Reconnaissance 3D de gestes pour l'interaction homme-système

Abstract : The goal of Human System Interaction (HSI) research is to increase the performance of human system interaction in order to make it similar to human-human interaction. As for communication between humans, gestural communication is also widely used in human system interaction. This thesis is about gesture recognition for natural human system interaction based on gestures. The goal of works conducted in this thesis is to propose recognition approaches for different kind of dynamic gesture: simple gesture and composed gesture. Fist of all, we proposed a novel 3D gesture descriptor computed by human body joints angles provided by Kinect sensor. Second, we proposed two dynamic gestures recognition approaches: a) simple gestures recognition approach, b) composed gestures recognition approach. The first approach is based on Hidden Markov Models (HMM). One HMM was created for each gesture. The joints angles variations have been used as input for HMMs. Then, this method has been combined with the Dynamic Time Warping algorithm in order to eliminate bad classification. The second approach treats the case of composed and successive gestures in the same sequence. This approach combines Dynamic Time Warping method with an adaptative window, hence the name: Adaptive Dynamic Time Warping. Two versions have been proposed: Forward and Backward version for online and offline recognition.
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/tel-01804336
Contributor : Frédéric Davesne <>
Submitted on : Thursday, May 31, 2018 - 4:23:17 PM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM
Long-term archiving on: Saturday, September 1, 2018 - 2:36:21 PM

File

2016SACLE052.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-01804336, version 1

Citation

Hajar Hiyadi. Reconnaissance 3D de gestes pour l'interaction homme-système. Traitement du signal et de l'image [eess.SP]. Université Paris-Saclay; Université d'Evry-Val-d'Essonne; Université Mohammed V de Rabat, 2016. Français. ⟨NNT : 2016SACLE052⟩. ⟨tel-01804336⟩

Share

Metrics

Record views

162

Files downloads

771