Skip to content

CaloriNet: From silhouettes to calorie estimation in private environments

Research output: Contribution to conferencePaper

Original languageEnglish
Number of pages14
DateAccepted/In press - 6 Jul 2018
DatePublished (current) - 20 Jul 2018
Event29th British Machine Vision Conference - Northumbria University, Newcastle upon Tyne, United Kingdom
Duration: 3 Sep 20186 Sep 2018


Conference29th British Machine Vision Conference
CountryUnited Kingdom
CityNewcastle upon Tyne
Internet address


We propose a novel deep fusion architecture, CaloriNet, for the online estimation of energy expenditure for free living monitoring in private environments, where RGB data is discarded and replaced by silhouettes. Our fused convolutional neural network architecture is trainable end-to-end, to estimate calorie expenditure, using temporal foreground silhouettes alongside accelerometer data. The network is trained and cross-validated on a publicly available dataset, SPHERE_RGBD + Inertial_calorie. Results show state-of-the-art minimum error on the estimation of energy expenditure (calories per minute), outperforming alternative, standard and single-modal techniques.

    Structured keywords

  • Digital Health


29th British Machine Vision Conference

Duration3 Sep 20186 Sep 2018
Location of eventNorthumbria University
CityNewcastle upon Tyne
CountryUnited Kingdom
Web address (URL)
Degree of recognitionInternational event

Event: Conference

Download statistics

No data available



  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via BMVC at . Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 2.34 MB, PDF document


View research connections

Related faculties, schools or groups