Learning and recognition of object manipulation actions using linear and nonlinear dimensionality reduction
2007 (English)In: 2007 RO-MAN: 16TH IEEE International Symposium On Robot And Human Interactive Communication, Vols 1-3, 2007, 1003-1008 p.Conference paper (Refereed)
In this work, we perform an extensive statistical evaluation for learning and recognition of object manipulation actions. We concentrate on single arm/hand actions but study the problem of modeling and dimensionality reduction for cases where actions are very similar to each other in terms of arm motions. For this purpose, we evaluate a linear and a nonlinear dimensionality reduction techniques: Principal Component Analysis and Spatio-Temporal Isomap. Classification of query sequences is based on different variants of Nearest Neighbor classification. We thoroughly describe and evaluate different parameters that affect the modeling strategies and perform the evaluation with a training set of 20 people.
Place, publisher, year, edition, pages
2007. 1003-1008 p.
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-39594ISI: 000255993700183ScopusID: 2-s2.0-48749121521ISBN: 978-1-4244-1634-9OAI: oai:DiVA.org:kth-39594DiVA: diva2:441947
16th IEEE International Symposium on Robot and Human Interactive Communication Location: Cheju Isl, South Korea, Date: AUG 26-29, 2007