Portrait_201603s 

Dr. Xiaowei SHAO   肖偉

 

 

Project Associate Professor

Shibasaki Lab

Earth Observation Data Integration and Fusion Research Initiative

The University of Tokyo

 

TEL:  +81-4-7136-4307

E-mail:

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Xiaowei Shao received the B.E. and Ph.D. degrees in electronic engineering and information science from the University of Science and Technology of China, Hefei, China, in 1999 and 2006, respectively. From 2004 to 2012, he was with the Center for Spatial Information Science, the University of Tokyo, Japan, where he had been a Project Assistant Professor since 2008. In 2012, he joined the Earth Observation Data Integration and Fusion Research Initiative, the University of Tokyo, Japan as a Project Associate Professor. His research interests include range data processing, pattern recognition and machine intelligence, object detection and tracking, and spatial data assimilation.

 

 

 

Research Topics

 

1. Crowd Surveillance via Range Sensors

 

a01s

Comparing with traditional image and video based crowd surveillance, range sensors bring new possibilities of monitoring both global people flow and individual movement in an accurate and efficient way. Our tracking algorithm is capable of tracking more than 170 pedestrians simultaneously (processed in real-time when the number of people is less than 50) and achieves satisfactory tracking accuracy in a series of field tests.

 

 

2. Spatial Data Assimilation of People Flow

 

a03s

Sensing people flow via various sensors attracts increasing attention from worldwide, which is critical for many potential applications. However, considering the cost it is difficult to collect sufficient information in practice. In many cases, only partial information in adjacent areas, or data of different kinds are available. Our purpose is to estimate and assimilate people flow from such incomplete data.

 

 

3. Urban/Village Mapping

 

a02s

Identifying residential areas in developing countries is an important topic which helps improving the management and quality of the residents' life. We have been assisting the remote sensing group of our laboratory in recognizing urban/village areas, by carefully combining novel machine learning techniques with multi-source satellite images.

 

 

 

 

 

Publications (selected five)  Full List

 

Ø  X. Shao, Y. Shi, H. Zhao, X. Li, R. Shibasaki, “Efficient Closed-Loop Multiple-View Registration”,  IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 15, no. 6, pp. 2524-2538, 2014.

Ø  Z. Guo, X. Shao*, Y. Xu, H. Miyazaki, W. Ohira, R. Shibasaki, "Identification of Village Building via Google Earth Images and Supervised Machine Learning Methods", Remote Sensing, vol. 8, no. 4, 271, 2016.

Ø  Y. Duan, X.Shao*, Y. Shi, H. Miyazaki, K. Iwao, R. Shibasaki, "Unsupervised Global Urban Area Mapping via Automatic Labeling from ASTER and PALSAR Satellite Images", Remote Sensing, vol. 7, no. 2, pp. 2171-2192, 2015.

Ø  X. Shao, H. Zhao, K. Katabira, R. Shibasaki and Y. Nakagawa, "Tracking a Variable Number of Pedestrians in Crowded Scenes by Using Laser Range Scanners", Proc. IEEE International Conference on Systems, Man, and Cybernetics, pp. 1545-1551, 2008. Finalist of Franklin V. Taylor Memorial award (the best paper award)

Ø  X. Song, X. Shao, H. Zhao, J. Cui, R. Shibasaki and H. Zha, "An online approach: learning-semantic-scene-by-tracking and tracking-by-learning-semantic-scene", Proc.  IEEE International Conference on Computer Vision and Pattern Recognition, pp.1652 - 1659, 2010.

 

 

Patents and Inventions (Japanese)

 

1)特許出願 「通行人行動解析装置及び通行人行動解析方法並びにそのプログラム」, 【公開番号】特開2009-110185

 

2)特許出願 「シミュレータ装置、係数決定装置、及びシミュレータシステム」 , 【公開番号】特開2013-15965

 

Inventions managed by Todai TLO  (Technology Licensing Organization, the University of Tokyo)

 

1)マルチレーザスキャナによる移動体の抽出追跡システム, 知的財産部管理番号50B115001-1

 

2)レーザスキャナによる歩行者流動計測システム, 知的財産部管理番号C50138002

 

3Kinectセンサによる歩行者流動計測システム, 知的財産部管理番号C50138001

 

 

 

Funded Projects

 

We have conducted about 20 cooperative research projects with Hitachi Ltd., East Japan Railway Company, and other companies since 2004, focusing on developing and applying latest range sensing techniques for spatial awareness of people. We have been exploring various possibilities of using range sensors in different ways and situations for crowd surveillance——detection, localization, tracking, et al.

(Based on the requirements of cooperative companies, details of the project information cannot be displayed here)

 

 

Team Members

 

 

Yongwei Xu

Project Researcher

Guo

Zhiling Guo

M1

 

 

 

Resources

 

The resource of open range sensing data set for crowd surveillance is quite few, and we plan to share our 2D/3D range sensing data of real field experiments for the research society. The experiment has been conducted inside the Kashiwa campus of the University of Tokyo and the data are under preparation now. 

 

 

 

 

Last updated: 2016-06-29