头像

全红艳

职称: 副教授

直属机构: 计算机科学与技术学院

学科:

10 访问

相关教师

个人资料

  • 部门: 计算机科学与技术学院
  • 性别:
  • 专业技术职务: 教师
  • 毕业院校:
  • 学位: 博士
  • 学历:
  • 联系电话:
  • 电子邮箱: hyquan@cs.ecnu.edu.cn
  • 办公地址: 中山北路
  • 通讯地址:
  • 邮编: 200062
  • 传真:

教育经历

工作经历

2006,09 — 2019,06 华东师范大学 计算机科学与软件工程学院

2019,06 — Now  华东师范大学 计算机科学与技术学院

个人简介

社会兼职

中国计算机学会高级会员.


研究方向

人工智能,计算机视觉,图像处理,智能制造



目前研究兴趣点: 

    医学影像智能分析与可视化,医学影像精细分割与三维重建









开授课程

(1)计算机视觉

(2)数字图像处理

(3)操作系统

(4)图形图像处理技术


专著:

1. 全红艳,曹桂涛,数字图像处理原理与实现方法,机械工业出版社,2013,9787111447276

2. 全红艳,王长波,数字图像处理原理与实践,2017,9787111572909

3. 全红艳等,智能图像处理,科学出版社,2022年

4. 全红艳,数字图像处理:原理与智能技术,机械工业出版社,2022

5. 全红艳,数字图像处理实践:从入门到智能方法,械工业出版社,2022年


课程建设及获奖:

1. 上海市本科重点课程《数字图像处理》,2019

2. 上海普通高校优秀本科教材《数字图像处理原理与实现方法》,2015年,全红艳

3. 华东师范大学本科教学成果奖,2019年,《数字图像处理原理与实践》


科研项目

在研主持及近期参与开发的科研项目:

[1] 超声智能医疗辅助诊断关键技术研发

[2] 智能虚拟样机建模工具

[3] 工业互联网领域数据采集技术研发

[4] 预报产品展示辅助系统

[5] 基于云模式的虚拟机配置与管理系统

[6] ***遥感信息提取

[7] 增强现实中动态纹理重建与交互的关键技术研究


 








学术成果

在《Computer Animation and Virtual  Worlds》、《Multimedia System》《计算机学报》、《软件学报》、《电子学报》、《ICASSP》、《BIBM》等刊物和会议上发表多篇论文:

代表性学术论文:

[1] Hongyan Quan,Jiashun Dong,XiaoXiao Qian,Med-3D: 3D Reconstruction of Medical Images based on Structure-from-Motion via Transfer Learning,International Conference on Bioinformatics & Biomedicine, 2021(CCF B) 

[2] Shuying Xu, Hongyan Quan, ECT-NAS: Searching Efficient CNN-Transformers Architecture for Medical Image Segmentation,International Conference on Bioinformatics & Biomedicine, 2021(CCF B) 

[3]Hongyan Quan,Mingwei Yao,Xiaoxiao Qian, Geometry consistancy of augmented reality based on semantics, ICASSP2021.(CCF B)

[4] Shuying Xu,Hongyan Quan,LiteTrans: Reconstruct Transformer with Convolution for Medical Image Segmentation,The International Symposium on Bioinformatics Research and Applications,2021

[5]Xiaoxiao Qian, Hongyan Quan, Min Wu. PRNet: polar regression network formedical image segmentation,The Visual Computer,2021.

[6] Kaifei Shen,Hongyan Quan,Jun Han,Min Wu,URO-GAN: An untrustworthy region optimization approach for adipose tissue segmentation based on adversarial learning,Applied Intelligence,2021,accepted

[7]Ning Wang, Hongyan Quan, GLUNet: Global-Local Fusion U-Net for 2D Medical Image Segmentation,ICANN,2021

[8]Junjie Xue,Junhua Zhou,Guoqiang Shi,Yanhong Jiang,Shuying Xu,Hongyan Quan,Key Technique of Constructing Collaborating Environment based on OPENMBEE,2020 IEEE 6th International Conference on Computer and Communications, 2020.

[9] Junjie Xue,Junhua Zhou,Guoqiang Shi,Yanhong Jiang ,Bowen Wei,Hongyan Quan,A Model based Heterogeneous Data Collaboration Method, International Conference on Electronics and Communication Engineering,2020

[10] Chao Liu,Hongyan Quan. A Global-Local Architecture Constrained by Multiple Attributes for  Person Re-identification.International Conference on Artificial Neural Networks,2019

[11]Mingwei Yao,Hongyan Quan. An End-to-end Network for Monocular Visual Odometry Based on Image Sequence,International joint conference on neural networks,2019

[12] Zhen Wang, Hongyan Quan,Fashion Outfit Composition Combining SequentialLearning and Deep Aesthetic Network,International joint conference on neural networks,2019

[13]Hongyan Quan,Ning Wang, Jimeng Li, Changbo Wang, Extracting-mapping Scheme for Dynamic Detail in Fluid Re-simulation from Video,Multimedia Systems,2019

[14]Hongyan Quan, Xinquan Zhou, Changbo Wang,Illumination Recovery for Realistic Fluid Re-simulation,18th Asia Simulation Conference, AsiaSim 2018

[15]Shuangshuang Zhou, Hongyan Quan , Zilong Song, Changbo Wang,Terrain Synthesis Guided by User Hand Sketch, Asia Simulation Conference,2018

[16]HongyanQuan,ChangboWang,YahuiSong,  Fluid re-simulation based on physical driven model from video.The Visual Computer.

[17]Hongyan Quan(#)(*),Xiao Song,Mingqi Yu,Yahui Song,3D Fluid Scene Synthesis and Animation,Proceeding VRCAI '14 Proceedings of the 13th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry,2014,219-222

[18]Hongyan Quan(#)(*),Hanyu Xue,Xiao Song,3D Fluid Scene Synthesizing Based on Video,AsiaSim

2014,Communications in Computer and Information Science,2014,243-254

[19]Hongyan Quan(#)(*),Maomao Wu,Reconstruction of fluid surface using physical property,International Journal of Modeling, Simulation, and Scientific Computing,2014,93(23):63-75

[20]Mingqi Yu(#),Hongyan Quan(*),Fluid surface reconstruction based on specular reflection model,Computer Animation and Virtual World,2013,24(5):497-510

[21]Hongyan Quan(#)(*),Mingqi Yu,Xiao Song,Yan Gao,Real Time Reconstruction Fluid Video,International Journal of Modeling, Simulation, and Scientific Computing,2013,4(4):841-852

[22]全红艳(#)(*),王长波,一种流体运动矢量计算的有效方法,计算机学报,2013,36(6):1889-1897

[23]俞铭琪(#),全红艳(*),宋晓,真实感流体实时重建,计算机辅助设计与图形学学报,2013,25(5):622-630

[24]全红艳(#)(*),利用特征向量聚类的流体运动矢量计算,计算机辅助设计与图形学学报,2013,25(2):221-228

[25]Hanyu Xue(#),Hongyan Quan(*),Xiao Song,Maomao Wu,Construction of Simulation Environment based on Augmented Reality Technique,AsiaSim 2013 Communications in Computer and Information Science,2013,333-339

[26]Hongyan Quan(#)(*),Maomao Wu,A Real-Time SFM Method in Augmented Reality,International Conference on Information Technology and Software Engineering,2012,841-848

[27]Maomao Wu(#),Hongyan Quan(*),Fluid Motion Vector Calculation Using Continuity Equation Optimizing,AsiaSim 2012 Communications in Computer and Information Science 2012,372-380

[28]Hongyan Quan(#)(*),Dynamic Texture Recognition based on Fluid Motion Vector Calculation,International Conference on Multimedia Technology 2011


正在申请专利:

14.全红艳等,202011623215.0,一种基于特征迁移的超声或CT医学影像三维重建方法,实审阶段

13.全红艳等,202110878837.6,一种基于自注意力Transformer的超声或CT医学影像三维重建方法实审阶段

12. 全红艳等,202110881631.9,一种跨视图视觉Transformer的超声或CT医学影像三维重建方法审阶段

11. 全红艳等,02110881585.2,一种极线约束的稀疏注意力机制医学影像三维重建方法阶段

10. 全等,202110881619.8,一种两视图孪生Transformer的超声或CT影像跨模态三维重建方法阶段

9. 全等,202110881611.1,一种2D3D端对端的超声或CT医学影像跨模态重建方法阶段

8. 全红艳等,202110881635.7,一种基于互注意力Transformer的医学影像三维重建方法阶段 

7.全红艳等,202110881600.3,一种跨视图几何约束的医学影像三维重建方法,阶段 

6.全红艳,姚铭炜,CN201910530398.2,一种基于深度学习的场景深度和摄像机位置姿势求解方法,实审阶段

5.全红艳;王振,CN110263252A,一种基于深度学习的服装检索方法,实审阶段

4.全红艳;王振,CN201910564831.4,一种基于美学特征的服装搭配方法,实审阶段  

3.全红艳;周双双,CN109242922A,一种基于径向基函数网络的地形合成方法,实审阶段 

2.全红艳;周双双,CN201811430770.4,一种多尺度细节融合的地形合成方法,实审阶段

1.全红艳,刘超,CN201910941997.3,多属性约束的行人重识别方法,实审阶段

    

授权专利:

20.全红艳等,202011621411.4,一种基于迁移学习的超声或CT医学影像三维重建方法,授权

19.全红艳等,202011623243.2,一种超声或CT医学影像三维重建方法,授权

18.全红艳等,202011623217.X,一种基于极坐标的超声或者磁共振影像的分割方法,授权

17.全红艳等,202011623228.8,一种面向智能医疗辅助诊断的超声影像三维重建方法,授权

16. 全红艳等,202011621388.9,一种基于知识蒸馏的超声或CT医学影像的三维重建方法,授权

15.一种基于深度学习的图像目标抠图方法,201810649490.6,授权

14. 明度一致性学习的图像融合方法,20180650466.4,授权

13.一种深度图像空洞的自动填充方法,201611031251.1,授权 

12.一种物理数据驱动的真实感流体重仿真方法,201610624291.0,授权

11.真实感流体重仿真方法, 201610620770.5,授权

10.基于Phong模型的视频流体光照计算方法,201610624318.6,授权

9. 流体场景光照参数计算方法,ZL 201610363267.6,授权

8. 视频流体物理驱动模型恢复及重新仿真的方法,201410805222.0,授权

7. 具有时空连续性的真实感三维流体场景合成方法,201410315413,授权

6. 三维空间中真实感流体场景合成方法,201410033195.X,授权

5. 一种3D流体场景合成方法,ZL201310629156.1,授权

4. 一种基于视频的海浪场景生成方法,201310594347.9,授权

3. 一种真实感流体实时重建方法,201310120591,授权

2. 一种视频流体高度计算的方法,201210237823.7,授权

1. 一种视频流体运动矢量计算方法,201210237110.0,授权.


研究内容: 

医学影像跨模态三维重建  

Hongyan Quan,Jiashun Dong,XiaoXiao Qian,Med-3D: 3D Reconstruction of Medical Images based on Structure-from-Motion via Transfer Learning,International Conference on Bioinformatics & Biomedicine, 2021 

 


医学影像2D分割  

Xiaoxiao Qian, Hongyan Quan, Min Wu. PRNet: polar regression network formedical image segmentation,The Visual Computer

 

                    

增强现实虚实一致性

Hongyan Quan,Mingwei Yao,Xiaoxiao Qian, Geometry consistancy of augmented reality based on semantics, ICASSP2021.(CCF B)

  

  

行人重识别 

Chao Liu, Hongyan Quan.A GlobalLocal Architecture Constrained by Multiple Attributes for  Person Re-identification. International Conference on Artificial Neural Networks,2019  


    

摄像机参数恢复及深度估计

Mingwei Yao,Hongyan Quan. An End-to-end Network for Monocular Visual Odometry Based on Image Sequence,International joint conference on neural networks,2019


  

  

  

服装检索及基于美学特征的搭配

Zhen Wang, Hongyan Quan,Fashion Outfit Composition Combining SequentialLearning and Deep Aesthetic Network,International joint conference on neural networks,2019   

  


 

 

视频流体物理驱动的真实感仿真

Quan, H., Wang, N., Li, J. et al.Extracting-mapping scheme for the dynamic details in fluid re-simulations from videos.Multimedia Systems2019,25:371,SCI,https://doi.org/10.1007/s00530-019-00612-0  

  

 

  

  

  

智能地形构建技术

基于学习策略的地形合成技术研究,2018   

  

 

 

基于深度学习的图像合成

基于深度学习的图像合成技术研究,2018   

  

 

 

视频流体物理驱动估计

Quan, H., Wang, C. & Song, Y.Fluid re-simulation based on physically driven model from video.The Visual Computer (2017) 33: 85 


  

 

基于视频的3D流体场景合成

Hongyan  Quan,Xiao Song,Mingqi Yu,Yahui Song.3D Fluid Scene Synthesis and  AnimationProceeding VRCAI  '14 Proceedings of the 13th ACM SIGGRAPH International Conference on  Virtual-Reality Continuum and its  Applications in Industry,2014:219-222

 

  

基于物理属性的视频流体三维重建

Hongyan  QuanMaomao WuReconstruction of fluid surface using physical  propertyInternational Journal  of Modeling, Simulation, and Scientific Computing,2014,12


  

基于表面光照属性的流体表面重建

Yu, MQ. Quan, HY.Fluid  surface reconstruction based on specular reflection  model.Computer  Animation and Virtual Worlds,2013,24(5):497-510  


 

流体运动矢量计算

全红艳,王长波.一种流体运动矢量计算的有效方法,计算机学报,2013366):1889-1897

Han  Zhuang,Hongyan  Quan.Fluid Motion Estimation Based on Energy Constraint,AsiaSim Communications  in Computer and Information Science 2012, 308-318 


 

增强现实技术研究

Hanyu  XueHongyan Quan(*)Xiao SongMaomao WuConstruction of Simulation Environment  based on Augmented  Reality TechniqueAsiaSim 2013 Communications in Computer and Information Science333-339 

 

 

基于运动矢量计算的动态纹理识别

Hongyan  QuanDynamic Texture Recognition based on Fluid Motion Vector  CalculationInternational Conference  on Multimedia Technology 2011,308-318  


 

 

几何模型简化

全红艳,张田文,董宇欣.一种基于区域分割的几何模型简化方法,计算机学报,2006,10,1834-1842    

  

  

 

 

 

几何模型简化

全红艳,张田文.基于区域生长的网格模型分割技术,计算机辅助设计与图形学学报,2006,18(7)

全红艳,张田文.一种基于多区域并行的网格模型简化的两步法,机器人,2006,28(4)

  

  

 

  

摄像机标定

全红艳,张田文.一种新的利用模板进行摄像机自标定的方法,电子学报 2005年第11,电子学报200533    

  

  

  

  

荣誉及奖励