http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Pedestrian Detection Method Based on Convolution Nerve Network
Jiang Yingjun,Wang Jianxin,Guo Kehua 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.11
One new pedestrian detection method integrating static high-level features and movement features based on convolution nerve network is proposed in this paper. During the phase of unsupervised deep learning of pedestrian features, the hierarchical static features of pedestrians are extracted from the low to the high with convolution nerve network; the pedestrian movement features are obtained through mean value approach of rectangular block pixel difference. During the logic regression recognition phase, static features and movement features are integrated. The results show that the pedestrian detection algorithm of convolution nerve network integrating movement features greatly improve the pedestrian detection performance under complicated background.
Active noise cancellation frequency‑locked loop with a notch filter
Lei Pan,Dongxing Xu,Jingmei Zhang,Chang Yin,Zifeng Wu,Yingjun Guo 전력전자학회 2021 JOURNAL OF POWER ELECTRONICS Vol.21 No.12
To improve the performance of frequency-locked loops (FLLs) under distorted grid conditions, a series of pre-filtering techniques have been added to remove harmonics. One of them is the FLL-based comb filter (COMB-FLL), which offers a high disturbance rejection capability. However, it has some disadvantages, such as approximating a fractional delay and compensating an accumulated round-off error in the digital implementation of COMB-FLL. To alleviate these problems, this study proposes an active noise cancellation (ANC) FLL with a notch filter (NF), which incorporates an NF and an ANC to improve the frequency-locking ability. In this research, the structure of a comb filter is simplified into an NF, and an ANC is creatively introduced to eliminate harmonics from the frequency signal obtained by FLL. Furthermore, ANC has been improved to make it suitable for electricity-related applications. The proposed FLL features a unique cascade structure, which has excellent frequency-locking ability and dynamic characteristics under normal, abnormal, and harmonically distorted grid conditions. The simulations and experimental results verify the validity and reliability of the proposed FLL.