http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
RefineDet과 Deformable convolution을 활용한 다중 도로 객체 검출 및 교통 신호, 표지 인식 네트워크
이소열(So-Yeol Lee),선지영(Jee-Young Sun),고성제(Sung-Jea Ko) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.8
In this paper, we propose a deep convolutional neural network that detects multiple on—road objects and recognizes the traffic lights and signs for autonomous driving. The proposed network first detects on—road objects by using RefineDet with deformable convolution, and the color of traffic lights and subtype of traffic signs are then classified by a simple convolutional neural network—based recognition module. Experimental results demonstrate that the proposed network can effectively detect on—road objects and recognize traffic lights and signs.