Combining embedded accelerometers with computer vision for recognizing food preparation activities

S. Stein, S.J. McKenna

    Research output: Chapter in Book/Report/Conference proceedingChapter

    315 Citations (Scopus)

    Abstract

    This paper introduces a publicly available dataset of complex activities that involve manipulative gestures. The dataset captures people preparing mixed salads and contains more than 4.5 hours of accelerometer and RGB-D video data, detailed annotations, and an evaluation protocol for comparison of activity recognition algorithms. Providing baseline results for one possible activity recognition task, this paper further investigates modality fusion methods at different stages of the recognition pipeline: (i) prior to feature extraction through accelerometer localization, (ii) at feature level via feature concatenation, and (iii) at classification level by combining classifier outputs. Empirical evaluation shows that fusing in- formation captured by these sensor types can considerably improve recognition performance.
    Original languageEnglish
    Title of host publicationUbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing
    Pages729-738
    Number of pages10
    DOIs
    Publication statusPublished - 1 Jan 2013

    Fingerprint

    Dive into the research topics of 'Combining embedded accelerometers with computer vision for recognizing food preparation activities'. Together they form a unique fingerprint.

    Cite this