The 2015 Smart World Congress Keynotes

Abstract:
With the rapid growth of video data from various sources, there arise requirements for both online real-time analysis and offline batch processing of large-scale video data. Existing video processing systems fall short in addressing many challenges in large-scale video processing, for example performance, data storage, and fault-tolerance. We proposes a general cloud-based architecture and platform that can provide a robust solution to intelligent analysis and storage for video data based on deep learning. We have implemented the BiF architecture using both Hadoop platform and Storm platform. The proposed architecture can handle continual surveillance video data effectively, where real-time analysis, batch processing, distributed storage and cloud services are seamlessly integrated to meet the requirements of video data processing and management. The evaluations show that the proposed approach is efficient in terms of performance, storage, and fault-tolerance.

 

Biography:
Weishan Zhang is a professor, deputy head for research of Department of Software Engineering, China University of Petroleum. He was a Research Associate Professor/Senior Researcher at Computer Science Department, University of Aarhus (til Dec. 2010). He visited Department of Systems and Computer Engineering, Carleton University, Canada (Jan. 2006 - Jan. 2007). He was an Associate Professor at School of Software Engineering, Tongji University, Shanghai, China (Aug. 2003- June 2007). He was a NSTB post-doctoral research fellow at Department of Computer Science, National University of Singapore (Sept. 2001 to Aug. 2003). My current H-index is 13, I10-index is 18, and the number of total citations is over 500 in Jan 2015.