吴毅红             English

说明: \\192.168.82.248\html\Faculty\yhwu\6.jpg

　

研究员，博士生导师
　

机 器人视觉组

模 式识别国家重点实验室

中 国科学院自动化研究所

 


Email: yhwu at nlpr.ia.ac.cn

Tel:   +86-10-82544697

Fax:  +86-10-82544594


　


----------------------------------------------------------------------------------------------------------

**中国科学院 自动化研究所 模式识别国家重点实验室**
**机器人视觉课题组**


主要研究方向：
1. 基于RGB-D相机的SLAM
2. 基于深度学习的视觉定位（位置识别，特征匹配）
3. 基于深度学习的点云任务
4. 激光视觉惯导融合的SLAM
5. 视觉惯导融合的里程计
6. 基于激光的SLAM

招收 **3D 视觉方向实习生**，要求：
1. 有严谨的科学态度，**遵守学术道德规范，身心健康，遵纪守法**。
2. 工科专业的本科生、硕士及博士，对编程及学术研究有较强的兴趣；
3. 具有计算机视觉或深度学习相关基础知识；
4. **得到在校导师的许可**，保证半年以上的实习期。

享受所籍研究生同样的指导和补助待遇，具体如下：
1. 保持已有研究方向并得到导师指导，或参与课题组的研究型项目；
2. 指导发表高水平论文（参与论文撰写或独立撰写），如机器人领域顶级会议ICRA、IROS等，视觉领域顶级会议CVPR、ICCV、ECCV等。
3. 实习工资。

其他：
1. 充足的**个人工作站及服务器等**计算资源。
2. 将深入参与知名企业委托的前瞻性课题。
3. 可提供实习证明及推荐信，表现优异者优先获得实验室硕、博深造机会。
4. 地点：北京市海淀区中关村东路95号

有意者请发送简历至yhwu@nlpr.ia.ac.cn，邮件标题请注明“姓名+应聘实习生”。
此招聘长期有效。　

----------------------------------------------------------------------------------------------------------

3DV 2020 Tutorial: Visual Localization in the Age of Deep Learning

ACCV 2018 Tutorial: Developments of 3 Dimensional Computer Vision Since 2017     PDF

_____________________________________________________________________________________________

　

　

研 究领域

1.  多视几何理论研究，几何不变量与括号代数在视 觉中的应用

2.  相 机标定与定位，图像匹配，三维重建，SLAM， 移动视觉等  

3.  SLAM应 用：机器人定位与导航，AR，VR

　

　

代 表 性论文

  1. Y. Wu, Y.F. Li, and Z. Hu. Detecting and Handling Unreliable Points for Camera Parameter Estimation.International Journal of Computer Vision (IJCV), Vol. 79, No. 2, pp. 209-223, 2008. PDF
  2. Y. Wu and Z. Hu. Invariant Representations of a Quadric Cone and a Twisted Cubic. 
    IEEE Transactions on Pattern Analysis and Machine Intelligence     (PAMI), Vol. 25, No. 10, pp. 1329-1332, 2003. PDF      
  3. Y. Wu and Z. Hu. Geometric Invariants and Applications under Catadioptric Camera Model. 
    The 10th International Conference on Computer Vision     (ICCV), pp.1547-1554, 2005.     PDF
  4. Y. Wu, H. Zhu, Z. Hu, and F. Wu. Camera Calibration from the Quasi-Affine Invariance of Two Parallel Circles. 
    The 8th European Conference on Computer Vision     (ECCV), pp. 190-202, 2004.     PDF
  5. P. Gurdjos, P. Sturm, and Y. Wu. Euclidean Structure from N>=2 Parallel Circles: Theory and Algorithms. 
    The 10th  European Conference on Computer Vision     (ECCV), pp. 238-252, 2006. PDF
  6. Y. Wu, X. Li, F. Wu, and Z. Hu. Coplanar Circles, Quasi-Affine Invariance and Calibration.  
    Image and Vision Computing    , Vol. 24, Iss. 4, pp. 319-326, 2006.     PDF
  7.  Y. Wu and Z. Hu. PnP Problem Revisited. 
    Journal of Mathematical Imaging and Vision    , Vol. 24, No. 1, pp. 131-141, 2006. PDF
  8.  H. Li and Y. Wu. Automated Short Proof Generation with Cayley and Bracket Algebras I. Incidence Geometry. 
    Journal of Symbolic Computation    , Vol. 36, Iss. 5, pp. 717-762, 2003.
  9.  H. Li and Y. Wu. Automated Short Proof Generation with Cayley and Bracket Algebras II. Conic Geometry. 
    Journal of Symbolic Computation    , Vol. 36, Iss. 5, pp. 763-809, 2003.
  10. H. Li and Y. Wu. Filtered-Graded Transfer of Groebner Basis Computation in Solvable Polynomial Algebra. 
    Communications in Algebra    , Vol.28, No.1, pp. 15-32, 2000.
  11. B. Zhang, Y. Li, and Y. Wu. Self-Recalibration of a Structured Light System via Plane-Based Homography. Pattern Recognition, Vol. 40, Iss. 4, pp. 1368-1377, 2007.
  12. F. Wu, F. Duan, Z. Hu, and Y. Wu. A New Linear Algorithm for Calibrating Central Catadioptric Cameras. Pattern Recognition, 41(10): 3166-3172, 2008.
  13. Zhijun Dai, Yihong Wu, Fengjun Zhang, and Hongan Wang. A Novel Fast Method for L_infinity Problems in Multiview Geometry. ECCV, pp. 116-129, 2012.
  14. Yihong Wu, Zhanyi Hu, and Youfu Li. Radial Distortion Invariants and Lens Evaluation under a Single-Optical-Axis Omnidirectional Camera. Computer Vision and Image Understanding, 126: 11-27, 2014. PDF
  15. Wei Liu, Yihong Wu, Fusheng Guo, and Zhanyi Hu. An Efficient Approach of 2D to 3D Video Conversion Based on Piece-wise Structure from Motion. The Visual Computer, Vol. 31, Iss. 1, pp 55-68, January, 2015.  PDF
  16. Youji Feng, Lixin Fan, and Yihong Wu. Fast Localization in Large Scale Environments Using Supervised Indexing of Binary Features. IEEE Transactions on Image Processing, Vol. 25, No. 1, pp. 343-358, 2016.   PDF
  17. Youji Feng, Yihong Wu, and Lixin Fan. Real-time SLAM Relocalization with On-line Learning of Binary Feature Indexing. Machine Vision and Applications, 2017.
  18. Xiaomei Zhao, Yihong Wu, Guidong Song, Zhenye Li, Yazhuo Zhang, Yong Fan. A Deep Learning Model Integrating FCNNs and CRFs for Brain Tumor Segmentation. Medical Image Analysis, Vol. 43, pp. 98-111, 2018.
  19. Yihong Wu, Fulin Tang, and Heping Li. Image Based Camera Localization: an Overview. Invited paper by Visual Computing for Industry, Biomedicine and Art, 2018. PDF
  20. Haoren Wang, Juan Lei, Ao li, and Yihong Wu. A Geometric based Point Cloud Reduction Method for Mobile Augmented Reality. Journal of Computer Science and Technology, 2018.
  21. Yihong Wu, Haoren Wang, Fulin Tang, and Zhiheng Wang. Efficient Conic Fitting with a Polar-N-Direction Geometric Distance. Pattern Recognition, 2019.
  22. Fulin Tang, Heping Li, Yihong Wu. FMD Stereo SLAM: Fusing MVG and Direct Formulation Towards Accurate and Fast Stereo SLAM. ICRA, 2019.
  23. Lang Wu, Yihong Wu. Similarity Hierarchy Based Place Recognition by Deep Supervised Hashing for SLAM. IROS 2019.
  24. Xiaomei Zhao, Yihong Wu. Automatically Extract Semi-transparent Motion-blurred Hand from a Single Image. IEEE Trans. on Signal Processing Letters, Vol. 26, No. 11, pp. 1598- 1602, 2019.
  25. Fulin Tang, Yihong Wu, Xiaohui Hou, Haibin Ling. 3D Mapping and 6D Pose Computation for Real Time Augmented Reality on Cylindrical Objects. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 30, Issue 9, pp. 2887-2899, 2020.
  26. Hao Wei, Fulin Tang, Chaofan Zhang, Yihong Wu. Highly Efficient Line Segment Tracking with an IMU-KLT Prediction and a Convex Geometric Distance Minimization. ICRA 2021.
  27. Bingxi Liu, Fulin Tang，Yujie Fu, Yanqun Yang, Yihong Wu. A Flexible and Efficient Loop Closure Detection based on Motion Knowledge. ICRA 2021.
  28. Yujia Zhai, Fulin Tang, Weijun Li, Jian Xu, Yihong Wu. 3OFLR-SLAM: Visual SLAM with 3D-assisting Optical Flow and Local-RANSAC. ACPR, 2021.
  29. Pengju Zhang, Chaofan Zhang, Zheng Rong, Yihong Wu. Learning to Decompose and Restore Low-light Images with Wavelet Transform. ACM MM Asia, 2021.
  30. Zewen Xu, Zheng Rong, Yihong Wu. A Survey: Which Features are Required for Dynamic Visual SLAM? Visual Computing for Industry, Biomedicine, and Art, 2021.
  31. Hao Wei, Fulin Tang, Zewen Xu, Chaofan Zhang, Yihong Wu. A Point-Line VIO System with Novel Feature Hybrids and with Novel Line Predicting-Matching. IEEE Robotics and Automation Letters, 2021. 
  32. Pengju Zhang, Chaofan Zhang，Bingxi Liu, and Yihong Wu. Leveraging Local and Global Descriptors in Parallel to Search Correspondences for Visual Localization. Pattern Recognition, 2021.
  33. 龙霄潇,程新景,朱昊,张朋举,刘浩敏,李俊,郑林涛,胡庆拥,刘浩,曹汛,杨睿刚,吴毅红,章国锋,刘烨斌,徐凯,郭裕兰,陈宝权. 三维视觉前沿进展.中国图象图形学报,2021,26(06):1389-1428.

 

 

 

发表论文列表

　

　

视觉定位研究展示

1. 基于视觉的移动增强现实

 

ms2ms1  


                  

2. 动 态目标SLAM

 

 

HSLAM

cylinder SLAM

 

 

3. 场景SLAM

 

SceneSLAM

 

 

4. SLAM重 定位

 

ReL1

ReL2

 

 

5. 结合IMU的SLAM

 

　

SLAM with IMU


6. SLAM devices

研制多款软硬协同实时在线三维重建设备，室内外皆可

SLAM device


　

个 人简历

1995年毕业于山西雁北师院获本科学位；1998年毕业于陕西师范大学获硕士学位，导师李会师教授；2001年6月 毕业于中国科学院系统科学研究所获博士学位，导师李洪波研究员；之后到模式识别国家重点实验室做博 士后，导师胡占义研究员。2003年被评为副研究员；2008年 被评为研究员。2005年，2010年，被法国IRIT实 验室邀请合作研究。2006年至 2008年，被香港城市大学多次邀请合作研究。获1项高等学校科学研究自然科学奖二等奖，排名第三。获三星电子校企合作卓越 贡献奖。首批阿里菜鸟驼峰计划特约专家。申请多项 国内外发明专利，多项被授权。

 

 

教学

Semester

Course

Place


      2001 秋季

射影几何

中国科学院自动化研究所

   
2002-2008 春季

射影几何与三维视觉


中国科 学院研究生院

2017-今， 春季          机器人定位导航        中国科学院大学
 

　

 

学 术活动

Area Chair of CVPR 2021

Associate Editor of Pattern Recognition

Area Chair of ICPR 2018

Area Chair of PRCV 2021

SPC of IJCAI 2019/2020/2021

Editorial Board Member of ACTA AUTOMATICA SINICA

Editorial Board Member of Journal of CAD & CG

Editorial Board Member of Journal of Frontiers of Computer Science and Technology

Editorial Board Member of the Open Artificial Intelligence /Computer Science Journal

Editorial Board Member of CADDM

PC Member of VISUAL 2007

PC Member of ICCV 2007

PC Member of PCM 2007

PC Member of WCICA 2008

PC Member of CVPR 2008  

Session Chair of ACCV 2007

Session Chair of RIUPEEEC 2005

PC Member of KES 2009

Reviewer of ICCV 2009/ACCV 2009

CSIG 三维计算机视觉专委会副主任

CSIG 机器视觉专委会常委

特 邀报告

1.  吴 毅红，国际会议，图像科学和信息处理中的数学与计算大会,“PnP Problem Revisited”，新加坡，2003年10月.

2.  吴毅红，国内会议，第三届全国几何设计与计算 学术会议，“计算机视觉的任务及目前研究的现状”，兰州，2007年7月.

3.  吴毅红，国内会议，全国数学与信息科学研究生 学术研讨会，“计算机视觉的历史和现状”，北京，2008年12月.

4.  吴毅红，国内会议，中国自动化大会暨钱学森诞 辰一百周年，“视觉定位和三维建模”，北京，2011年11月.

5.  吴毅红，国际会议，三星研究院计算机视觉研讨 会，“Efficient Pose Tracking and Mapping”，2014年7月.

6.  吴毅红，国际会议，WCR，“Camera Localization and 3D Mapping in Large Scale Environments”, 2015年9月.

7.  吴毅红，国内会议，系统科学青年学者论坛,“大数据的视觉定位与三维重建& rdquo;, 2015年12月.

8.  吴毅红，国内会议，RACV，“基于图像的定位：发展与应用& amp; rdquo;，2016年9月.

9.  吴毅红，国内会议，Vision China，“视觉建模与定位 ”，2016年10月.

10. 吴毅红，国内会议，华为北研工程技术论坛，& ldquo;视觉建模与定位研究”，2016年12月.

11. 吴毅红，国内会议，全球人工智能大会，“三 维视觉研究及应用”，2017年5月.

12. 吴毅红，国内会议，VALSE，“2017年以来的2Dto3D& rdquo;，2018年4月22日.

 

 

 

主 持课题

Single view based metrology (863)

A study on the theory and algorithm of camera self-calibration (NSFC)

Geometric invariant computation and camera pose determination from n perspective points (NSFC)

Image based 3-dimensional reconstruction (973)

Camera parameter computation from video sequence (Key NSFC)

Ominidirectional camera calibration (IA)

Study on image invariants and applications under multiple camera models (NSFC)

Image-based modeling for complex and large scale environment (NLPR)

Visual SLAM (Nokia RC in Finland)

Non-planar object tracking (Samsung)

Camera pose tracking (Samsung)

VR pose tracking (Huawei)

　

 

 

举 办国际会议

 

The First Workshop on Community Based 3D Content and Its Applications in Mobile Internet Environments,In conjunction with ACCV 2009

 

 

The Second Workshop on Community Based 3D Content and Its Applications,In conjunction with ICME 2012

 

 

ACCV 2018 Tutorial

Developments of 3 Dimensional Computer Vision Since 2017

 

Virtual reality (VR), augmented reality (AR), robotics, and autonomous driving have recently attracted much attention from the academic as well as the industrial community. 3 dimensional (3D) computer vision plays important roles in these fields. Autonomous localization and navigation is necessary for a moving robot, where using cameras is the most flexible and low cost approach for building map and localization. To augment reality in images, camera pose determination or localization is needed. To view virtual environments, the corresponding viewing angle is necessary to be computed. Furthermore, cameras are ubiquitous and people carry mobile phones that have cameras every day. There have been some AR applications in mobile phones. Therefore, 3D computer vision has great and widespread applications.

 

This tutorial will provide the developments of 3D computer vision of the past two years. The important works since 2017 will be introduced in image matching, camera localization including camera pose determination and simultaneous localization and mapping (SLAM), 3D reconstruction. 

 

The contents have five parts:

1. Preface

Some fundamental knowledge of 3D vision is introduced as well as some events related to 3D vision in this past two years.

 

2. Developments in image matching

Some important works of image feature detectors and descriptors since 2017 are introduced. Also, some important woks of image matching and two dataset since 2017 are introduced. Among these works, deep learning based methods are growing.

 

3. Developments in camera localization

A complete classification of image based camera localization mapped as a tree structure is given. The important directions are pointed out. The developments of camera localization in both known environments and unknown environments are introduced since 2017. The ones in known environments are PnP works. The ones in unknown environments are SLAM works. SLAM works include the general geometric SLAM, learning SLAM, semantic SLAM, and marker SLAM. Except SLAM under the traditional cameras, there are some SLAM works under the event cameras and RGBD cameras.

 

4. Developments in 3D reconstruction

This part will introduce structure from motion (SFM) based 3D reconstruction, learning 3D reconstruction, RGBD 3D reconstruction or RGBD SLAM since 2017. 

 

5. Trends of 3D vision

I will share my views for 3D vision trends.

 

PDF

 

 

3DV 2020 Tutorial:

 Visual Localization in the Age of Deep Learning

 

 

A short description:

Deep learning is a subset of machine learning and one of the foundations of Artificial Intelligence. Recent years see its remarkable development and wide applications. It has been used in almost every task of computer vision field and shows its powerful ability. 3D computer vision, developed under the Marr framework, re-blooms by deep learning again. Visual localization, a key task in 3D computer vision, has many applications in AR, VR, robot navigation, and driverless car. Deep learning has been used in visual localization by various ways. There are end-to-end and non-end-to-end deep learning visual localizations. The main topics in visual localization include image feature extraction and description, image matching, image retrieval, 2D-3D matching, RANSAC, PnP, feature tracking, loop closure detection, SLAM, bundle adjustment. All these have combined deep learning.

The tutorial consists of five parts. In the first part, this tutorial will give an overview of visual localization, share with some personal viewpoints to use deep learning in 3D vision. In the second part, the tutorial will introduce some important literatures in image feature extraction and description, and matching with deep learning. Then, work of camera pose determinations from known 3D structure knowledge with deep learning is reported in the third part, including the work of image retrieval, 2D-3D matching, RANSAC, and PnP. In the fourth part, work of SLAM with deep learning is reported, including the work of feature tracking, loop closure detection, bundle adjustment etc. As we see, every aspect combines deep learning in visual localization. It shows free exploration to use deep learning. Finally, i.e. in the last part, some personal views are shared for some existing problems when using deep learning, for example, there are no clear training dataset and test dataset given in some public dataset. Besides, future trends for visual localization are also shared.

 

Syllabus:

The contents have five parts:

1. An overview of visual localization

Some fundamental knowledge of 3D vision and an overview of image-based localization are introduced. A complete classification of image-based localization mapped as a tree structure is given. The possible best way to use deep learning in 3D vision is also analyzed.

 

2. Image feature representation and matching with deep learning

Some important literatures of image feature detectors and descriptors with deep learning are introduced. Also, some important literatures of image matching with deep learning and dataset are introduced.

 

3. Camera pose determination from known 3D structure knowledge with deep learning

Deserved studies with deep learning are pointed out. The developments of camera localization in known environments are introduced. PnP and RANSAC using deep learning are also presented.

 

4. SLAM with deep learning

This part will introduce some learning-based SLAM, recent new dataset, and challenges. It also includes feature tracking from videos, loop closure detection, bundle adjustment etc.

 

5. Problems and trends when view geometry using deep learning

Some personal views are shared for some problems and trends when view geometry using deep learning.

 

 

 

 ______________________________________________________________________________________________________________________________

Last Updated  by Yihong Wu, September 2020