Tao Yang

Professor   Ph.D

杨涛 教授

Shaanxi Provincial Key Laboratory of Speech and Image Information Processing(SAIIP)
School of Computer Science
Northwestern Polytechnical University
Xi'an, Shaanxi, P.R. China

Email: yangtaonwpu@163.com tyang@nwpu.edu.cn

Mailing address: PO Box 886, School of Computer Science,Chang'an Campus,Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China, 710129

Google Scholar Citations: TaoYang ········?/span>主讲课程:数字图像处理 (Digital Image Processing)       中文简历:Chinese CV



Jump to:CV

?/span>| Education | Research Experiences | News | Research interests | Teaching | International Competition | Fundings and Projects | Publications | Demos |Presentations and Slides | Professional Activities | My Students and Thesis |Links


Dr. Yang is a Professor in School of Computer Science at Northwestern Polytechnical University, Xi'an, China. His research interests is concerned with algorithms and applications for video scene understanding, such as real time tracking, hybrid camera array based occluded object imaging, aerial video stabilization, mosaicing and analysis, multiple camera information processing.

Dr.Yang was born in ShaanXi province, China in 1979. He received his Bachelor degree in Automation, Master degree and Ph.D. degree in Control Theory and Engineering from Northwestern Polytechnical University, Xi'an, China, in 2001, 2003 and 2008, respectively. From December 2013 to December 2014, he is a Visiting Scholoar in Grapic and Imaging Lab, University of Delaware, Newark, DE USA. From September 2008 to September 2010, he was a Post-Doctoral Fellow in Shaanxi Provincial Key Laboratory of Speech and Image Information Processing(SAIIP), Northwestern Polytechnical University, Xi’an, China. From August 2006 to January 2007, he was invited as the first overseas Chinese intern at Multimedia Group, FX Palo Alto Laboratory (FXPAL), Palo Alto, CA, USA. From September 2003 to March 2004, He was a visiting scholar in National Laboratory of Pattern Recognition (NLPR), Beijing, China. From April 2004 to June 2004, he was a visiting student of visual computing group, Microsoft Research Asia (MSRA). In 2006, he received the HP Excellent Chinese Student Award from the China Scholarship Council.

He has received the Soaring Star Award of Northwestern Polytechnical University in 2011, and The First Prize of Teaching Contest of Young Teachers of Northwestern Polytechnical University in 2013,and The First Prize of Excellent Teacher of NPU in 2013, and New Soaring Star Award of NPU in 2014. He has published over 40 tyang/papers and applied 4 US patents and over ten Chinese patents in the fields of computer vision and pattern recognition. As the Principal Investigator, he hosted 8 research fundings include two National Science Foundations of China (NSFC), Special Foundation for Excellent Chinese Post-Doctoral, NPU Foundation for New Direction, NPU Foundation for Fundamental Research etc. As the Technical Leader, he lead 4 projects include the National Hightech R&D Program of China (863 program). As the Key Member, he has participated two National Science Foundations of China (NSFC). He served as the reviewer for IEEE Transactions on Circuits and Systems for Video Technology, Optics & Laser Technology, International Journal of Image and Vision Computing (IVC), Optical Engineering etc. From 2013 he served as the reviewer for National Science Foundations of China (NSFC).


Research Experiences


Research interests


International Competition

Fundings and Projects




The Wings of Light---Vision Guidance Landing System Automatically


We - the wings of light,on bahalf of the NorthWestern Polytechnical University,participated in the thrid international UAV Innovation Competition in the 2015.

The Wings of Light-Vision Gudiance Landing System Automatically[DEMO]

2015 UAV Innovation Competition:We cheer for you, We also cheer for ourselves! The Best Times !

The Wings of Light Team. The Best Performance!


Moving video synthetic aperture imaging (on going project)





Camera Array Automatic Focusing Through Occlusion




Autofocus is a fundamental and key problem for modern imaging sensor designing. Although this problem has been well studied in the single camera literature, unfortunately, little research work has been done on large scale camera array. Most of the existing synthetic aperture imaging system still needs to manually select the optimal plane of focus while object moving. Unlike the conventional autofocus method, which sweeps the focus plane to find the maximal contrast, we present a novel optimization framework to handle the above challenges. In particular, we formulate the camera array autofocus problem as a constrained optimization problem by minimizing the temporal and spatial correspondences error subject to global loop constraint. Then this problem is relaxed as a quadratic program and solved using sequential quadratic programming. The experimental results show that the proposed method achieves a better performance compared with the results of traditional methods.



Real-time Hybrid Synthetic Aperture Detection, Imaging and Tracking system





Network Camera Array based Synthetic Aperture Imaging System






Multiple Camera Multiple People Detection and Tracking





Panoramic Camera with Pyramid Mirror





Multiple Camera Detection and Tracking System





Flying Sword: A Real-time Motion Video Analysis System



Developing a fully automatic, efficient and robust video content analysis system is a subject of great scientific and commercial interest. Intelligent video content analysis with a static camera has been well researched over the past decade, and many excellent algorithms and systems have been proposed in the literature. However, robust video content analysis for moving camera is still a challenge currently, and we saw this technology gap as an opportunity to develop our own advanced video processing algorithms and system,for important applications such as aerial video surveillance, wide-area monitoring, and moving camera based moving object tracking.

The FlyingSowrd was originally developed to perform video stabilization, but recent developments have added new algorithms and greatly improve its effective and efficiency. Currently, FlyingSword is a real-time system capable of performing registration, mosaicing, stabilization, moving object detection,tracking of videos taken from moving platforms.

The FlyingSword System mainly contains two components: (1) Global motion compensation, and(2)moving object detection and tracking. Global motion compensation. Motion compensation is the premise and key technology of aerial video stabilization, panorama stitching and ground moving target detection and tracking. In FlyingSword System, we develop a novel scene complexity and invariant feature based motion video registration algorithm. Detecting moving objects automatically is a key component of an automatic visual surveillance and tracking system. In many application fields such as airborne surveillance, the moving objects (car, people) may be small, sometimes even color information is not available (thermal video). To handle this problem, we use Motion Histogram Image (MHI) and cumulative object motion over an image sub-sequence for foreground segmentation. Tracking is the fundamental block for the high level content analysis and exploitation. Currently, blob tracking is implemented for its simplicity and efficiency, we implement Global Nearest Neighbor (GNN) for data association, and similarity scores between tracks and new measured blobs are estimated by computing their spatial distance. For occlusion handling, we maintain object moving direction, velocity as well as object appearance model. To deal with broken trajectories, a post-processing algorithm is under developed to create a global tracking trajectory.



Passenger Counting In Traffic Bus With A Single Camera



Automatic counting of passenger is very important for both business and security applications. This project takes a single camera based vision system which is able to count passenger in a highly crowded situation at the entrance of traffic bus. The unique characteristics of the proposed system include: (1) A novel feature point tracking and online clustering based passenger counting framework is presented, which performs much better than those of background modeling and foreground blob tracking based methods. Moreover, this framework is general and can be easily implemented in other passenger counting application fields. (2) A simple and highly accurate clustering algorithm is developed, which projects the high dimensional feature point trajectories into a two dimensional feature space by their appearing and disappearing time, and count the number of people through online clustering. (3) All test video sequences in the experiment are captured from real traffic bus in ShangHai city, and the results show that the system can process two 320x240 video sequences at a frame rate of 25fps simultaneously, and count passengers reliably in various difficult scenarios with complex interaction and occlusion among people, achieves high accuracy rates up to 96.5%.

TaoYang, Yanning Zhang, DapeiShao, YingLi. Clustering method for counting passenger getting in a bus with single camera. Optical Engineering, 49(037203), March 2010 [pdf]



Intelligent Video Survelliance Systems





DOTS: Dynamic Object Tracking System





Real-time 3D reconstruction System









Journal Paper:

  1. TaoYang, JingLi, Jingyi Yu, Sibing Wang, Yanning Zhang.Diverse Scene Stitching from Large-scale Aerial Video Dataset.Remote Sensing, 2015, 7, 6932-6949. ( IF:3.180) [LINKS]
  2. TaoYang, JingLi, Jingyi Yu, Yanning Zhang,WenguangMa, Xiaomin Tong, RuiYu,Lingyan Ran. Multiple-Layer Visibility Propagation-Based Synthetic Aperture Imaging through Occlusion. Sensors, 2015, 15, 18965-18984. ( IF:2.245) [LINKS]
  3. TaoYang, Wenguang Ma, Sibing Wang, JingLi, Jingyi Yu, Yanning Zhang.Kinect based real-time synthetic aperture imaging through occlusion.Multimedia Tools and Applications, 2015 ( IF:1.058) [LINKS]
  4. Yanning Zhang, Xiaomin Tong, TaoYang, Wenguang Ma. Multi-Model Estimation based Moving Object Detection for Aerial Video.Sensors, 15(4), 8214-8231,2015 ( IF:2.245) [LINKS]
  5. TaoYang, YanningZhang, RuiYu, XiaoqiangZhang, TingChen, Lingyan Ran, Zhengxi Song, Wenguang Ma.Simultaneous Camera Array Focus Plane Estimation and Occluded Moving Object Imaging.Image and Vision Computing, Elsevier,DOI:10.1016/j.imavis.2014.05.001, 2014 (5-year IF:2.059) [LINKS]
  6. TaoYang, YanningZhang, Xiaomin Tong, XiaoqiangZhang, RuiYu. A New Hybrid Synthetic Aperture Imaging Model for Tracking and Seeing People Through Occlusion.IEEE Transactions on Circuits and Systems for Video Technology.23(9): 1461-1475,2013  [LINKS] (IF:2.259)
  7. TaoYang, Yanning Zhang, Xiaomin Tong, Wenguang Ma, Rui Yu.High Performance Imaging Through Occlusion via Energy Minimization-Based Optimal Camera Selection.International Journal of Advanced Robotic Systems,2013 [LINKS] (IF:0.821)
  8. TaoYang, Yanning Zhang, RuiYu, TingChen. Exploiting Loops in the Camera Array for Automatic Focusing Depth Estimation.International Journal of Advanced Robotic Systems, vol.10,2013. (IF:0.821) [LINKS]
  9. Z.Pei, Y.N.Zhang, T.Yang, X. Zhang, and Y.H. Yang.A Novel Multi-Object Detection Method in Complex Scene Using Synthetic Aperture Imaging.Pattern Recognition. 2012,45(4) :1637-1658 (IF:2.584) [pdf]
  10. TaoYang, Yanning Zhang, DapeiShao, YingLi. Clustering method for counting passenger getting in a bus with single camera. Optical Engineering, 49(037203), March 2010 (IF:0.958) [pdf]
  11. Jing Li, Tao Yang, Jingyi Yu, Zhaoyang Lu etc. Fast Aerial Video Stitching.International Journal of Advanced Robotic Systems, 2014, 11:167. doi: 10.5772/59029 (IF:0.821)
  12. Xiaomin Tong,Yanning Zhang,TaoYang. Robust object tracking based on adaptive and incremental subspace learning. ACTA AUTOMATICA SINICA. [pdf]
  13. TaoYang, Yanning Zhang, XiuweiZhang,Xingong Zhang.Scene complexity and invariant feature based aerial video registration. ACTA ELECTRONICA SINICA, 2010 [pdf]
  14. TaoYang,JingLi,QuanPan,Yanning Zhang. Scene model and statistic learning based pedestrian detection.ACTA AUTOMATICA SINICA, 2010,36(4): 499-508 [pdf]
  15. TaoYang,JingLi,QuanPan,Yanning Zhang.Pepole tracking through occlusion. ACTA AUTOMATICA SINICA, 2010,36(3): 375-384 [pdf]
  16. Xiuwei Zhang,Yanning Zhang,TaoYang,Xingong Zhang,Dapei Shao. Co-motion based CCD/IR video registration. ACTA AUTOMATICA SINICA, ,2010.9 [pdf]
  17. TaoYang, JingLi, QuanPan, YongmeiCheng. Real-time object tracking with automatic confident region extraction. International Journal of Image and Graphics,2008,8(3):369~381
  18. TaoYang, Stan Z.Li, QuanPan, Jing Li, Chunhui Zhao, Yongmei Cheng. Online adaptive fast multipose face tracking based on visual cue selection.ACTA AUTOMATICA SINICA, 2008,14~20 [pdf]
  19. TaoYang,JingLi,QuanPan,YongmeiCheng.A multiple layer background model for foreground detection. Chinese JOURNAL OF IMAGE AND GRAPHICS.2008, 13(7):1303~1308 [pdf]
  20. Jing Li,TaoYang,QuanPan,YongmeiCheng.Invariant feature based motion video registration. Chinese JOURNAL OF IMAGE AND GRAPHICS. 2008,13(2):335~344
  21. Jing Li,TaoYang, Quan Pan, Yongmei Cheng. A novel algorithm for speeding up keypoint detection and matching. International Journal of Image and Graphics, 2008,8(4):643~661
  22. Jing Li, TaoYang, Quan Pan, Yongmei Cheng. Combing scene model and fusion for night video enhancement. Journal of Electronics (China), 2009,26(1): 88-93
  23. Y. Xie, L. Xing, D. Paquin, D. Levy, T. Yang. Deformable Image Registration with Inclusion of Auto-detected Homologous Tissue Features. International Journal of Radiation Oncology, Biology, Physics, 2007, 69(3): S646~S647 (IF:4.176)

Conference Paper:

1.      Tao Yang, Yanning Zhang, Jingyi Yu, Jing Li, Wenguang Ma, Xiaomin Tong, Rui Yu, Lingyan Ran.All-In-Focus Synthetic Aperture Imaging. Europeon Conference on Computer Vision (ECCV),Vol 8694, 2014, pp 1-15. [LINKS]

2.      TaoYang, YanningZhang, Xiaomin Tong, XiaoqiangZhang, RuiYu. Continuously tracking and see-through occlusion based on a new hybrid synthetic aperture imaging model. IEEE Computer Vision and Pattern Recognition Conference (CVPR), Colorado Springs, USA, 2011 [pdf]

3.      TaoYang, Stan Z.Li ,Quan Pan, Jing Li. Real-time multiple object tracking with occlusion handling in dynamic scenes. IEEE Computer Vision and Pattern Recognition Conference (CVPR), San Diego, USA, 2005, 970~975 [pdf] (Cited by Google Scholar: 200+)

4.      TaoYang, Xiaoqiang Zhang, Lingyan Ran, RuiYu, Runping Xi. Camera Array Synthetic Aperture Focusing and Fusion based Hidden Object Imaging. 2011 Sino-foreign-interchange Workshop on Intelligence Science and Intelligent Data Engineering, Xi’an, China, October 2011 (Oral paper)

5.      TaoYang, Francine Chen, Don Kimber, Jim Vaughan. Robust people detection and tracking in a multi-camera indoor visual surveillance system. IEEE International Conference on Multimedia & Expo 2007(ICME), Beijing, China, 2007, 675~678 [pdf]

6.      Andreas Girgensohn, Don Kimber, Jim Vaughan, Tao Yang, Frank Shipman, Thea Turner, Eleanor Rieffel, Lynn Wilcox, Francine Chen, Tony Dunnigan. DOTS: Support for effective video surveillance. ACM Multimedia 2007(ACM_MM, Full Paper), Augsburg, Germany, September 2007, 423~432 [pdf]

7.      Wenguang Ma, TaoYang, Yanning Zhang, Xiaomin Tong.Unstructured Synthetic Aperture Photograph based Occluded Object Imaging.7th International Conference on Image and Graphics,Qingdao,China,2013

8.      Xiaomin Tong, Yanning Zhang, TaoYang, Wenguang Ma. Automatic Object Tracking in Aerial Videos via Spatial-temporal Feature Clustering.ISCIDE 2013: 78-85

9.      Bingxin Qu, Yanning Zhang, TaoYang: Local-Global Joint Decision Based Clustering for Airport Recognition.IScIDE 2013:94-10

10.  R.Yao, Y.N. Zhang, T.Yang, F.Duan. Detection of small space target based on iterative distance classification and trajectory association. Optics and Precision Engineering.2012,20(1):179-189

11.  Z.Pei, Y.N.Zhang, T.Yang, and X. Chen.Synthetic Aperture Image Quality Assessment Based on Camera Array: Measures and Their Performance.In FSKD '12: Proceedings of the Ninth International Conference on Fuzzy Systems and Knowledge Discovery,Chongqing, China,2012, 1981-1985

12.  X.S. Zheng, Y.N.Zhang, T.Yang, X.Q.Zhang. High-quality synthetic aperture auto-imaging under occlusion. Workshop on Intelligence Science and Intelligent Data Engineering 2012 (Oral paper) [pdf]

13.  X.Q.Zhang, Y.N.Zhang, T.Yang, ZhengxiSong. Calibrate a moving camera on a linear translating stage using virtual plane + parallax. Workshop on Intelligence Science and Intelligent Data Engineering 2012

14.  Z.Pei, Y.N.Zhang, T.Yang, and X. Chen.Synthetic Aperture Image Quality Assessment Based on Camera Array: Measures and Their Performance. In Proceedings of the Ninth International Conference on Fuzzy Systems and Knowledge Discovery, Chongqing, China,2012, 1981-1985

15.  Tao Zhuo, Yanning Zhang, Tao Yang, and Xiaoqiang Zhang.Moving People Detection in Dynamic Scenes by Stereo Vision. 2011 Sino-foreign-interchange Workshop on Intelligence Science and Intelligent Data Engineering, Xi’an, China, October 2011

16.  TaoYang, Yanning Zhang, MengLi, Dapei Shao, Xingong Zhang. A multi-camera network system for markerless 3d human body voxel reconstruction. International conference on image and graphics, Xi’an, China, 2009,706-711 [pdf]

17.  TaoYang, Yanning Zhang. FlyingSword: A Real-time Motion Video Registration, Stabilization, Mosaicing and Moving Object Tracking System. Asian Conference on Computer Vision (ACCV), China, 2009 [pdf]

18.  Xiaomin Tong, TaoYang, Runping Xi, Dapei Shao, Xiuwei Zhang. A Novel Multi-Planar Homography Constraint Algorithm for Robust Multi-People Location with Severe Occlusion. International Conference on Image and Graphics, Xi’an, China, 2009,349-354 [pdf]

19.  Rui Yu, TaoYang, Jiangbin Zheng, Xingong Zhang, Real-Time Camera Pose Estimation Based on Multiple Planar Markers, Fifth International Conference on Image and Graphics(ICIG), Xi’an, China, 2009.

20.  Don Kimber, Anthony Dunnigan, Andreas Girgensohn, Frank Shipman, Thea Turner, TaoYang. Trailblazing:Video playback control by direct object manipulation.IEEE International Conference on Multimedia & Expo 2007(ICME), Beijing, China, 2007, 1015~1018 [pdf]

21.  TaoYang, Jing Li, Quan Pan, Chunhui Zhao, Yiqiang Zhu. Active learning based pedestrian detection in real scenes. 18th International Conference on Pattern Recognition (ICPR), HongKong, China, 2006, 904~907 [pdf]

22.  TaoYang, Stan Z.Li ,Quan Pan, Jing Li, Chunhui Zhao. Reliable and Fast Tracking of Faces under Varying Pose, IEEE FRG, UK, 2006 (Cited by Google Scholar: 24)

23.  TaoYang, Stan Z.Li, Quan Pan, Jing Li. Real-time and accurate segmentation of moving objects in dynamic scene. ACM Multimedia-2nd International Workshop on Video Surveillance and Sensor Networks (VSSN), NewYork, USA, 2004, 136~143 [pdf] (Cited by Google Scholar: 78 )

24.  TaoYang, Quan Pan, Stan.Z.Li, Jing Li. Multiple layer based background maintenance in complex environment. Third International Conference on Image and Graphics (ICIG), Hong Kong, China, 2004, 112~115

25.  TaoYang, Quan Pan , Jing Li, Yongmei Cheng, Chunhui Zhao. Real-time head tracking system with an active camera. Proceedings of IEEE 5th World Congress on Intelligent Control and Automation (WCICA), Hangzhou, China, 2004, 1910~1914

26.  Jing Li, Stan Z. Li, Quan Pan, Tao Yang. Illumination and motion based video enhancement for night surveillance. IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (ICCV?5_VS-PETS), Beijing, China, 2005, 169~175 [pdf]

27.  Jing Li, Quan Pan, TaoYang, Stan Z. Li. Automated feature points management for video mosaic construction. International Conference on Information Technology and Application (ICITA?5), Sydney, Australia, 2005, 760~763 [pdf]

28.  Jing Li, Quan Pan, TaoYang, Yongmei Cheng. Color based grayscale-fused Image enhancement algorithm for video surveillance. Third International Conference on Image and Graphics (ICIG), HongKong, China, 2004, 47~50 [pdf]

29.  DianWang,Yongmei Cheng,TaoYang,QuanPan,Chunhui Zhao.Moving cast shadow suppression from a Gaussian mixture shadow model. Journal of Computer Applications,2006

30.  TaoWang,Yongmei Cheng,TaoYang,QuanPan,Chunhui Zhao.A Human Face Best Viewpoint Selection Algorithm in Multiple Cameras Environment,Computer Engineering and Applications,2005


Presentations and Slides

Professional Activities

Serving as a Reviewer for:


My Students and Thesis


Markerless Motion Capture

Co-supervise with Prof.Y.N.Zhang

Now he is a researcher at Tencent, Beijing, China


Multiple Camera Moving Object Tracking

Co-supervise with Prof.Y.N.Zhang

Now he is a Ph.D Candidate of Vision Laboratory, Queen Mary University,London

Wenguang Ma

Moving Camera based Synthetic Aperture Imaging Through Occlusion

Fundation for outstanding masters of NWPU 2014 ( 30 students of the whole university)

Sibing Wang

2013-present Compact Array High Resolution Object Imaging

2012-2013 RGBD sensor based Real Time SLAM and Synthetic Apertutre Imaging Links!

Outstanding Dissertation Award of NWPU 2013

Bowei Yao

Dim object detection and tracking in wide area aerial image sequence

Zhannan He

Light field camera imaging through occlusion

Guangpo Li

Panoramic Imaging based on dense camera array

Zhuoyue Zhang

UAV vision SLAM algorithm

Xiaofei Liu

Compressive Tracking and Tracking and Detection

Xiuchuan Xie

3D Reconstruction

Qiang Ren

Multi-Object Detection Based on Binocular Stereo Vision

Wencheng Duan

Ground target tracking and data association

Zhi Li

UAV real-time vision SLAM

Chao Wang

Camera Array based UAV Location

Miao Wang

Visual Object Tracking

Peiqi Li

UAV vision navigation

Dongdong Li

3D real - time dense reconstruction

Jie Fan

Graduate Design 2013

RGB-D camera based 3D reconstruction and visual SLAM Links!

Outstanding Dissertation Award of NWPU 2013

Now she is studying at France

Yanwu Han

Graduate Design 2013

Camera array synthetic aperture imaging based occluded people tracking

Wen Zhao

Graduate Design 2012

Research and develop of panoramic camera with pyramid mirror reflection Links!

Now he is a Master student at Iowa State University, USA

ZhengXi Song

Graduate Design 2012

Camera array stereo focusing and see object through occlusion

Now she is a PhD at our digital video processing group

BingXin Qu

Graduate Design 2012

Online detection and learning based visual object tracking

Now she is working at BaiDu, Beijing,China

Yang Zhao

Graduate Design 2012

Kinect based real time multiple people location and counting