http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
High efficient semantic segmentation for autonomous vehicle
Ganzorig Gankhuyag,Changyu Park(박창규),KyoungWon Min(민경원) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
The Image segmentation algorithm has significantly improved by deep learning. However, high accuracy trades off huge computational costs and is therefore not suitable for the limited resource of autonomous driving vehicle. We propose a deep learning framework for image segmentation that is efficient enough for an autonomous driving vehicle environment while maintaining high accuracy and speed. Our proposed work achieves high segmentation accuracy at Cityscape public dataset and our private test dataset. At the same time, the frame rate is high enough for deployment in autonomous vehicles.