• ETRI Journal
• /
• v.37 no.2
• /
• pp.406-416
• /
• 2015

Timing plays a key role in expressing the qualitative aspects of a character's motion; that is, conveying emotional state, personality, and character role, all potentially without changing spatial positions. Temporal editing of locomotion style is particularly difficult for a novice animator since observers are not well attuned to the sense of weight and energy displayed through motion timing; and the interface for adjusting timing is far less intuitive to use than that for adjusting pose. In this paper, we propose an editing system that effectively captures the timing variations in an example locomotion set and utilizes them for style transfer from one motion to another via both global and upper-body timing transfers. The global timing transfer focuses on matching the input motion to the body speed of the selected example motion, while the upper-body timing transfer propagates the sense of movement flow - succession - through the torso and arms. Our transfer process is based on key times detected from the example set and transferring the relative changes of angle rotation in the upper body joints from a timing source to an input target motion. We demonstrate that our approach is practical in an interactive application such that a set of short locomotion cycles can be applied to generate a longer sequence with continuously varied timings.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.33-43
• /
• 2021

In this paper, we propose a framework that transfers the information of style motions to content motions based on a variational autoencoder network combined with a style encoding in the latent space. Because we transfer a style to a content motion that is sampled from a variational autoencoder, we can increase the diversity of existing motion data. In addition, we can improve the unnatural motions caused by decoding a new latent variable from style transfer. That improvement was achieved by additionally using the velocity information of motions when generating next frames.

• Smart Media Journal
• /
• v.5 no.4
• /
• pp.63-68
• /
• 2016

Texture transfer is a method to transfer the texture of an input image into a target image, and is also used for transferring artistic style of the input image. This study presents a real-time texture transfer for generating artistic style video. In order to enhance performance, this paper proposes a parallel framework using T-shape kernel used in general texture transfer on GPU. To accelerate motion computation time which is necessarily required for maintaining temporal coherence, a multi-scaled motion field is proposed in parallel concept. Through these approach, an artistic texture transfer for video with a real-time performance is archived.

• Korean Journal of Applied Biomechanics
• /
• v.20 no.2
• /
• pp.213-219
• /
• 2010

The purpose of this study is developing a method to analyze and evaluate a golf swing motion using the ground reaction force (GRF) data. Proper weight shifting is essential for a successful shot in golf swing and this could be evaluated by means of the forces between the feet and ground. GRF during the swing were measured from 15 low-handicapped male golfers including professionals. Four clubs(driver, iron 3, iron 5, and iron 7) were selected to analyze the differences due to different characteristics of club. Swings of each subject were taken using a high speed video camera and GRF data were taken simultaneously by two AMTI force platforms. To simplify the GRF data, forces of the three major component of GRF(vertical, lateral, anterior-posterior force) at 10 predefined temporal events for each trial were selected and the mean of each event were calculated and evaluated. Analyzed vertical GRF (VGRF) data could be divided into two different styles, one-legged and two legged. One-legged style shows good weight transfer to the target leg and most of the previous study shows this style as a typical pattern of good players. Therefore the data from the iron 5 swing obtained from 10 one-legged style golfers are provided as criteria for the evaluation of a swing.

• Korean Journal of Applied Biomechanics
• /
• v.17 no.4
• /
• pp.115-125
• /
• 2007

Grould Reaction force(GRF) is important in human movements and GRF measurements are one of the most frequently used tool in biomechanical studies. In the studies of the golf swing motion, people refer to GRF as weight transfer. A successful golf swing motion requires many segments activation sequences which are controled by the nerve system. Due to the inter- and intra-individual variability of the human movement and the movement strategies, reliability of the measurements are important in human movement studies. Previous golf researches were based on group studies and certain events' values were analyzed. The purposes of this study were to determine the number of trials for the reliable golf swing GRF data collection, to reveal the variability level of the meaningful components of the golf swing GRF, and to classify the types of the golf swing GRF patterns. Twenty three male professional golfers($26.4{\pm}6.6$ years, $174.3{\pm}5.2\;cm$, $71.3{\pm}6.5\;kg$) signed an informed consent form prior to participation in this study. GRFs of driver swings were collected with Kistler 9285 force platform and 9865A amplifier, and calculated by the KwonGRF program(Visol, Korea). Sampling frequency was 1080 Hz. GRF data were trimmed from 1.5 s prior to the impact to 0.5 s after the impact. The number of trials for the reliable GRF collection was determined when the change in floating mean overs the 25 % of the standard deviation of that variable. Variabilities of the variables were determined by the coefficient of variation(CV) of 10 %. The types of GRF patterns were determined by visual inspection of the peak GRF shapes. The minimum number of trials for the reliable golf swing GRF data collection was five. Ten-trial seems more conservative. The value of the peak GRF was more reliable than the value of the impact GRF. The CV of the peak GRF and impact GRF were 7.4 %, 15.2 %, respectively. Because of the +/- sigh of the peak GRF appearance time, it was impossible to calculate CV of the peak GRF appearance time. Golf swing GRF patterns were classified as sing peak type, double peak type, and plateau peak type. This classification suggests the presence of the different golf swing weight transfer strategies.