Tao Zhang

Dr. Tao Zhang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 May 2025 in Sensors
Verified
Journal Article
Open access
PDF file
DYDongqi Yan
Dongqi Yan
TZTao Zhang
Tao Zhang
Although deep learning has exhibited remarkable performance in lane detection, lane detection remains challenging in complex scenarios, including those with damaged lane markings, obstructions, and insufficient lighting. Furthermore, a significant drawback of most existing lane-detection algorithms lies in their reliance on complex post-processing and strong prior knowledge. Inspired by the DETR architecture, we propose an end-to-end Transformer-based model, MHFS-FORMER, to resolve these issues. To tackle the interference with lane detection in complex scenarios, we have designed MHFNet. It fuses multi-scale features with the Transformer Encoder to obtain enhanced multi-scale features. These enhanced multi-scale features are then fed into the Transformer Decoder. A novel multi-reference deformable attention module is introduced to disperse the attention around the objects to enhance the model’s representation ability during the training process and better capture the elongated structure of lanes and the global environment. We also designed ShuffleLaneNet, which meticulously explores the channel and spatial information of multi-scale lane features, significantly improving the accuracy of target recognition. Our method has achieved an accuracy score of 96.88%, a real-time processing speed of 87 fps on the TuSimple dataset, and an F1 score of 77.38% on the CULane dataset. Compared with the methods based on CNN and those based on Transformer, our method has demonstrated excellent performance.

20 December 2024 in Electronics
Verified
Journal Article
Open access
PDF file
FXFan Xiangsuo
Fan Xiangsuo
TLTianfeng Li
Tianfeng Li
LFLinping Feng
Linping Feng
YMYanfang Ma
Yanfang Ma
WXWenhao Xu
Wenhao Xu
TZTao Zhang
Tao Zhang
In this paper, a filtered differential phase shifter with good selectivity is proposed and constructed. This study proposes and builds a filtered differential phase shifter with good selectivity. The main and reference lines in the suggested filtered differential phase shifter are structurally identical. The main line’s bandpass filtering function is achieved by a new coupled feeder, a parallel coupled line loaded with shorted branches, and a coupled resonator at the load end. It has impedance matching and additional transmission zeros/poles. By loading the coupled resonator at the load end, the selectivity of the phase shifter can be improved and the passband and transmission zeros/poles of the phase shifter can be equitably distributed by varying the coupling coefficients and the electrical lengths of the loaded branches. The reference line is a coupled resonator with the same structure and its electrical length is related to the number of degrees of phase shift. Finally, a differential phase shifter is designed and measured. The fractional bandwidth of the proposed phase shifter is about 38%, the return loss reaches −11 dB, the insertion loss is about 1.02 dB, the deviation of the simulated results in terms of the number of degrees of phase shift is about 2.5 degrees, and the deviation of the tested results is about 6 degrees. The trend of the simulation results and the actual measurement results are in good agreement.

1 January 2026 in Journal of Applied Optics
Verified
Journal Article
Open access
PDF file
BDBiao DA
Biao DA
昆明昆明理工大学信息工程与自动化学院,云南昆明650500
昆明理工大学信息工程与自动化学院,云南昆明650500
TZTao Zhang
Tao Zhang
JWJian Wang
Jian Wang
HFHongli Fang
Hongli Fang
云南云南省计算机技术应用重点实验室,云南昆明650500
云南省计算机技术应用重点实验室,云南昆明650500

在多光谱辐射测温中,数据处理作为一项关键步骤,其发展一直受制于目标的未知发射率。传统的解决思路往往是依据发射率与波长或温度之间的内在联系,构建相应的发射率假设模型。然而,由于实际情况的复杂性,当预先设定的假设模型与目标物体的真实发射率特性出现偏差时,这种偏差会在温度测量过程中被放大,进而导致显著的误差。因此,多光谱辐射测温技术的核心挑战在于构建发射率自校正机制,通过多光谱数据融合与自适应温度反演算法,在无需预设材料发射率模型的条件下,实现更高的测温精度。提出了一种基于改进NRBO-GA(hybrid Newton-Raphson-based optimizer and genetic algorithm)的混合优化算法,该算法的关键创新在于建立多波长辐射测温的约束优化数学模型。首先将光谱发射率分布参数化,构建满足辐射传输约束的光谱发射率种群作为初始解集;继而采用自适应目标函数进行适应度量化评估,通过进化算法在可行解空间内实施动态寻优;最终通过约束边界引导的全局收敛机制,获得符合黑体辐射定律且适应度最优的温度-发射率联合反演。该方法无需预设发射率模型,即可同步反演目标光谱发射率与真实温度。针对6种典型发射率模型开展仿真实验,结果表明,本算法对单调递增/递减、多极值波动等典型光谱发射率分布形态均表现出强适应性。在900 K和