| 제목 |
가상 3D 라이다 기반 객체 분류 딥러닝 학습 데이터셋 구축 방법에 관한 연구 |
| 분야 |
전기ㆍ전자ㆍ통신 |
| 언어 |
Korean |
| 저자 |
장형준(국민대학교), 손원일(국민대학교), 안태원(국민대학교), 이용기(국민대학교), 박기홍(국민대학교) |
| Key Words |
Autonomous drivng(자율주행), Lidar sensor(라이다 센서), Deep learning(딥러닝), Training dataset(학습 데이터셋), Object classification(객체 분류) |
| 초록 |
Deep learning algorithms are widely adopted in autonomous driving due to their strong capabilities of classifying the objects around the vehicle. This paper introduces methodologies for constructing datasets for training deep learning algorithms that receive LiDAR sensor data. The training datasets were built in a virtual environment using 3D LiDAR sensor models and different object models. These datasets were used to train the simple CNN model developed in this study. The performance of the trained CNN model was evaluated using the Waymo open datasets and driving scenarios that include multiple moving objects interfering with one another. The CNN model proved to be as good as the best benchmark models, which in turn assured the validity of the training datasets in this study. The proposed method can achieve significant time and cost savings in the generation of proper training datasets for deep learning algorithms in a variety of autonomous driving complexities. |
| 원문(PDF) |
다운로드
Journal Site
|
