With heightened security concerns across the globe and the increasing need to monitor, preserve and protect infrastructure and public spaces to ensure proper operation, quality assurance and safety are paramount. Recent sensor technologies from IoT to video are typically leveraged, resulting in an explosion of real-time content. Accordingly, there is a need the data to be monitored effectively and efficiently. However, leveraging human operators to constantly monitor all the data and video streams is not scalable or cost effective. Humans can become fatigued, subjective, and even disinterested and it is difficult to maintain high levels of vigilance when capturing, searching and recognizing events that occur infrequently or in isolation.

Overcoming these limitations requires a Live Video Computing (LVC) framework for managing and fusing live motion imagery and data via user-defined queries. LVC enables rapid development of video surveillance software much like traditional database applications of today. Such developed video stream processing applications and user-defined queries are able to "reuse" advanced image processing techniques and templates that have been developed. This results in lower software development and maintenance costs. A user requesting information provides refinement of the analysis via queries which are typically semantic in nature the enables multimedia information fusion. A query that is continuously refined reduces uncertainty and can update ontologies as part of the source, evaluation, and information quality. For example, a user receiving a response to a query can determine if the response meets the quality, evaluation, and source criteria. Demonstrated examples are presented for surveillance, networks, and emergency preparation.

Biography

Dr. Alex J. Aved received the BA degree in Computer Science and Mathematics in 1999 from Anderson University in Anderson, Indiana, an MS in Computer Science from Ball State University and PhD in Computer Science in 2013 (focus area: real-time multimedia databases) from the University of Central Florida. He is currently a technical advisor at the Air Force Research Laboratory Information Directorate in Rome, NY. Alex’s research interests include multimedia databases, stream processing (via CPU, GPU or coprocessor) and dynamically executing models with feedback loops incorporating measurement and error data to improve the accuracy of the model.

Select Publications:

Journal Papers:

1. Multi-View Boosting with Information Propagation for Classification,  J. Peng, A. Aved, G. Seetharaman, and K. Palaniappan, IEEE Transactions on Neural Networks and Learning Systems 2016.
2. Regularized Difference Criterion for Computing Discriminants for Dimensionality Reduction, A. Aved, J. Peng, and E. Blasch, IEEE Transactions on Aerospace and Electronic Systems 2017.
3. Approximate Regularized Least Squares and Parzen Windows, P. Zhang, J. Peng, and A. Aved, Machine Learning, 2017.

Book Chapter:

1. Aved, Alex J., and Erik Blasch. "Context Understanding from Query-Based Streaming Video." Context-Enhanced Information Fusion. Springer International Publishing, 2016. 507-537.