scholarly journals Modeling and evaluating beat gestures for social robots

2021 ◽  
Author(s):  
Unai Zabala ◽  
Igor Rodriguez ◽  
José María Martínez-Otzeta ◽  
Elena Lazkano
Keyword(s):  
Motion Capture ◽  
Motion Capture System ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Desirable Feature ◽  
Quantitative Results ◽  
Path Lengths ◽  
End Effectors ◽  
The One ◽  
Made In

AbstractNatural gestures are a desirable feature for a humanoid robot, as they are presumed to elicit a more comfortable interaction in people. With this aim in mind, we present in this paper a system to develop a natural talking gesture generation behavior. A Generative Adversarial Network (GAN) produces novel beat gestures from the data captured from recordings of human talking. The data is obtained without the need for any kind of wearable, as a motion capture system properly estimates the position of the limbs/joints involved in human expressive talking behavior. After testing in a Pepper robot, it is shown that the system is able to generate natural gestures during large talking periods without becoming repetitive. This approach is computationally more demanding than previous work, therefore a comparison is made in order to evaluate the improvements. This comparison is made by calculating some common measures about the end effectors’ trajectories (jerk and path lengths) and complemented by the Fréchet Gesture Distance (FGD) that aims to measure the fidelity of the generated gestures with respect to the provided ones. Results show that the described system is able to learn natural gestures just by observation and improves the one developed with a simpler motion capture system. The quantitative results are sustained by questionnaire based human evaluation.

scholarly journals Image Completion with Large or Edge-Missing Areas

Algorithms ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 14
Author(s):  
Jianjian Ji ◽  
Gang Yang
Keyword(s):  
Experimental Results ◽  
The Other ◽  
Context Information ◽  
Network Structures ◽  
Image Completion ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Other Hand ◽  
The One ◽  
Pseudo Color

Existing image completion methods are mostly based on missing regions that are small or located in the middle of the images. When regions to be completed are large or near the edge of the images, due to the lack of context information, the completion results tend to be blurred or distorted, and there will be a large blank area in the final results. In addition, the unstable training of the generative adversarial network is also prone to cause pseudo-color in the completion results. Aiming at the two above-mentioned problems, a method of image completion with large or edge-missing areas is proposed; also, the network structures have been improved. On the one hand, it overcomes the problem of lacking context information, which thereby ensures the reality of generated texture details; on the other hand, it suppresses the generation of pseudo-color, which guarantees the consistency of the whole image both in vision and content. The experimental results show that the proposed method achieves better completion results in completing large or edge-missing areas.

scholarly journals A Hyperspectral Image Classification Method Based on Multi-Discriminator Generative Adversarial Networks

Sensors ◽  
2019 ◽  
Vol 19 (15) ◽  
pp. 3269 ◽  
Author(s):  
Hongmin Gao ◽  
Dan Yao ◽  
Mingxia Wang ◽  
Chenming Li ◽  
Haiyun Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
The One ◽  
Hyperspectral Remote Sensing Images

Hyperspectral remote sensing images (HSIs) have great research and application value. At present, deep learning has become an important method for studying image processing. The Generative Adversarial Network (GAN) model is a typical network of deep learning developed in recent years and the GAN model can also be used to classify HSIs. However, there are still some problems in the classification of HSIs. On the one hand, due to the existence of different objects with the same spectrum phenomenon, if only according to the original GAN model to generate samples from spectral samples, it will produce the wrong detailed characteristic information. On the other hand, the gradient disappears in the original GAN model and the scoring ability of a single discriminator limits the quality of the generated samples. In order to solve the above problems, we introduce the scoring mechanism of multi-discriminator collaboration and complete semi-supervised classification on three hyperspectral data sets. Compared with the original GAN model with a single discriminator, the adjusted criterion is more rigorous and accurate and the generated samples can show more accurate characteristics. Aiming at the pattern collapse and diversity deficiency of the original GAN generated by single discriminator, this paper proposes a multi-discriminator generative adversarial networks (MDGANs) and studies the influence of the number of discriminators on the classification results. The experimental results show that the introduction of multi-discriminator improves the judgment ability of the model, ensures the effect of generating samples, solves the problem of noise in generating spectral samples and can improve the classification effect of HSIs. At the same time, the number of discriminators has different effects on different data sets.

scholarly journals Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images

Electronics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 603
Author(s):  
Quang T. M. Pham ◽  
Janghoon Yang ◽  
Jitae Shin
Keyword(s):  
Real Data ◽  
Similarity Score ◽  
Generative Adversarial Network ◽  
Age Progression ◽  
Regression Methods ◽  
Adversarial Network ◽  
Face Images ◽  
The Face ◽  
Quantitative Results ◽  
Human Faces

The performance of existing face age progression or regression methods is often limited by the lack of sufficient data to train the model. To deal with this problem, we introduce a novel framework that exploits synthesized images to improve the performance. A conditional generative adversarial network (GAN) is first developed to generate facial images with targeted ages. The semi-supervised GAN, called SS-FaceGAN, is proposed. This approach considers synthesized images with a target age and the face images from the real data so that age and identity features can be explicitly utilized in the objective function of the network. We analyze the performance of our method over previous studies qualitatively and quantitatively. The experimental results show that the SS-FaceGAN model can produce realistic human faces in terms of both identity preservation and age preservation with the quantitative results of a decent face detection rate of 97% and similarity score of 0.30 on average.

scholarly journals Measurement of chest wall motion using a motion capture system with the one-pitch phase analysis method

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hiroyuki Tamiya ◽  
Akihisa Mitani ◽  
Hideaki Isago ◽  
Taro Ishimori ◽  
Minako Saito ◽  
...  
Keyword(s):  
Pulmonary Function ◽  
Chest Wall ◽  
Phase Analysis ◽  
Motion Capture ◽  
Vital Capacity ◽  
Wall Motion ◽  
Motion Capture System ◽  
High Precision Measurement ◽  
Chest Wall Motion ◽  
The One

AbstractSpirometry is a standard method for assessing lung function. However, its use is challenging in some patients, and it has limitations such as risk of infection and inability to assess regional chest wall motion. A three-dimensional motion capture system using the one-pitch phase analysis (MCO) method can facilitate high precision measurement of moving objects in real-time in a non-contacting manner. In this study, the MCO method was applied to examine thoraco-abdominal (TA) wall motion for assessing pulmonary function. We recruited 48 male participants, and all underwent spirometry and chest wall motion measurement with the MCO method. A significant positive correlation was observed between the vital capacity (Spearman’s ρ = 0.68, p < 0.0001), forced vital capacity (Spearman’s ρ = 0.62, p < 0.0001), and tidal volume (Spearman’s ρ = 0.61, p < 0.0001) of spirometry and the counterpart parameters of MCO method. Moreover, the MCO method could detect regional rib cage and abdomen compartment contributions and could assess TA asynchrony, indicating almost complete synchronous movement (phase angle for each compartment: − 5.05° to 3.86°). These findings suggest that this technique could examine chest wall motion, and may be effective in analyzing chest wall volume changes and pulmonary function.

scholarly journals Machine Learning-Based Direct Solver for One-To-Many Problems on Temporal Shaping of Electron Beams

2021 ◽  
Author(s):  
Jinyu Wan ◽  
Yi Jiao ◽  
Juhao Wu
Keyword(s):  
Machine Learning ◽  
Stochastic Optimization ◽  
Optimization Methods ◽  
Supervised Machine Learning ◽  
Generative Adversarial Network ◽  
Local Optima ◽  
Adversarial Network ◽  
Dispersion Terms ◽  
The One ◽  
Temporal Profiles

Abstract To control the temporal profile of an electron beam to meet requirements of various advanced scientific applications, a widely-used technique is to manipulate the dispersion terms which turns out to be one-to-many problems. Due to their intrinsic one-to-many property, current popular stochastic optimization approaches on temporal shaping are not very effective, for being trapped into local optima or suggesting only one solution. Here we propose a real-time solver for one-to-many problems of temporal shaping, with the aid of a semi-supervised machine learning method, the conditional generative adversarial network (CGAN). We demonstrate that the CGAN solver can learn the one-to-many dynamics and is able to accurately and quickly predict the required dispersion terms for different custom temporal profiles. This machine learning-based solver overcomes the limitation of the stochastic optimization methods and is expected to have the potential for wide applications to one-to-many problems in other scientific fields.

scholarly journals A Deep-Learning Method for Radar Micro-Doppler Spectrogram Restoration

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 5007
Author(s):  
Yuan He ◽  
Xinyu Li ◽  
Runlong Li ◽  
Jianping Wang ◽  
Xiaojun Jing
Keyword(s):  
Deep Learning ◽  
Motion Capture ◽  
Radio Frequency Interference ◽  
Learning Method ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Qualitative And Quantitative ◽  
Adversarial Network ◽  
Simulated Motion ◽  
Coarse To Fine

Radio frequency interference, which makes it difficult to produce high-quality radar spectrograms, is a major issue for micro-Doppler-based human activity recognition (HAR). In this paper, we propose a deep-learning-based method to detect and cut out the interference in spectrograms. Then, we restore the spectrograms in the cut-out region. First, a fully convolutional neural network (FCN) is employed to detect and remove the interference. Then, a coarse-to-fine generative adversarial network (GAN) is proposed to restore the part of the spectrogram that is affected by the interferences. The simulated motion capture (MOCAP) spectrograms and the measured radar spectrograms with interference are used to verify the proposed method. Experimental results from both qualitative and quantitative perspectives show that the proposed method can mitigate the interference and restore high-quality radar spectrograms. Furthermore, the comparison experiments also demonstrate the efficiency of the proposed approach.

Simulation of the internal temperature in the Passol Laboratory, University of Debrecen

2012 ◽  
Vol 3 (1) ◽  
pp. 63-73 ◽  
Author(s):  
I. Csáky ◽  
F. Kalmár
Keyword(s):  
Temperature Variation ◽  
Air Temperature ◽  
Indoor Air ◽  
Storage Capacity ◽  
Building Structures ◽  
Internal Temperature ◽  
The One ◽  
Heavy Structure ◽  
East West ◽  
Made In

Abstract Nowadays the facades of newly built buildings have significant glazed surfaces. The solar gains in these buildings can produce discomfort caused by direct solar radiation on the one hand and by the higher indoor air temperature on the other hand. The amplitude of the indoor air temperature variation depends on the glazed area, orientation of the facade and heat storage capacity of the building. This paper presents the results of a simulation, which were made in the Passol Laboratory of University of Debrecen in order to define the internal temperature variation. The simulation proved that the highest amplitudes of the internal temperature are obtained for East orientation of the facade. The upper acceptable limit of the internal air temperature is exceeded for each analyzed orientation: North, South, East, West. Comparing different building structures, according to the obtained results, in case of the heavy structure more cooling hours are obtained, but the energy consumption for cooling is lower.

Gender differences in the Achilles tendon load during the fencing lunge

2014 ◽  
Vol 6 (3) ◽  
Author(s):  
Jonathan Kenneth Sinclair ◽  
Lindsay Bottoms
Keyword(s):  
Gender Differences ◽  
Achilles Tendon ◽  
Motion Capture ◽  
Tendon Injury ◽  
Force Platform ◽  
Motion Capture System ◽  
3D Motion ◽  
Loading Rates ◽  
Tendon Pathology ◽  
3D Motion Capture

AbstractRecent epidemiological analyses in fencing have shown that injuries and pain linked specifically to fencing training/competition were evident in 92.8% of fencers. Specifically the prevalence of Achilles tendon pathology has increased substantially in recent years, and males have been identified as being at greater risk of Achilles tendon injury compared to their female counterparts. This study aimed to examine gender differences in Achilles tendon loading during the fencing lunge.Achilles tendon load was obtained from eight male and eight female club level epee fencers using a 3D motion capture system and force platform information as they completed simulated lunges. Independent t-tests were performed on the data to determine whether differences existed.The results show that males were associated with significantly greater Achilles tendon loading rates in comparison to females.This suggests that male fencers may be at greater risk from Achilles tendon pathology as a function of fencing training/ competition.

Sign in / Sign up

Export Citation Format

Share Document