朱新军

作者:发布时间:2020-08-30浏览次数:16360

朱新军

副教授

硕士生导师

研究生招生专业:人工智能、控制科学与工程、控制工程

研究方向:机器视觉与机器学习、光学三维测量

联系方式:xinjunzhu@tiangong.edu.cn

个人简介 ——————————————————————————————

主要研究基于人工智能的高精度、高速、动态条纹投影三维重建关键问题,该问题属于机器视觉、光学成像与人工智能的交叉领域。具体包括:(1)基于深度学习与深度神经网络,开展人工智能的高精度相位提取、相位展开、深度估计等条纹投影三维重建问题研究。(2)采用基于变分图像分解、多尺度几何分析工具等图像及信号处理方法对条纹图进行自适应分解与相位提取,提高相位提取的精度与重建速度。(3)开展光场成像与深度神经网络的三维重建关键问题研究及系统开发。以第一作者和通讯作者发表Optics Letters, Applied Optics等期刊SCI检索论文15EI检索论文5篇。指导本科生发表SCI二区期刊(Optics Express)论文1篇。出版机器视觉与机器学习教材1部。Optics ExpressOptics LettersApplied Optics、光学学报、激光光电子学进展等期刊审稿人。天津市131第三层次人才。天津市科技特派员。指导天津市大学生创新创业项目1项,国家大学生创新创业项目1项。

教育经历 ——————————————————————————————

2011.09-2015.01

天津大学

博士

2008.09-2011.06

山东理工大学

硕士

2004.09-2008.06

临沂师范学院

学士

工作经历 ——————————————————————————————

2022.01-至今

天津工业大学人工智能学院

副教授

2018.11-2021.12

天津工业大学人工智能学院

讲师

2015.01-2018.10

天津工业大学电气工程与自动化学院

讲师

主要科研项目 ————————————————————————————

[1] 国家自然科学基金青年基金项目,基于深度学习与光场成像的条纹结构光动态复杂场景三维测量,619051782020/01-2022/1223万元,结题,主持。

[2] 基于多角度动态光散射的气溶胶宽范围高分辨颗粒粒度分布测量研究, 天津市自然科学基金青年项目, 18JCQNJC711006万元,2018/10-2022/07, 6万元,结题,主持。

[3] 天津市高等学校基本科研业务费,基于偏振虚拟双目视觉的单帧条纹投影动态三维测量关键问题研究,2019KJ0216万元,在研,主持。

[4] 国家重点实验室开放基金“精密测试技术及仪器国家重点实验室”, 基于激光技术的高空间分辨率发动机叶片三维形态成像方法研究,2016/06-2019/068万元,结题,参加。

专著/教材———————————————————————————————

[1]宋丽梅、朱新军主编,机器视觉与机器学习:算法原理、框架应用与代码实,机械工业出版社,2020.

[2]宋丽梅,朱新军,李云鹏,机器视觉原理及应用教程,438千字,机械工业出版社,2023.

主要学术论文 ————————————————————————————

[1] Xinjun Zhu(*), Ruiqin Tian, Limei Song, Hongyi Wang, Qinghua Guo,Edge enhancement and feature modulation based network for light field depth estimation,Optics and Lasers in Engineering,184,1,2025,108662.

[2] Zhao, Y., Zhu, X. (*), Lan, T. et al. Binocular speckle structured light disparity estimation based on spatial pyramid densely connected stereo matching network. J Opt (2025).

[3] Xinjun Zhu(*), Tianyang Lan, Yixin Zhao, Hongyi Wang, and Limei Song, "End-to-end color fringe depth estimation based on a three-branch U-net network," Appl. Opt. 63, 7465-7474 (2024).

[4] ZHU Xinjun(*), ZHAO Haomiao, WANG Hongyi, SONG Limei, SUN Ruiqun. A hybrid network based on light self-limited attention for structured light phase and depth estimation[J]. Chinese Optics, 2024, 17(1): 118-127.

朱新军(*), 赵浩淼, 王红一, 宋丽梅, 孙瑞群. 基于轻型自限制注意力的结构光相位及深度估计混合网络[J]. 中国光学(中英文), 2024, 17(1): 118-127.

[5] 朱新军(*), 孙瑞群, 侯林鹏, 赵海川, 宋丽梅, 王红一. 基于区域立体匹配的单频条纹结构光三维测量[J]. 激光与光电子学进展, 2024, 61(10): 1011006.

[6] Xinjun Zhu(*), Haomiao Zhao, Limei Song, Hongyi Wang, Qinghua Guo, Triple-output phase unwrapping network with a physical prior in fringe projection profilometry, Applied Optics [J], 2023,62, 7910-7916.

[7] Xinjun Zhu(*), Zhiqiang Han, Zhizhi Zhang, Limei Song, Hongyi Wang and Qinghua Guo, PCTNet: depth estimation from single structured light image with a parallel CNN-transformer network, Meas. Sci. Technol.,2023, 34:085402.

[8] Zhu, X. (*), Zhao, H., Yuan, M. et al. Phase unwrapping based on deep learning in light field fringe projection 3D measurement. Optoelectron. Lett. 19, 556–562 (2023).

[9] Xinjun Zhu(*); Zhiqiang Han; Mengkai Yuan; Qinghua Guo; Hongyi Wang; Limei Song; Hformer: Hybrid convolutional neural network transformer network for fringe order prediction in phase unwrapping of fringe projection, Optical Engineering, 2022, 61(09)093107.

[10] 朱新军(*); 侯林鹏; 宋丽梅; 袁梦凯; 王红一; 武志超; 基于虚拟双目的条纹结构光三维重建, 红外与激光工程, 2022, 51(11)2021095.

[11] Zhu, X. (*), Han, Z., Song, L. et al.Wavelet based deep learning for depth estimation from single fringe pattern of fringe projection profilometry. Optoelectron. Lett.18, 699–704 (2022).

[12]袁梦凯; 朱新军(*); 侯林鹏; 基于R2U-Net的单帧投影条纹图深度估计, 激光与光电子学进展, 2022, 59(16)1610001-1610001.

[13] Jiashuo Shi, Xinjun Zhu(*), Hongyi Wang, Limei Song, and Qinghua Guo, Label enhanced and patch based deep learning for phase retrieval from single frame fringe pattern in fringe projection 3D measurement, Opt. Express,2019, 27, 28929-28943.

[14] Xinjun Zhu(*), Limei Song(*), Hongyi Wang, Qinghua Guo. Assessment of fringe pattern decomposition with a Cross-Correlation index for phase retrieval in fringe projection 3D measurements, Sensors, 2018, 18(10): 3578.

[15]Xinjun Zhu(*), Jing Li, John Thomas, Limei Song, Qinghua Guo, Jin Shen. Lp-norm-residual constrained regularization model for estimation of particle size distribution in dynamic light scattering. Applied Optics, 2017, 56(19): 5360-5368.

[16]Xinjun Zhu(*), Chen Tang, Biyuan Li, Chen Sun and Linlin Wang, Phase retrieval from single frame projection fringe pattern with variational image decomposition. Optics laser in engineering 59, 25-33 (2014).

[17]Xinjun Zhu(*), Chen Tang, Hongwei Ren, Chen Sun, and Si Yan. Image decomposition model BL-Hilbert-L2 for dynamic thermal measurements of the printed circuit board with a chip by ESPI. Optics and Laser technology 63 ,125-131 2014.

[18]Xinjun Zhu(*), Z. Chen, and C. Tang, "Variational image decomposition for automatic background and noise removal of fringe patterns," Opt. Lett. 38, 275-277 (2013).  

[19]Xinjun Zhu(*), Z. Chen, C. Tang, Q. Mi, and X. Yan, "Application of two oriented partial differential equation filtering models on speckle fringes with poor quality and their numerically fast algorithms," Appl. Opt. 52, 1814-1823 (2013). 

[20]Xinjun Zhu(*), J. Shen, and J. Thomas, "Analysis of noisy dynamic light scattering data using constrained regularization techniques," Appl. Opt. 51, 7537-7548 (2012).

[21]Xinjun Zhu(*), Jin Shen, Yuanlei Wang, et. al. The reconstruction of particle size distributions from dynamic light scattering data using particle swarm optimization techniques with different objective functions. Optics and Laser technology. 2011, 43(7):1128-1137.

[22] Xinjun Zhu(*), Jin Shen, Wei Liu, et al. Nonnegative least square truncated singular value decomposition to particle size distribution inversion from dynamic light scattering data. App. Opt., 2010, 49 (34):6591-6596.

会议论文

[1] Changheng Fan,Yuhang Wang, Kai Sun, Xinyi Cui, Zhizhi Zhang, and XinJun Zhu,"Depth estimation in light field structured light using SROACC-Net", Proc. SPIE 13288, Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024), 132880D (9 October 2024).

[2] X. Zhu(*), Z. Zhang, L. Hou, L. Song and H. Wang, "Light field structured light projection data generation with Blender,"2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA), Changchun, China, 2022, pp. 1249-1253.