http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Optical Flow 추정을 위한 딥러닝 기반의 Lightweight Deep Neural Network
최주성(Joo sung Choi),김중희(Jung Hee Kim),박재서(Jae Seo Park),강석주(Suk-Ju Kang) 대한전자공학회 2019 대한전자공학회 학술대회 Vol.2019 No.11
Conventional methods for optical flow estimation are inappropriate for applications that demand real-time operation and small memory capacity. Deep learning based networks, such as FlowNet[l] and FlowNet2[2], have high accuracy and fast running time, but require more than 160M of parameters. Therefore, we introduce tow deep learning based networks called PWC-Net[3] and LiteFlowNet[4] that have compact number of parameters and also have effective performances. Introducing two network models of compact but effective CNN models for optical flows, called PWC-Net and LiteFlowNet.
김동욱(D.U.Kim),김연풍(Y.P.Kim),신현주(H.J.Shin),백병산(B.S.Baek),류승표(S.P.Ryu),민병권(B.G.Min) 전력전자학회 1999 전력전자학술대회 논문집 Vol.- No.-
When several UPSs are connected in parallel, individual UPS should take charge of exactly same load current Because the output impedance of each UPSs is very low, small voltage difference among them will give rise to circulating current will bring about the decrease of UPS own capacity.<br/> In order to solve this problem in this paper an inverter controller for the UPS which has a good response characteristic and robustness for directly applying in industrial world is proposed. This paper also describes that difference between load current divided by number of operating inverters and its own current is detected as unbalanced current Then frequency and voltage are controlled to minimize the active component and the reactive component respectively. A good controller load-sharing technique is verified by experiments in the parallel poerating system with 40kVA UPSs.