http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이동진(Dongjin Lee),김재홍(Jaehong Kim),한승준,최정단,박정희(Cheong Hee Park) 대한전자공학회 2016 대한전자공학회 학술대회 Vol.2016 No.6
This paper presents a traffic light recognition(TLR) system using two different methods. First, we adopt a histogram of oriented gradients (HOG), which is a feature descriptor, originally used for pedestrian detection. Second, a pre-trained convolutional neural network model is used for fine-tuning the traffic light dataset. To evaluate the performance of our proposed method, we used the LISA traffic light dataset, which is publicly available from VIVA challenge website. Using the dataset, we achieved 99.13% recognition accuracy using the HOG feature.