Yongzhi Tian

Yongzhi Tian


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
11 December 2018 in Journal of Materials Chemistry C
Verified
Journal Article
Closed access
PDF file
YCYan-Cheng Chen
Yan-Cheng Chen
YLYing-Jie Lu
Ying-Jie Lu
QLQian Liu
Qian Liu
CLChao-Nan Lin
Chao-Nan Lin
JGJuan Guo
Juan Guo
Chong-Xin ShanChong-Xin Shan
Chong-Xin Shan
A multi-channel Ga 2 O 3 photodetector array with 16 cells was fabricated to realize solar-blind imaging.

17 September 2019 in Journal of Materials Chemistry C
Verified
Journal Article
Closed access
PDF file
ZZZhihui Zhao
Zhihui Zhao
DWDi Wu
Di Wu
JGJiawen Guo
Jiawen Guo
EWEnping Wu
Enping Wu
CJCheng Jia
Cheng Jia
YTYongzhi Tian
Yongzhi Tian
High-performance self-powered ultraviolet (UV) photodetector based on a WS 2 /GaN heterojunction was demonstrated, which exhibits excellent UV photoresponse properties. Significantly, this photodetector has exhibited excellent UV imaging capability.

27 July 2020 in Science China Physics, Mechanics & Astronomy
Verified
Journal Article
Closed access
PDF file
KLKaiyong Li
Kaiyong Li
Xun YangXun Yang
Xun Yang
YTYongzhi Tian
Yongzhi Tian
YCYancheng Chen
Yancheng Chen
CLChaonan Lin
Chaonan Lin
Chong-Xin ShanChong-Xin Shan
Chong-Xin Shan

27 July 2021 in Physica Status Solidi (RRL) – Rapid Research Letters
Verified
Journal Article
Closed access
PDF file
KLKaiyong Li
Kaiyong Li
JZJinhao Zang
Jinhao Zang
Xun YangXun Yang
Xun Yang
YTYongzhi Tian
Yongzhi Tian
CLChaonan Lin
Chaonan Lin
Chong-Xin ShanChong-Xin Shan
Chong-Xin Shan

2 January 2020 in Journal of Nuclear Science and Technology
Verified
Journal Article
Closed access
BZBin Zhang
Bin Zhang
MLMengmeng Liu
Mengmeng Liu
YTYongzhi Tian
Yongzhi Tian
GWGe Wu
Ge Wu
XYXiaohui Yang
Xiaohui Yang
JLJianning Li
Jianning Li
In order to effectively conduct the defect detection of nuclear fuel pellets end face and avoid the leakage of nuclear radiation, a defect detection system for the nuclear fuel pellets end face based on machine vision is proposed. Firstly, aiming at the complexity of the defect detection of nuclear fuel pellets, a set of image acquisition system lighted by left-right symmetric grating is designed. Then, after fusing the images of left-right structured light those cross points are extracted which classified based on the Gaussian mixture model (GMM). Finally, a series of morphological operations such as dilation operation are conducted for the classified points to obtain the defect area of nuclear fuel pellets end face. The experimental results show that this method reduces the influence of complex characteristics of form, texture, and color of the sample end face on the defect detection and relatively good detection results are gained for various defects with 99.5% accuracy. It takes less than 0.4 s to fully meet the requirements of industrial automation testing.

25 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
ESErjie Su
Erjie Su
YTYongzhi Tian
Yongzhi Tian
ELErjun Liang
Erjun Liang
JWJiayu Wang
Jiayu Wang
YZYibo Zhang
Yibo Zhang
The identification of wear rubber balls in the rubber ball cleaning system in heat exchange equipment directly affects the descaling efficiency. For the problem that the rubber ball image contains impurities and bubbles and the segmentation is low in real time, a multi-scale feature fusion real-time instance segmentation model based on the attention mechanism is proposed for the object segmentation of the rubber ball images. First, we introduce the Pyramid Vision Transformer instead of the convolution module in the backbone network and use the spatial-reduction attention layer of the transformer to improve the feature extraction ability across scales and spatial reduction to reduce computational cost; Second, we improve the feature fusion module to fuse image features across scales, combined with an attention mechanism to enhance the output feature representation; Third, the prediction head separates the mask branches separately. Combined with dynamic convolution, it improves the accuracy of the mask coefficients and increases the number of upsampling layers. It also connects the penultimate layer with the second layer feature map to achieve detection of smaller images with larger feature maps to improve the accuracy. Through the validation of the produced rubber ball dataset, the Dice score, Jaccard coefficient, and mAP of the actual segmented region of this network with the rubber ball dataset are improved by 4.5%, 4.7%, and 7.73%, respectively, and our model achieves 33.6 fps segmentation speed and 79.3% segmentation accuracy. Meanwhile, the average precision of Box and Mask can also meet the requirements under different IOU thresholds. We compared the DeepMask, Mask R-CNN, BlendMask, SOLOv1 and SOLOv2 instance segmentation networks with this model in terms of training accuracy and segmentation speed and obtained good results. The proposed modules can work together to better handle object details and achieve better segmentation performance.