From augmented personal telepresence to mobile dietary assessment: an image processing perspective"
|Event Date:||February 11, 2014|
|Speaker:||Dr Fengqing Maggie Zhu|
|Speaker Affiliation:||Huawei Technologies USA
Santa Clara, CA
|Sponsor:||Communications, Networking, Signal & Image Processing|
|Contact Name:||Professor Jan Allebach
|Open To:||ACCEPTABLE FOR ECE 694A
Advancement in image/video processing enables many novel applications that improve our daily life, such as immersive and interactive teleconferencing and smart mobile health monitoring. Immersion is a highly desirable characteristic in audio-visual conferencing, with potential to revolutionize long-distance healthcare and education. However, such capability is currently associated with high-cost and limited accessibility. In the first part of the talk, I will present a coherent suite of technology, including video analysis and processing as well as human computer interaction that may eventually allow one to experience telepresence using smartphones anywhere with access to the Internet.
As an early exploration of mobile health monitoring, I will present a method for dietary assessment in the second part of the talk. Measuring accurate dietary intake is an open research problem in the nutrition and health fields. Our method is capable of automatically identifying and locating food in a variety of images captured during controlled and natural eating events. Two concepts are combined to achieve this: a set of segmented objects can be partitioned into perceptually similar object classes based on global and local features; and perceptually similar object classes can be used to assess the accuracy of image segmentation. Improved accuracy of segmenting food images with classifier feedback is achieved. Finally, I will discuss future developments targeting remote healthcare and long-distance learning.
Fengqing Maggie Zhu received the B.S., M.S. and Ph.D. degrees in Electrical and Computer Engineering in 2004, 2006 and 2011, respectively, all from Purdue University. Her graduate study was partially supported by a Charles C. Chappelle Graduate Fellowship and a Motorola Foundation Fellowship. She was a Student Intern at the Sharp Laboratories of America, Camas, WA, in the summer of 2007 and attended the McKinsey Insight Engineering & Science Program in the summer of 2008, as well as the NIH Mobile Health Summer Training Institute in 2011. She is currently a Staff Researcher in the media communication & interaction group at Huawei Technologies (USA), Santa Clara, CA, where she received a Huawei Certification of Recognition for Core Technology Contribution in 2012. Dr. Zhu's research interests include video compression, image/video processing and analysis, computer vision and computational photography.