Virtual Character Animation based on Data-driven Motion Capture using Deep Learning Technique

Remaining useful life (RUL) estimation is one of the most important aspects of prognostics and health management (PHM). Various deep learning (DL) based techniques have been developed and applied for the purposes of RUL estimation. One limitation of DL is the lack of physical interpretations as they are purely data driven models. Another limitation is the need for an exceedingly large amount of data to arrive at an acceptable pattern recognition performance for the purposes of RUL estimation. This research is aimed to overcome these limitations by developing physics based DL techniques for RUL prediction and validate the method with real run-to-failure datasets. The contribution of the research relies on creating hybrid DL based techniques as well as combining physics based approaches with DL techniques for effective RUL prediction.

Download Full-text

Manifold Learning Techniques for Editing Motion Capture Data

10.26686/wgtn.17019701 ◽

2021 ◽

Author(s):

◽

Christopher Dean

Keyword(s):

Motion Capture ◽

Manifold Learning ◽

Fundamental Problem ◽

Character Animation ◽

Data Driven ◽

Motion Capture Data ◽

Edit Propagation ◽

Learning Techniques ◽

Non Local ◽

The Difference

<p>Streamlining the process of editing motion capture data and keyframe character animation is a fundamental problem in the animation field. This paper explores a new method for editing character animation, by using a data-driven pose distance as a falloff to interpolate new poses seamlessly into the sequence. This pose distance is the measure given by Green's function of the pose space Laplacian. The falloff shape and timing extent are naturally suited to the skeleton's range of motion, replacing the need for a manually customized falloff spline. This data-driven falloff is somewhat analogous to the difference between a generic spline and the ``magic wand'' selection in an image editor, but applied to the animation domain. It also supports powerful non-local edit propagation in which edits are applied to all similar poses in the entire animation sequence.</p>

Download Full-text

Manifold Learning Techniques for Editing Motion Capture Data

10.26686/wgtn.17019701.v1 ◽

2021 ◽

Author(s):

◽

Christopher Dean

Keyword(s):

Motion Capture ◽

Manifold Learning ◽

Fundamental Problem ◽

Character Animation ◽

Data Driven ◽

Motion Capture Data ◽

Edit Propagation ◽

Learning Techniques ◽

Non Local ◽

The Difference

<p>Streamlining the process of editing motion capture data and keyframe character animation is a fundamental problem in the animation field. This paper explores a new method for editing character animation, by using a data-driven pose distance as a falloff to interpolate new poses seamlessly into the sequence. This pose distance is the measure given by Green's function of the pose space Laplacian. The falloff shape and timing extent are naturally suited to the skeleton's range of motion, replacing the need for a manually customized falloff spline. This data-driven falloff is somewhat analogous to the difference between a generic spline and the ``magic wand'' selection in an image editor, but applied to the animation domain. It also supports powerful non-local edit propagation in which edits are applied to all similar poses in the entire animation sequence.</p>

Download Full-text

Data-driven soft sensor development based on deep learning technique

Journal of Process Control ◽

10.1016/j.jprocont.2014.01.012 ◽

2014 ◽

Vol 24 (3) ◽

pp. 223-233 ◽

Cited By ~ 209

Author(s):

Chao Shang ◽

Fan Yang ◽

Dexian Huang ◽

Wenxiang Lyu

Keyword(s):

Deep Learning ◽

Soft Sensor ◽

Data Driven ◽

Sensor Development ◽

Learning Technique

Download Full-text

A deep learning technique-based data-driven model for accurate and rapid flood prediction

10.5194/hess-2021-596 ◽

2022 ◽

Author(s):

Qianqian Zhou ◽

Shuai Teng ◽

Xiaoting Liao ◽

Zuxiang Situ ◽

Junman Feng ◽

...

Keyword(s):

Deep Learning ◽

Prediction Model ◽

Hydrodynamic Model ◽

Bayesian Optimization ◽

Data Driven ◽

Real Time Control ◽

Flood Prediction ◽

Urban Flood ◽

Learning Technique ◽

Flood Maps

Abstract. An accurate and rapid urban flood prediction model is essential to support decision-making on flood management, especially under increasing extreme precipitation conditions driven by climate change and urbanization. This study developed a deep learning technique-based data-driven flood prediction model based on an integration of LSTM network and Bayesian optimization. A case study in north China was applied to test the model performance and the results clearly showed that the model can accurately predict flood maps for various hyetograph inputs, meanwhile with substantial improvements in computation time. The model predicted flood maps 19,585 times faster than the physical-based hydrodynamic model and achieved a mean relative error of 9.5 %. For retrieving the spatial patterns of water depths, the degree of similarity of the flood maps was very high. In a best case, the difference between the ground truth and model prediction was only 0.76 % and the spatial distributions of inundated paths and areas were almost identical. The proposed model showed a robust generalizability and high computational efficiency, and can potentially replace and/or complement the conventional hydrodynamic model for urban flood assessment and management, particularly in applications of real time control, optimization and emergency design and plan.

Download Full-text