Zhijian Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhijian Yang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Guolin He
School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, China
1 shared publication Kang Ding
South China University of Technology School of Mechanical and Automotive Engineering, Guangzhou, China
1 shared publication- Weihua Li
South China University of Technology
1 shared publication - Zhaoqian Wu
School of Mechanical Engineering, Dongguan University of Technology, Dongguan, China
1 shared publication - Ziyi Chen
School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China
1 shared publication
Latest Publications
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (7) , 7371-7380
LaneTD: Lane Feature Aggregator Based on Transformer and Dilated Convolution
Deep-Learning-Based algorithms successfully improve the detection accuracy of traffic lanes. Most of them employed stacked convolutional neural networks( CNNs) to extract semantics, but they have trouble gathering global visual information. What’s more, the stacked CNNs perform multiple down-sampling, which reduce the resolution of feature map, causing the tiny features easy to be ignored. To address these problems, LaneTD is proposed: a novel lane feature aggregator that extracts and fuses local and global features. This method adopts dilated convolution to extract local features of various scales, and enhances global representation base on transformer encoder. The local and global information are then weighted fused using bidirectional feature pyramid. In addition, we apply unsupervised image style transfer to improve the performance in nighttime and dark scenarios. The method is quantitatively evaluated on public challenging CULane dataset, the result shows that the proposed method significantly improves the accuracy and computational efficiency of lane detection in different scenarios. Furthermore, an ablation study is carried out, as well as a discussion of efficiency trade-off choices that can be applied in practice.
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (7) , 7371-7380
LaneTD: Lane Feature Aggregator Based on Transformer and Dilated Convolution
Deep-Learning-Based algorithms successfully improve the detection accuracy of traffic lanes. Most of them employed stacked convolutional neural networks( CNNs) to extract semantics, but they have trouble gathering global visual information. What’s more, the stacked CNNs perform multiple down-sampling, which reduce the resolution of feature map, causing the tiny features easy to be ignored. To address these problems, LaneTD is proposed: a novel lane feature aggregator that extracts and fuses local and global features. This method adopts dilated convolution to extract local features of various scales, and enhances global representation base on transformer encoder. The local and global information are then weighted fused using bidirectional feature pyramid. In addition, we apply unsupervised image style transfer to improve the performance in nighttime and dark scenarios. The method is quantitatively evaluated on public challenging CULane dataset, the result shows that the proposed method significantly improves the accuracy and computational efficiency of lane detection in different scenarios. Furthermore, an ablation study is carried out, as well as a discussion of efficiency trade-off choices that can be applied in practice.
- 14 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 37 (1) , 820-829
Transfer Mechanism Analysis of Injected Voltage Harmonic and its Effect on Current Harmonic Regulation in FOC PMSM
Harmonic injection method is widely used in the suppression of current harmonic and torque ripple in field-oriented control (FOC) permanent magnet synchronous motor (PMSM) servo system. However, under some working conditions of FOC PMSM, the harmonic injection method fails to suppress the current harmonics and causes oscillation. To analyze the cause of oscillation, the transfer mechanism of injected voltage harmonic is analyzed in this article, and the relation between injected voltage harmonic and current harmonic is derived. The theoretical analysis results show that the relation between harmonics will change with motor speed and parameters of FOC PMSM. When the relation between harmonics is reversed, the existing harmonic injection method will fail and cause harmonic oscillation. To solve this problem, a simple improvement of the harmonic injection method is proposed in this article based on the proposed close-loop model. The correctness of the mathematical derivation and the effectiveness of the proposed method is evaluated by experiment and simulation.
- 14 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 37 (1) , 820-829
Transfer Mechanism Analysis of Injected Voltage Harmonic and its Effect on Current Harmonic Regulation in FOC PMSM
Harmonic injection method is widely used in the suppression of current harmonic and torque ripple in field-oriented control (FOC) permanent magnet synchronous motor (PMSM) servo system. However, under some working conditions of FOC PMSM, the harmonic injection method fails to suppress the current harmonics and causes oscillation. To analyze the cause of oscillation, the transfer mechanism of injected voltage harmonic is analyzed in this article, and the relation between injected voltage harmonic and current harmonic is derived. The theoretical analysis results show that the relation between harmonics will change with motor speed and parameters of FOC PMSM. When the relation between harmonics is reversed, the existing harmonic injection method will fail and cause harmonic oscillation. To solve this problem, a simple improvement of the harmonic injection method is proposed in this article based on the proposed close-loop model. The correctness of the mathematical derivation and the effectiveness of the proposed method is evaluated by experiment and simulation.