Real-time food intake classification and energy expenditure estimation on a mobile device

Daniele Ravi, Benny Lo, Guang Zhong Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Assessment of food intake has a wide range of applications in public health and life-style related chronic disease management. In this paper, we propose a real-time food recognition platform combined with daily activity and energy expenditure estimation. In the proposed method, food recognition is based on hierarchical classification using multiple visual cues, supported by efficient software implementation suitable for realtime mobile device execution. A Fischer Vector representation together with a set of linear classifiers are used to categorize food intake. Daily energy expenditure estimation is achieved by using the built-in inertial motion sensors of the mobile device. The performance of the vision-based food recognition algorithm is compared to the current state-of-the-art, showing improved accuracy and high computational efficiency suitable for realtime feedback. Detailed user studies have also been performed to demonstrate the practical value of the software environment.

Original languageEnglish
Title of host publication2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)9781467372015
DOIs
Publication statusPublished - 15 Oct 2015
Externally publishedYes
Event12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015 - Cambridge, United States
Duration: 9 Jun 201512 Jun 2015

Publication series

Name2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015

Conference

Conference12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015
Country/TerritoryUnited States
CityCambridge
Period9/06/1512/06/15

Fingerprint

Dive into the research topics of 'Real-time food intake classification and energy expenditure estimation on a mobile device'. Together they form a unique fingerprint.

Cite this