A case study for human gesture recognition from poorly annotated data

Ciliberto, Mathias, Roggen, Daniel, Wang, Lin and Zillmer, Ruediger (2018) A case study for human gesture recognition from poorly annotated data. UbiComp '18, Singapore, 9th - 11th October, 2018. Published in: UbiComp '18 Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. 1434-1443. Association for Computing Machinery, New York. ISBN 9781450359665

[img] PDF - Accepted Version
Download (469kB)
[img] PDF - Published Version
Restricted to SRO admin only

Download (550kB)

Abstract

In this paper we present a case study on drinking gesture recognition from a dataset annotated by Experience Sampling (ES). The dataset contains 8825 "sensor events" and users reported 1808 "drink events" through experience sampling. We first show that the annotations obtained through ES do not reflect accurately true drinking events. We present then how we maximise the value of this dataset through two approaches aiming at improving the quality of the annotations post-hoc. First, we use template-matching (Warping Longest Common Subsequence) to spot a subset of events which are highly likely to be drinking gestures. We then propose an unsupervised approach which can perform drinking gesture recognition by combining K-Means clustering with WLCSS. Experimental results verify the effectiveness of the proposed method.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Research Centres and Groups: Sensor Technology Research Centre
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
T Technology
Related URLs:
Depositing User: Daniel Roggen
Date Deposited: 24 Jun 2019 15:11
Last Modified: 25 Jun 2019 15:01
URI: http://sro.sussex.ac.uk/id/eprint/84480

View download statistics for this item

📧 Request an update