• ETRI Journal
• /
• 제37권2호
• /
• 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.

• 한국컴퓨터그래픽스학회논문지
• /
• 제27권5호
• /
• pp.33-43
• /
• 2021

본 논문에서는 변형 자동 인코더 네트워크(variational autoencoder network)의 잠재 공간 내에 스타일 자동 인코더 네트워크를 적용하여 컨텐츠 캐릭터의 모션에 스타일 캐릭터 모션의 스타일 정보를 이전하는 프레임워크를 제안한다. 이 프레임워크를 사용하면 기존의 변형 자동 인코더를 통해 얻은 모션의 다양성을 스타일 캐릭터 모션의 스타일 정보를 이전하여 증가시킬 수 있다. 또한 입력 데이터 및 출력 데이터에 모션의 속도 정보를 포함시켜 이전 프레임의 모션에 속도를 적분하여 모션을 계산함으로써, 변형 자동 인코더로 인한 샘플링과 잠재 공간 내에서 스타일 정보가 이전된 새로운 잠재 변수의 디코더 네트워크를 통한 확장으로 발생할 수 있는 부자연스러운 동작을 개선할 수 있다.

• 스마트미디어저널
• /
• 제5권4호
• /
• pp.63-68
• /
• 2016

텍스처전이(Texture Transfer) 기법은 타겟영상의 고주파 성분인 텍스쳐를 소스영상에 적용시키는 영상처리 방법이다. 이 텍스쳐 전이기법은 입력 영상에 표현되고 있는 질감 등의 스타일을 대상 영상에 전이시키는데 사용 될 수 있다. 본 연구에서는 이러한 텍스쳐 전이기법을 비디오에 적용시키기 위한 방법을 제안한다. 특히 동영상에 적용시키기 위한 실시간 병렬 처리 알고리즘을 제안한다. 이를 위해서 기존 텍스쳐 전이기법에 사용되는 커널의 모양을 변경하여 병렬화가 가능하도록 하였으며, 동영상 적용 시 발생하는 시간적 일관성문제를 해결하기 위한 방법으로 비디오 프레임 영상의 다중해상도를 사용한 광류측정법을 제안하여 적용함으로써 실시간 비디오 처리를 가능하게 하였다.

• 한국운동역학회지
• /
• 제20권2호
• /
• 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.

• 한국운동역학회지
• /
• 제17권4호
• /
• 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.