Game Engine Driven Synthetic Data Generation for Computer Vision-Based Construction Safety Monitoring

  • Lee, Heejae (School of Architecture and Building Science, Chung-Ang University) ;
  • Jeon, Jongmoo (School of Architecture and Building Science, Chung-Ang University) ;
  • Yang, Jaehun (School of Architecture and Building Science, Chung-Ang University) ;
  • Park, Chansik (School of Architecture and Building Science, Chung-Ang University) ;
  • Lee, Dongmin (School of Architecture and Building Science, Chung-Ang University)
  • 발행 : 2022.06.20

초록

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.

키워드

과제정보

This research was supported by the Chung-Ang University Research Grants in 2021. This study was financially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government's Ministry of Science and ICT (MSIP) [No. NRF-2020R1A4A4078916] and [No. NRF-2022R1G1A1012897].