management in Industrial Worksites (09/2021 - 06/2022)
Sponsor: VelocityEHS
Collaborated with Prof. Daeho Kim at the University of Toronto and Prof. Meiyin Liu at Rutgers University
Non-Invasive Personalized Normative Messaging Intervention for the Reduction of Household Energy Consumption (09/2020 - 07/2021)
Sponsor: National Science Foundation, USA
Seoul National University (2014 - 2020, Participating Researcher)
Seoul National University (2014 - 2020, Participating Researcher)
Automated DB-Free Visual Analytics Platform for Enhancing Construction Productivity by 20% (04/2019 - 12/2021)
Sponsor: Korea Agency for Infrastructure Technology Advancement
Collaborated with Prof. JoonOh Seo at the Hong Kong Polytechnic University
Smart Digital Engineering Education and Training for Lead Engineer (03/2019 - 09/2020)
Sponsor: Korea Institute of Advancement of Technology
Urban Infrastructure Safety and Maintenance Using Big Data Analytics (07/2019 - 02/2020)
Sponsor: Ministry of Land, Infrastructure and Transport, Korea
Development of Hazardous Condition and Unsafe Behavior Monitoring System Based on CCTV Image Analysis on Construction Sites (07/2018 - 01/2020)
Sponsor: Seoul National University
Collaborated with Prof. Herbert Biggs at Queensland University of Technology
Development of a Hazardous Condition and Worker's Unsafe Behavior System for Construction Safety (01/2019 - 12/2019)
Sponsor: LG Yonam Foundation
Collaborated with Prof. Carlos H. Caldas at the University of Texas at Austin
Improvement of Construction Safety through Design for Safety (DfS) System and Case Analysis (05/2019 - 10/2019)
Sponsor: Samsung Electronics Co., Ltd.
Collaborated with Prof. Bon-Gang Hwang at National University of Singapore
Developing Risk Based Inspection Model for Offshore Plant Maintenance (01/2018 - 02/2019)
Sponsor: Hyundai Heavy Industries Co., Ltd.
Tackling Urban Issues with Big Data (04/2018 - 12/2018)
Sponsor: Seoul Digital Foundation
Standardization of Land Compensation Procedures in Urban Infrastructure Construction Projects (04/2018 - 12/2018)
Sponsor: National Agency for Administrative City Construction, Korea
Emergency Event Detection and Response in Single Person Households Using Multi Sound Recognition (11/2017 - 10/2018)
Sponsor: National Research Foundation of Korea
Development of Decision-Making Supporting System on Construction Sites Using Deep Learning-based Visual Data Analytics (05/2017 - 02/2018)
Sponsor: National Research Foundation of Korea
Development of Productivity Monitoring System for Construction Equipment Using Visual Big-Data Analytics (09/2017 - 01/2018)
Sponsor: SNU Big Data Institute
Fleet Management for Construction Equipment and Smart Construction Technology Using ICT (07/2014 - 12/2017)
Sponsor: Korea Agency for Infrastructure Technology Advancement
Page updated
Google Sites
Report abuse