Monday, September 18, 2017

Acoustic Events Semantic Detection, Classification, and Annotation for Persistent Surveillance Applications


Acoustic Events Semantic Detection, Classification, and Annotation for Persistent Surveillance Applications

 Abstract:

Understanding of group activity based on analysis of spatiotemporally correlated acoustic sound events has received a minimum attention in the literature and hence is not well understood. Identification of group sub-activities such as: Human-Vehicle Interactions (HVI), Human-Object Interactions (HOI), and Human-Human Interactions (HHI) can significantly improve Situational Awareness (SA) in Persistent Surveillance Systems (PSS). 

In this paper, salient sound events associated with group activities are preliminary identified and applied for training a Gaussian Mixture Model (GMM) whose features are employed as feature vectors for training of algorithms for acoustic sound recognition. In this paper, discrimination of salient sounds associated with the HVI, HHI, and HOI events is achieved via a Correlation Based Template Matching (CMTM) classifier. To interlinked salient events representing an ontology-based hypothesis, a Hidden Markov Model (HMM) is employed to recognize spatiotemporally correlated events. Once such a connection is established, then, the system generates an annotation of each perceived sound event. This paper discusses the technical aspects of this approach and presents the experimental results for several outdoor group activities monitored by an array of acoustic sensors.

 Author Bio:

 Dr. Amjad Alkilani is a program chair for the Forbes School of Business & Technology™ at Ashford University. He earned his Ph.D. in Computer & Information Systems Engineering from Tennessee State University; M.S. in Software Engineering from California State University-Fullerton, and B.S. in Computer Science from Mutah University. Before he joined Ashford University he worked as an assistant professor with University of Central Missouri, and before that he was a teaching assistant at Tennessee State University. In addition to his teaching experience he held several positions with different software companies and government agencies: Sr. Software Engineer with State of Tennessee, PM & Sr. Technical Trainer with CBM Integrated Software – Irvine CA, Software Developer with Los Angeles County, and Software Analyst/Developer with A-Z Group Inc. in Irvine CA.

Dr. Alkilani is a recognized expert in enterprise software development related subjects, and his research focus is on solving real-life problems through intelligent systems methodologies.

 Link to Research:

http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1884359

 Reference:

 Alkilani, A., and Shirkhodaie, A., “Acoustic Events Semantic Detection, Classification, and Annotation for Persistent Surveillance Applications”, SPIE Defense, Security and Sensing Conference, Baltimore, Maryland, April 2014.

 Linked-In Address:

https://www.linkedin.com/in/amjad-alkilani-phd-17b8a3119/