|
The papers in this volume were part of the technical conference cited on the cover and title page. Papers were selected and subject to review by the editors and conference program committee. Some conference presentations may not be available for publication. Additional papers and presentation recordings may be available online in the SPIE Digital Library at SPIEDigitalLibrary.org. The papers reflect the work and thoughts of the authors and are published herein as submitted. The publisher is not responsible for the validity of the information or for any outcomes resulting from reliance thereon. Please use the following format to cite material from these proceedings: Author(s), “Title of Paper,” in Signal Processing, Sensor/Information Fusion, and Target Recognition XXVII, edited by Ivan Kadar, Proceedings of SPIE Vol. 10646 (SPIE, Bellingham, WA, 2018) Seven-digit Article CID Number. ISSN: 0277-786X ISSN: 1996-756X (electronic) ISBN: 9781510618039 ISBN: 9781510618046 (electronic) Published by SPIE P.O. Box 10, Bellingham, Washington 98227-0010 USA Telephone +1 360 676 3290 (Pacific Time) · Fax +1 360 647 1445 Copyright © 2018, Society of Photo-Optical Instrumentation Engineers. Copying of material in this book for internal or personal use, or for the internal or personal use of specific clients, beyond the fair use provisions granted by the U.S. Copyright Law is authorized by SPIE subject to payment of copying fees. The Transactional Reporting Service base fee for this volume is $18.00 per article (or portion thereof), which should be paid directly to the Copyright Clearance Center (CCC), 222 Rosewood Drive, Danvers, MA 01923. Payment may also be made electronically through CCC Online at copyright.com. Other copying for republication, resale, advertising or promotion, or any form of systematic or multiple reproduction of any material in this book is prohibited except with permission in writing from the publisher. The CCC fee code is 0277-786X/18/$18.00. Printed in the United States of America. Publication of record for individual papers is online in the SPIE Digital Library. Paper Numbering:Proceedings of SPIE follow an e-First publication model. A unique citation identifier (CID) number is assigned to each article at the time of publication. Utilization of CIDs allows articles to be fully citable as soon as they are published online, and connects the same identifier to all online and print versions of the publication. SPIE uses a seven-digit CID article numbering system structured as follows:
AuthorsNumbers in the index correspond to the last two digits of the seven-digit citation identifier (CID) article numbering system used in Proceedings of SPIE. The first five digits reflect the volume number. Base 36 numbering is employed for the last two digits and indicates the order of articles within the volume. Numbers start with 00, 01, 02, 03, 04, 05, 06, 07, 08, 09, 0A, 0B…0Z, followed by 10-1Z, 20-2Z, etc. Altman, Emilie, 0K Anderson, Evan, 1K Angotta, Bill, 1A Astyakopoulos, Alkis, 0U Bacher, E., 0S Bailey, Colleen P., 1R Balaji, Bhashyam, 0K Balasingam, Balakumar, 07 Bar-Shalom, Yaakov, 05, 07, 09, 0B, 1S Bayer, Michael A., 12 Belfadel, Djedjiga, 05, 1S Ben-Dov, R., 09 Borel-Donohue, Christoph, 14 Bothos, John, 0V Carniglia, Peter, 0K Chance, Zachary, 1K Chandran, Krishnan, 13 Chen, Lingji, 02, 03, 04 Colonna-Romano, John, 0O Copsey, Keith, 0P Couwenhoven, Doug W., 12 Cox, Kevin, 0Z da Silva, Felipe B., 11 DeMars, Kyle J., 06 Diltz, Robert, 1A Dou, Wenbo, 0B Dunham, Joel, 1M Emge, Darren K., 1H English, Woody, 1A Eum, Sungmin, 16 Fowler, Stuart, 1A Gatsak, Tatiana, 0K Giovanneschi, F., 0S Gómez Miguel, Beatriz, 0U Grewe, Lynne, 13 Hammer, M., 0S Hengy, S., 0S Hommes, A., 0S Hurley, Jeffery D., 1M Johannes, W., 0S Johnson, Clint, 1M Jones, Brandon A., 0F Kadar, Ivan, 0M Kashyap, Archana, 13 Kay, Steven M., 0N, 1F Kong, Yingying, 0W Kontoes, Haris, 0U Kowalski, Michael, 1S Kwon, Heesung, 14, 16 Kyriazanos, Dimitris M., 0U, 0V Langford, Darrell, 1A Laurenzis, M., 0S Lee, Hyungtae, 14, 16 LeGrand, Keith A., 06 Leirens, Sylvain, 15 Le Moigne, Jaqueline, 10 Leung, Henry, 0L, 0W Levchuk, Georgiy, 0O Li, Boyuan, 0L Lu, Qin, 07, 0B Lykousis, Vasilios, 0U Mahler, Ronald, 0C, 0D, 0E Maraviglia, Carlos, 0Z Mareboyana, Manohar, 10 Markellou, Marina, 0U Martins, Ana, 0U McArdle, Sean M., 0F Milgrom, B., 09 Miosso, Cristiano J., 11 Mohler, David, 0A Mowakeaa, Rami, 1H Mulgrew, Bernard, 0P Narayanan, Priya, 14 Nehmetallah, George, 1P Oxley, Mark E., 0G, 0H Pados, Dimitris A., 1R Page, Scott, 0P Park, Sungjoo, 0Z Pattipati, Krishna, 0B Pereira da Silva, Alex, 15 Poyet, J.-M., 0S Prasad, Lakshman, 0Q Rao, Raghuveer, 14 Rassy, O., 0S Ravago, Nicholas, 0F Relyea, Stephen, 1K Rinehart, Stephen A., 1P Rizogiannis, Constantinos, 0U, 0V Robinson, Brian, 1A Rumbley, Sarah E., 02 Schertzer, S., 0S Schubert Kabban, Christine M., 0G, 0H Seneviratne, Chatura, 0L Shah, Akhil K., 0F Shahshahani, Allen, 13 Shahshahani, Jake, 13 Shapero, Samuel A., 1L Simmons, Jimmy, 1M Taylor, Clark N., 0A Thanos, Konstantinos Georgios, 0V Thomas, Paul, 0P Thomopoulos, Stelios C. A., 0U, 0V Trypitsidis, Anestis, 0U Tsouni, Alexia, 0U Tucker, Andrew W., 1F Üney, Murat, 0P Varkitzi, Ioanna, 0U Vieira, Fábio AL., 0U Vila Hernandez de Lorenzo, Jordi, 1P Visina, Radu, 0B von Borries, Ricardo, 11 Walters, Josh, 1A Walvoord, Derek J., 12 Willett, Peter, 07, 09, 0B, 1S Yang, Kaipei, 09 Yoedt, Cedric, 0Z Zalonis, Andreas, 0V Zhang, Shu, 0W Zhou, Xin, 0N Conference CommitteeSymposium Chair Symposium Co-chair Conference Chairs Conference Co-chairs
Conference Program Committee
Session Chairs
Introduction to the Invited Panel DiscussionDeep Learning in AI and Information Fusion In the early days of artificial intelligence (AI) starting, say in the 1970s and 1980s, the predominant reasoning methods were logical and symbolic, using, e.g., Lisp/Prolog languages. Later in the 1980s, AI tools were used such as Knowledge Environment Engineering (KEE) and Automated Reasoning Tool (ART) expert systems, and early heuristic reasoning methods. Also, the concept and mathematical representation of “context” logic was defined. The concept and apps of both “knowledge based” and “context” are currently used in several apps in information fusion (IF) along with several methods to apply and learn contextual information. In the early 1980’s, AI was viewed as the solution to information fusion problems. In fact, many contributors to the first distributed sensor networks program were AI researchers. However, inadequate computing and AI approaches such as expert systems and heuristic uncertainty reasoning could not address the challenges of information fusion. Thus, important advances in information fusion, and in particular, multi-target tracking, were made with little contribution from AI. During the long AI winter, researchers addressed the deficiencies of early AI, developing rigorous representation and reasoning techniques for uncertainty, and machine learning approaches. Recently, data science was established as a popular area to exploit the large volumes of data (a.k.a. Big Data) collected by physical sensors and online activities using machine learning and other analytic tools. Artificial intelligence and data science pose both challenges and opportunities to IF. They are challenges because they appear to address the same problems as information fusion, but with more powerful techniques, thus siphoning away both research funding and research talent. However, these challenges can also be opportunities because AI and data science provide new research directions for information fusion. Examples include: IF with big data, hard and soft data fusion, learning about context, graph techniques for tracking and fusion, dynamic network analysis, apps to cyber and imagery processing. The objective of this panel was to bring to the attention of the fusion community the importance of the application of deep learning in AI and IF, highlighting issues, illustrating approaches and addressing challenges. A number of invited experts discussed challenges in processing and research, and addressed these challenges with IF. The panelists illustrated parts of the above-mentioned areas over different applications and association with IF. The panel highlighted impending issues and challenges using conceptual and real-world related examples associated with the applications of above. Chee-Yee Chong Ivan Kadar |