|
|
Jump to:CV | Education | Research Experiences | News | Research interests | Teaching | International Competition | Research projects | Publications | Demos |Presentations and Slides | Professional Activities | My Students | Reading Meeting | Links
| CV |
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 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.
Since April 2010, Dr. Yang has been an Associate 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. 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.
He has published over 40
papers and applied 4 US patents and 4 Chinese patents in the fields of computer vision and pattern
recognition. As the Principal Investigator, he hosted research fundings include two National Science
Foundations of China (NSFC), Special Foundation for Excellent Chinese Post-Doctoral, NPU Foundation
for Fundamental Research etc. As the Technical Leader, he lead four 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. He is a member of IEEE, ACM, and China Computer Federation (CCF).
| Education |
| Research Experiences |
| News |
| Research interests |
| Teaching |
| International Competition |
Research projects |
| Moving video synthetic aperture imaging (on going project) | |
Sponsored by the National Nature Science Fundation of China (NSFC), I am leading a project of moving video syntehtic apeture imaging, and we have already setup several experiment platforms.
|
| 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 |
||
We have designed and developed a real-time panoramic camera, which consists of six mirror and Pointgrey Flea3 cameras. |
||
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 |
||
We have developed an approach to accelerate 3D reconstruction by introducing a mechanism of vertices sharing during the process of traditional voxel splitting. Our system can run at 10fps with 8 cameras on a PC with configuration: i7-950 CPU, 4G RAM. |
||
| Demos |
| Publications |
2013
2012
2011
2010
2009
2008
2007
Before 2006
| Presentations and Slides |
| Professional Activities |
Serving as a Reviewer for:
Others:
| My Students |
 |
Wenguang Ma |
2012-present Moving Camera based Synthetic Aperture Imaging Through Occlusion |
 |
Sibing Wang | 2013-present Unstructured Light Field based and vSLAM |
 |
2010-2012 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 |
|
 |
MengLi |
2009-2011 Markerless Motion Capture Co-supervise with Prof.Y.N.Zhang Now he is a researcher at Tencent, Beijing, China |
 |
Jie Fan | Graduate Design 2013 Visual SLAM with camera on moving platform |
 |
Yanwu Han | Graduate Design 2013 Camera array synthetic aperture imaging based occluded people tracking in crowd |
 |
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 Master student at our digital video processing group |
 |
BingXin Qu |
Graduate Design 2012 Online detection and learning based visual object tracking Now she is a Master student at our digital video processing group |
 |
Yang Zhao |
Graduate Design 2012 Kinect based real time multiple people location and counting |
| Links |
