상세정보
학술지
Development of System for Collecting User-specified Training Data for Autonomous Driving Based on Virtual Road Environment
- 저자
- 김민수, 장인성
- 발행일
- 202212
- 출처
- Sensors and Materials, v.34 no.12(5), pp.4813-4825
- ISSN
- 0914-4935
- 출판사
- MYU K.K.
- 협약과제
- 22IR1300, 수요처 맞춤형 실감형 3D 공간정보 갱신 및 활용지원 기술개발, 장인성
- 초록
- Deep learning technologies that use road images to recognize autonomous driving environments have been actively developed. Such deep-learning-based autonomous driving technologies need a large amount of training data that can represent various road, traffic, and weather environments. However, there have been many difficulties in terms of time and cost in collecting training data that can represent various road environments. Therefore, in this study, we attempt to build a virtual road environment and develop a system for collecting training data based on the virtual environment. To build a virtual environment identical to the real world, we convert and use two kinds of existing geospatial data: high-definition 3D buildings and high-definition roads. We also develop a system for collecting training data running in the virtual environment. The implementation results of the proposed system show that it is possible to build a virtual environment identical to the real world and to collect specific training data quickly and at any time from the virtual environment with various user-specified settings.
- KSP 제안 키워드
- 3D buildings, Amount of training data, Development of system, Geospatial Data, High definition, Learning-based, Real-world, Virtual environment, autonomous driving, deep learning(DL), driving environment
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
