I am co-founder of Hovertone, a young startup active in the domain of interactive experience design. I am also a postdoctoral researcher at the University of Mons where I am the head of the motion capture and analysis research group at the numediart institute. I hold a PhD in Applied Sciences, in the field of motion capture data analysis and machine learning based motion synthesis.
We present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized st... more We present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized styles are combinations or exaggerations of the walk styles present in the training database. Our synthesizer is also capable of generating walk sequences with controlled style transitions. In a first stage, Hidden Markov Models of eleven different gait styles are trained, using a database of motion capture walk sequences. In a second stage, the probability density functions inside the stylistic models are interpolated or extrapolated ...
Abstract In this work, we present a Hidden Markov Model (HMM) based stylistic walk synthesizer, w... more Abstract In this work, we present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized styles are combinations or exaggerations of the walk styles present in the training database. In a first stage, Hidden Markov Models of eleven different styles of gait are trained, using a database of motion capture walk sequences. In a second stage, the probability density functions inside the stylistic models are interpolated or extrapolated in order to synthesize walks with styles or style intensities that were not ...
The recent arise of Motion Capture (MoCap) technologies provides new possibilities, but also new ... more The recent arise of Motion Capture (MoCap) technologies provides new possibilities, but also new challenges in human motion analysis. Indeed, the analysis of a motion database is a complex task, due to the high dimensionality of motion data, and the number of independent factors that can affect movements. We addressed the first issue in some of our earlier work by developing MotionMachine, a framework helping to overcome the problem of motion data interpretation through feature extraction and interactive visualization [20]. In this paper, we address the question of the relations between movements and some of the various factors (social, psychological, physiological, etc.) that can influence them. To that end, we propose a tool for rapid factor analysis of a MoCap database. This tool allows statistical exploration of the effect of any factor of the database on motion features. As a use case of this work, we present the analysis of a database of improvised contemporary dance, showing the capabilities and interest of our tool.
ABSTRACT In this paper, we present a comparison between four HMM-based real-time decoding algorit... more ABSTRACT In this paper, we present a comparison between four HMM-based real-time decoding algorithms for stylistic gait recognition and following. The approach is based on a probabilistic modelling of walking gestures recorded through motion capture. The algorithms are evaluated on their ability to recover the progression of the performed gestures over time in real-time, i.e. as the gestures are performed, and their robustness when the decoding is only performed on a subset of the model dimensions. The performance of studied algorithms are also evaluated in the context of a framework for "gait reconstruction", i.e. where the walking gestures recognised on lower body dimensions are used to synchronously regenerate the upper body dimensions (and vice-versa).
We present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized st... more We present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized styles are combinations or exaggerations of the walk styles present in the training database. Our synthesizer is also capable of generating walk sequences with controlled style transitions. In a first stage, Hidden Markov Models of eleven different gait styles are trained, using a database of motion capture walk sequences. In a second stage, the probability density functions inside the stylistic models are interpolated or extrapolated ...
Abstract In this work, we present a Hidden Markov Model (HMM) based stylistic walk synthesizer, w... more Abstract In this work, we present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized styles are combinations or exaggerations of the walk styles present in the training database. In a first stage, Hidden Markov Models of eleven different styles of gait are trained, using a database of motion capture walk sequences. In a second stage, the probability density functions inside the stylistic models are interpolated or extrapolated in order to synthesize walks with styles or style intensities that were not ...
The recent arise of Motion Capture (MoCap) technologies provides new possibilities, but also new ... more The recent arise of Motion Capture (MoCap) technologies provides new possibilities, but also new challenges in human motion analysis. Indeed, the analysis of a motion database is a complex task, due to the high dimensionality of motion data, and the number of independent factors that can affect movements. We addressed the first issue in some of our earlier work by developing MotionMachine, a framework helping to overcome the problem of motion data interpretation through feature extraction and interactive visualization [20]. In this paper, we address the question of the relations between movements and some of the various factors (social, psychological, physiological, etc.) that can influence them. To that end, we propose a tool for rapid factor analysis of a MoCap database. This tool allows statistical exploration of the effect of any factor of the database on motion features. As a use case of this work, we present the analysis of a database of improvised contemporary dance, showing the capabilities and interest of our tool.
ABSTRACT In this paper, we present a comparison between four HMM-based real-time decoding algorit... more ABSTRACT In this paper, we present a comparison between four HMM-based real-time decoding algorithms for stylistic gait recognition and following. The approach is based on a probabilistic modelling of walking gestures recorded through motion capture. The algorithms are evaluated on their ability to recover the progression of the performed gestures over time in real-time, i.e. as the gestures are performed, and their robustness when the decoding is only performed on a subset of the model dimensions. The performance of studied algorithms are also evaluated in the context of a framework for "gait reconstruction", i.e. where the walking gestures recognised on lower body dimensions are used to synchronously regenerate the upper body dimensions (and vice-versa).
Uploads
Papers by Joelle Tilmanne