eprintid: 10115642 rev_number: 17 eprint_status: archive userid: 608 dir: disk0/10/11/56/42 datestamp: 2020-11-23 09:38:48 lastmod: 2021-11-04 00:15:27 status_changed: 2020-11-23 09:38:48 type: proceedings_section metadata_visibility: show creators_name: Bautista, MÁ creators_name: Hernández-Vela, A creators_name: Ponce, V creators_name: Perez-Sala, X creators_name: Baró, X creators_name: Pujol, O creators_name: Angulo, C creators_name: Escalera, S title: Probability-Based Dynamic Time Warping for Gesture Recognition on RGB-D Data ispublished: pub divisions: UCL divisions: B04 divisions: C04 divisions: F34 keywords: Depth maps, Gesture Recognition, Dynamic Time Warping, Statistical Pattern Recognition note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Dynamic Time Warping (DTW) is commonly used in gesture recognition tasks in order to tackle the temporal length variability of gestures. In the DTW framework, a set of gesture patterns are compared one by one to a maybe infinite test sequence, and a query gesture category is recognized if a warping cost below a certain threshold is found within the test sequence. Nevertheless, either taking one single sample per gesture category or a set of isolated samples may not encode the variability of such gesture category. In this paper, a probability-based DTW for gesture recognition is proposed. Different samples of the same gesture pattern obtained from RGB-Depth data are used to build a Gaussian-based probabilistic model of the gesture. Finally, the cost of DTW has been adapted accordingly to the new model. The proposed approach is tested in a challenging scenario, showing better performance of the probability-based DTW in comparison to state-of-the-art approaches for gesture recognition on RGB-D data. date: 2013 date_type: published publisher: Springer, Berlin, Heidelberg official_url: https://doi.org/10.1007/978-3-642-40303-3_14 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1818991 doi: 10.1007/978-3-642-40303-3_14 isbn_13: 9783642403026 publication_declined: 2021-04-21T22:48:20BST lyricists_name: Ponce Lopez, Victor lyricists_id: VPONC48 actors_name: Jayawardana, Anusha actors_id: AJAYA51 actors_role: owner full_text_status: public series: Lecture Notes in Computer Science book series volume: 7854 pagerange: 126-135 event_title: International Workshop on Depth Image Analysis and Applications 2012 issn: 1611-3349 book_title: International Workshop on Depth Image Analysis and Applications WDIA 2012: Advances in Depth Image Analysis and Applications citation: Bautista, MÁ; Hernández-Vela, A; Ponce, V; Perez-Sala, X; Baró, X; Pujol, O; Angulo, C; Bautista, MÁ; Hernández-Vela, A; Ponce, V; Perez-Sala, X; Baró, X; Pujol, O; Angulo, C; Escalera, S; - view fewer <#> (2013) Probability-Based Dynamic Time Warping for Gesture Recognition on RGB-D Data. In: International Workshop on Depth Image Analysis and Applications WDIA 2012: Advances in Depth Image Analysis and Applications. (pp. pp. 126-135). Springer, Berlin, Heidelberg Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10115642/1/Ponce%20Lopez_PDTW_ICPRWorkshop.pdf