Abstract
This paper systematically explores the capabilities of different forms of Dynamic Time Warping (DTW) algorithms and their parameter configurations in recognising whole-of-body gestures. The standard DTW (SDTW) (Sakoe and Chiba 1978), globally feature weighted DTW (Reyes et al. 2011) and locally feature weighted DTW (Arici et al. 2013) algorithms are particularly considered, while an enhanced version of the globally feature weighted DTW (EDTW) algorithm is presented. A wide range of configurable parameters: distance measures (Euclidean and Mahalanobis), combination of features (Cartesian velocity, angular velocity and acceleration), combinations of skeletal elements, reference signal count and k-nearest neighbour count are tested in order to understand the impact on final recognition accuracies. The study is conducted by collecting gesturing data from 10 participants for 9 different whole-of-body gesture commands. The results suggest that the proposed enhanced version of the globally feature weighted DTW algorithm performs significantly better than the other DTW algorithms. Given sufficient training data this study suggests that the Mahalanobis distance has the capability to better differentiate certain gestures compared to the Euclidean distance. Out of the features, Cartesian velocity combined with angular velocity provides the highest gesture discriminant capability while acceleration provides the lowest. When highly informative and stable skeletal elements are selected, the overall performance gain obtained by adding extra skeletal data is marginal. Also the recognition accuracies are sensitive to the reference signal count and the KNN percentage. Additionally, the presented results summarise the unique capabilities of certain configurations over others, highlighting the importance of selecting the appropriate DTW algorithm and its configurations to achieve optimal gesture recognition performances.
Highlights
Human-Computer Interaction (HCI) research encompasses an extremely rich and diverse set of communities, interest groups and disciplines
There have been many studies that have characterised the HCI community and its publications including the development of taxonomies [Quinn, 2011], analysis of authors [Bartneck 2009 and Kaye 2009] and visual explorations of the area [Henry, 2007]
While there has been previous work examining CHI trends using topic mapping and hierarchical cluster analysis [Padilla 2014 and Liu 2014], in this paper we present a novel way of comparing and contrasting two apparently similar communities: British HCI and CHI
Summary
Human-Computer Interaction (HCI) research encompasses an extremely rich and diverse set of communities, interest groups and disciplines. It has evolved and expanded rapidly as its researchers have embraced new challenges and developed new theories, methodologies and technologies. In such a complex, rapidly changing environment it can be difficult for new researchers to discern the differences between premier conferences in the field. We compare and contrast the British HCI conference (BHCI), a compact flagship HCI forum, against the largest and most popular conference in this field: CHI. There has been work into mapping conferences [Liu 2014 and Padilla 2014] and evaluation of conference processes [Thimbleby, 2012]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
