Multispectral Image Fusion and Night Vision Colorization

Level: Introductory Length: 4 hours Format: Online Intended Audience: Scientists, engineers, practitioners, students, and researchers who wish to learn more about how to combine multiband images to enhance computer vision and human vision for applications such as face recognition and scene understanding. Undergraduate training in engineering or science is assumed. Description: This course presents methods and applications of multispectral image fusion and night vision colorization organized into three areas: (1) image fusion methods, (2) evaluation, and (3) applications. Two primary multiscale fusion approaches, image pyramid and wavelet transform, will be emphasized. Image fusion comparisons include data, metrics, and analytics. Fusion applications presented include off-focal images, medical images, night vision, and face recognition. Examples will be discussed of night-vision images rendered using channel-based color fusion, lookup-table color mapping, and segment-based method colorization. These colorized images resemble natural color scenes and thus can improve the observer’s performance. After taking this course you will know how to combine multiband images and how to render the result with colors in order to enhance computer vision and human vision especially in low-light conditions. In addition to the course notes, attendees will receive a set of published papers, the data sets used in the analysis, and MATLAB code of methods and metrics for evaluation. A FTP website is established for course resource access. Learning Outcomes: This course will enable you to: - review the applications and techniques of image fusion and night vision enhancement - categorize multiscale image fusion methods: image pyramid vs. wavelet transform - apply quantitative vs. qualitative evaluation - investigate advanced fusion applications: target recognition, color fusion and face recognition - obtain an overview of colorization methods: color mapping, segment-based, and channel-based - evaluate colorized images: qualitative vs. quantitative, and correspondence with the NIIRS (National Imagery Interpretability Rating Scale) ratings - explore information fusion applications to a multispectral stereo face recognition systems at four levels: image, feature, score, and decision; to qualitatively evaluate performance improvement - recognize and discuss challenges for future development and applications Instructor(s): Yufeng Zheng is an associate professor of data science in the University of Mississippi Medical Center. He received the Ph.D. in optical engineering/image processing in 1997 from Tianjin University, China. He was a postdoctoral research associate at the University of Louisville, Kentucky, from 2001-2005. Dr. Zheng holds a utility patent in face recognition. He is the author or coauthor of three books, six book chapters, 24 articles in peer-reviewed journals and 54 papers in conference proceedings. He is the principal investigator of many funded projects such as cybersecurity enhancement with keyboard dynamics, canopy coverage estimation with neural network, multisensory image fusion and colorization; thermal face recognition; and multispectral face recognition. Dr. Zheng is a Cisco Certified Network Professional (CCNP), a senior member of IEEE & Signal Processing Society, and a senior member of SPIE. His research interests include image processing and pattern recognition; neural network and artificial intelligence; information fusion, biometrics (facial recognition); machine learning and computer vision; and computer-aided diagnosis. Erik P. Blasch received his B.S. in mechanical engineering from the Massachusetts Institute of Technology in 1992 and M.S. degrees in mechanical engineering, health science, and industrial engineering (human factors) from Georgia Tech. He completed an M.B.A., M.S.E.E., M.S. econ, M.S./Ph.D. psychology (ABD), and a Ph.D. in electrical engineering from Wright State University and is a graduate of Air War College. From 2000-2010, Dr. Blasch was the information fusion evaluation tech lead for the Air Force Research Laboratory (AFRL) Sensors Directorate—COMprehensive Performance Assessment of Sensor Exploitation (COMPASE) Center, and adjunct professor with Wright State University. From 2010-2012, Dr. Blasch was an exchange scientist to Defence R&D Canada at Valcartier, Quebec in the Future Command and Control (C2) Concepts group. He is currently with the AFRL Information Directorate supporting information fusion developments. He received the 2009 IEEE Russ Bioengineering, , 2012 IEEE AESS Magazine Mimno, and 2014 Military Sensing Symposium Mignogna Data Fusion awards. He is a past President of the International Society of Information Fusion (ISIF), a member of the IEEE Aerospace and Electronics Systems Society (AESS) Board of Governors, and a SPIE Fellow. His research interests include target tracking, information/sensor/image fusion, pattern recognition, and biologically-inspired applications. SPIE online courses are on-demand and self-paced, with access for one year. For more information visit: spie.org/education/online-courses