scholarly journals Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN

Computers ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 38
Author(s):  
Jacky C. P. Chan ◽  
Edmond S. L. Ho
Keyword(s):  
User Study ◽  
Image Representation ◽  
Visual Quality ◽  
Experimental Results ◽  
Body Motion ◽  
Data Driven ◽  
Image Translation ◽  
Motion Sequence ◽  
Perceived Emotion ◽  
Full Body

In this paper, we propose a new data-driven framework for 3D hand and full-body motion emotion transfer. Specifically, we formulate the motion synthesis task as an image-to-image translation problem. By presenting a motion sequence as an image representation, the emotion can be transferred by our framework using StarGAN. To evaluate our proposed method’s effectiveness, we first conducted a user study to validate the perceived emotion from the captured and synthesized hand motions. We further evaluate the synthesized hand and full body motions qualitatively and quantitatively. Experimental results show that our synthesized motions are comparable to the captured motions and those created by an existing method in terms of naturalness and visual quality.

F2FCrowds: Planning Agent Movements to Enable Face-to-Face Interactions

2017 ◽  
Vol 26 (2) ◽  
pp. 228-246 ◽  
Author(s):  
Tanmay Randhavane ◽  
Aniket Bera ◽  
Dinesh Manocha
Keyword(s):  
User Study ◽  
Body Motion ◽  
Virtual Agents ◽  
Virtual Agent ◽  
Face To Face ◽  
Sense Of Presence ◽  
Velocity Prediction ◽  
Multi Agent ◽  
Interaction Velocity ◽  
Full Body

The simulation of human behaviors in virtual environments has many applications. In many of these applications, situations arise in which the user has a face-to-face interaction with a virtual agent. In this work, we present an approach for multi-agent navigation that facilitates a face-to-face interaction between a real user and a virtual agent that is part of a virtual crowd. In order to predict whether the real user is approaching a virtual agent to have a face-to-face interaction or not, we describe a model of approach behavior for virtual agents. We present a novel interaction velocity prediction (IVP) algorithm that is combined with human body motion synthesis constraints and facial actions to improve the behavioral realism of virtual agents. We combine these techniques with full-body virtual crowd simulation and evaluate their benefits by conducting a user study using Oculus HMD in an immersive environment. Results of this user study indicate that the virtual agents using our interaction algorithms appear more responsive and are able to elicit more reaction from the users. Our techniques thus enable face-to-face interactions between a real user and a virtual agent and improve the sense of presence observed by the user.

scholarly journals An HMM-based averaging approach for creating mean motion data from a full-body Motion Capture system to support the development of a biomechanical model

2018 ◽  
Vol 4 (1) ◽  
pp. 389-393
Author(s):  
Andreas Kitzig ◽  
Julia Demmer ◽  
Tobias Bolten ◽  
Edwin Naroska ◽  
Gudrun Stockmanns ◽  
...  
Keyword(s):  
Motion Capture ◽  
Hidden Markov ◽  
Biomechanical Model ◽  
Human Movement ◽  
Body Motion ◽  
Game Development ◽  
Motion Data ◽  
Motion Sequence ◽  
Motion Capture Systems ◽  
Full Body

AbstractMotion capture systems or MoCap systems are used for game development and in the field of sports for the assessment and digitalization of human movement. Furthermore, MoCap systems are also used in the medical and therapeutic field for the analysis of human movement patterns. As examples gait analysis or examination of the musculoskeletal system and its function should be mentioned. Most application relate to a specific person and their movement or to the comparison of movements of different people. Within the scope of this paper an averaged motion sequence is supposed to be generated from MoCap data in order to be able to use it in the field of biomechanical modeling and simulation. For the averaging of individual movement sequences of different persons a Hidden Markov Model (HMM) based approach is presented.

scholarly journals Grasp Planning for a Multifingered Hand with a Humanoid Robot

2010 ◽  
Vol 22 (2) ◽  
pp. 230-238 ◽  
Author(s):  
Tokuo Tsuji ◽  
◽  
Kensuke Harada ◽  
Kenji Kaneko ◽  
Fumio Kanehiro ◽  
...  
Keyword(s):  
Motion Planning ◽  
Humanoid Robot ◽  
Experimental Results ◽  
Body Motion ◽  
Grasp Planning ◽  
Object Position ◽  
Hand Kinematics ◽  
Grasp Type ◽  
Geometrical Relationships ◽  
Full Body

This paper presents grasp planning for a multifingered hand with a humanoid robot. Our planner selects different ways of grasping even for the same object according to object position/orientation. If the planner cannot find a feasible grasp with arm/hand kinematics, it switches to full body motion planning. These functions are necessary for realizing the robust grasp planning. Our planner defines convex models on both the object and each grasp type. In considering geometrical relationships among these convex models, we determine the parameters required to define the final grasping configuration. We demonstrate effectiveness of grasp planning through simulation and experimental results.

scholarly journals Multimedia Quality Integration Using Piecewise Function

2011 ◽  
Vol 1 ◽  
pp. 375-380
Author(s):  
Shu Ai Wan ◽  
Kai Fang Yang ◽  
Hai Yong Zhou
Keyword(s):  
Visual Quality ◽  
Experimental Results ◽  
Integration Model ◽  
Quality Performance ◽  
Piecewise Function ◽  
Proposed Model ◽  
Constant Coefficients ◽  
Theoretical Analyses ◽  
Different Levels

In this paper the important issue of multimedia quality evaluation is concerned, given the unimodal quality of audio and video. Firstly, the quality integration model recommended in G.1070 is evaluated using experimental results. Theoretical analyses aide empirical observations suggest that the constant coefficients used in the G.1070 model should actually be piecewise adjusted for different levels of audio and visual quality. Then a piecewise function is proposed to perform multimedia quality integration under different levels of the audio and visual quality. Performance gain observed from experimental results substantiates the effectiveness of the proposed model.

Contrast Enhancement and Optimization for Image with Fog

2013 ◽  
Vol 380-384 ◽  
pp. 3778-3781
Author(s):  
Wei Na Huang ◽  
Zheng Xiang Xie
Keyword(s):  
Contrast Enhancement ◽  
Real Time ◽  
Visual Quality ◽  
Experimental Results ◽  
Video Monitoring ◽  
Adaptive Model ◽  
Absorption Effect ◽  
Atmospheric Visibility ◽  
Normal Work ◽  
Computing Speed

Aiming at the absorption effect of fog suspended in the atmosphere on light, the paper established the removing-fog compensation adaptive model which can improve the atmospheric visibility and restore the normal work of outdoor system. The experimental results show that the removing fog image processed by the method of removing-fog compensation optimization can accord with the requirement of human visual, and it can be used in real-time video monitoring as the fast computing speed. The method not only can be used in foggy video which the fog distributed uniformly, and can assess the visual quality for the images processed.

Deep Full-Body Motion Network for a Soft Wearable Motion Sensing Suit

2019 ◽  
Vol 24 (1) ◽  
pp. 56-66 ◽  
Author(s):  
Dooyoung Kim ◽  
Junghan Kwon ◽  
Seunghyun Han ◽  
Yong-Lae Park ◽  
Sungho Jo
Keyword(s):  
Body Motion ◽  
Motion Sensing ◽  
Full Body

scholarly journals Co-Reading as a Generative Ontology

2018 ◽  
Vol 6 (3) ◽  
pp. 151-163
Author(s):  
Simon Biggs
Keyword(s):  
Dark Matter ◽  
Motion Tracking ◽  
Interactive Systems ◽  
Body Motion ◽  
Interactive System ◽  
Assemblage Theory ◽  
Multi Agent ◽  
Technical Considerations ◽  
Full Body

This paper discusses the immersive full body motion tracking installation Dark Matter, developed by the author and completed in early 2016. The paper outlines the conceptual focus of the project, including the use of the metaphor of dark matter to explore questions around interactive systems and assemblage. The primary technical considerations involved in the project are also outlined. ‘Co-reading' is proposed as a framework for a generative ontology, within the context of assemblage theory, deployed within a multimodal multi-agent interactive system.

Stresses in compact end closures for cylindrical pressure vessels

1969 ◽  
Vol 4 (1) ◽  
pp. 57-64
Author(s):  
R W T Preater
Keyword(s):  
Cylindrical Shell ◽  
Rigid Body ◽  
Optimum Design ◽  
Cross Section ◽  
Experimental Verification ◽  
Pressure Vessels ◽  
Rigid Body Motion ◽  
Experimental Results ◽  
Body Motion ◽  
Annular Ring

Three different assumptions are made for the behaviour of the junction between the cylindrical shell and the end closure. Comparisons of analytical and experimental results show that the inclusion of a ‘rigid’ annular ring beam at the junction of the cylider and the closure best represents the shell behaviour for a ratio of cylinder mean radius to thickness of 3–7, and enables a prediction of an optimum vessel configuration to be made. Experimental verification of this optimum design confirms the predictions. (The special use of the term ‘rigid’ is taken in this context to refer to a ring beam for which deformations of the cross-section are ignored but rigid body motion is permitted.)

Sign in / Sign up

Export Citation Format

Share Document