• Title/Summary/Keyword: 리타겟팅

Search Result 18, Processing Time 0.019 seconds

Fast Content-Aware Video Retargeting Algorithm (고속 컨텐츠 인식 동영상 리타겟팅 기법)

  • Park, Dae-Hyun;Kim, Yoon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.18 no.11
    • /
    • pp.77-86
    • /
    • 2013
  • In this paper, we propose a fast video retargeting method which preserves the contents of a video and converts the image size. Since the conventional Seam Carving which is the well-known content-aware image retargeting technique uses the dynamic programming method, the repetitive update procedure of the accumulation energy is absolutely needed to obtain seam. The energy update procedure cannot avoid the processing time delay because of many operations by the image full-searching. By applying the proposed method, frames which have similar features in video are classified into a scene, and the first frame of a scene is resized by the modified Seam Carving where multiple seams are extracted from candidate seams to reduce the repetitive update procedure. After resizing the first frame of a scene, all continuous frames of the same scene are resized with reference to the seam information stored in the previous frame without the calculation of the accumulation energy. Therefore, although the fast processing is possible with reducing complexity and without analyzing all frames of scene, the quality of an image can be analogously maintained with an existing method. The experimental results show that the proposed method can preserve the contents of an image and can be practically applied to retarget the image on real time.

A study on retargeting error between motion capture FBX and 3ds Max bipod joints (모션캡쳐 FBX와 3ds Max 바이패드 관절의 리타게팅 오차 연구)

  • SangWon Lee
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2024.01a
    • /
    • pp.71-72
    • /
    • 2024
  • 본 논문에서는 Adobe Mixamo, 에픽게임즈 마켓플레이스, 유니티 에셋스토어 등에서 제공되는 모션캡쳐 FBX 데이터를 3ds Max 바이패드 애니메이션 시스템에 리타게팅 적용할 때 발생하는 문제점과 해결 방법을 살펴본다. 모션캡쳐 FBX를 바이패드에 리타게팅 하는 과정은 다양한 측면에서 이슈가 발생하는데 본 논문에서는 종아리와 하박 관절의 X축 회전 오차를 중심으로 살펴본다.

  • PDF

Improving Saliency Map using the Location of Background (배경 영상의 위치를 이용한 관심맵의 개선)

  • Ju, Chao;Gil, Jong In;Kim, Manbae
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2013.11a
    • /
    • pp.48-49
    • /
    • 2013
  • Saliency는 인간의 시각에서 관심 영역이나 객체를 찾기 위한 기법으로 최근 영상 리타겟팅, 영상분할 등에 다양하게 활용되고 있다. 기존 제안된 방법들을 전체영상을 대상으로 saliency map을 구하게 되어, 복잡한 객체들의 구성, 큰 전경객체들의 존재 등의 경우에는 성능이 저하되는 문제점이 있다. 따라서 본 논문에서는 배경이 존재하는 영상들을 대상으로 기존 방식중의 하나인 histogram based contrast(HBC)을 개선하는 방법을 제안한다. 배경영역의 빈도확률을 HBC에 적용하여 배경에 존재하는 픽셀값의 saliency을 감소하면, 상대적으로 전경에 존재하는 픽셀들의 saliency는 증가하게 된다. 실험에서는 제안한 기법으로 배경의 saliency는 감소하고, 전경객체는 증가하는 것을 증명하였다.

  • PDF

Retargetting Fine Facial Motion Data to New Faces (고밀도 얼굴 모션 캡쳐 데이터를 새로운 얼굴로 리타겟팅하는 기법)

  • Na, Kyung-Keon;Jung, Moon-R.
    • Journal of the Korea Computer Graphics Society
    • /
    • v.9 no.3
    • /
    • pp.7-13
    • /
    • 2003
  • 본 논문은 사람의 실제 얼굴에서 캡쳐된 얼굴 모션 데이터를 새로운 얼굴에 재적용하는 리타켓팅 기법을 제안한다. 본 기법은 형태가 매우 상이한 얼굴 모델에도 적용이 가능하며 특히 주름같은 세밀한 모션의 리타켓팅에 적합하다. 본 기법은 다중해상도 메쉬 즉 노말메쉬(normal mesh)를 사용함으로써 소스와 타켓의 계층적으로 대응관계를 결정하고 계층적으로 리타켓팅한다. 노말 메쉬는 주어진 메쉬를 베이스 메쉬 (base mesh)와 일련의 노말 오프셋 (normal offsets)을 이용하여 근사시킨 계층적 메쉬이다. 본 리타켓팅 기법은 우선 베이스 모션을 소스 모델에서 타겟 모델로 리타켓팅한 후 그 모션 위에 노말 오프셋의 모션을 계층적으로 더해준다. 이 기법은 형태가 매우 세밀한 모션에 대하여 안정적이면서도 정교한 리타켓팅 결과를 생성한다.

  • PDF

Effects of Temporal/Social Distance and Message Construal Level on Evaluations of a Retargeting Advertising (복합적인 심리적 거리와 메시지유형의 해석수준 일치가 리타겟팅 광고효과에 미치는 영향)

  • Choi, Hyejin;Kim, Heejin
    • The Journal of the Korea Contents Association
    • /
    • v.19 no.10
    • /
    • pp.593-606
    • /
    • 2019
  • This study examines effective message strategies that fit with the characteristics of retargeting advertisements, based on the Construal Level Theory. First, we investigate whether the social distance that applies between interpersonal interactions can also be observable in an online environment and test the effects of social distance, depending on the type of online sites. We then examine consumers' construal level when social and temporal distances interplay, and how the effects of the messages change accordingly. As a result, social distance and message construal levels by website type were consistent with existing CLT studies. However, the hypothesis that advertising effects will be higher only when all, multidimensions' distances and construal levels of messages match, was partially supported. Also the current view, that the consumers' evaluations will show no difference to when either or both dimensions are distal, was rejected. Instead, when a discrepancy between temporal and social distance was present, the construal level of the message was more effective when congruent with the social distance out the two dimensions. Hence, it is possible to infer that the influence of psychological distance may vary depending on the dimension of distance.

Deep Learning-based Single Image Generative Adversarial Network: Performance Comparison and Trends (딥러닝 기반 단일 이미지 생성적 적대 신경망 기법 비교 분석)

  • Jeong, Seong-Hun;Kong, Kyeongbo
    • Journal of Broadcast Engineering
    • /
    • v.27 no.3
    • /
    • pp.437-450
    • /
    • 2022
  • Generative adversarial networks(GANs) have demonstrated remarkable success in image synthesis. However, since GANs show instability in the training stage on large datasets, it is difficult to apply to various application fields. A single image GAN is a field that generates various images by learning the internal distribution of a single image. In this paper, we investigate five Single Image GAN: SinGAN, ConSinGAN, InGAN, DeepSIM, and One-Shot GAN. We compare the performance of each model and analyze the pros and cons of a single image GAN.

A study about the problems and their solutions in the production process of 3D character animation using optical motion capture technology (옵티컬 모션캡쳐 기술을 활용한 3D 캐릭터 애니메이션에서 제작과정상 문제점 및 해결방안에 관한 연구)

  • Lee, Man-Woo;Kim, Hyun-Jong;Kim, Soon-Gohn
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2006.11a
    • /
    • pp.831-835
    • /
    • 2006
  • Motion capture means the recording of movement of objects such as human beings, animals, creatures, machines, etc in a form applicable to computer. Since the motion capture system can be introduced to the fields where realistic movement of human beings and animals, which cannot be attained with an existing key frame method is required, large scale is necessary or economical burden exists, it has a merit and possibility of new expression. For these reasons, this method is increasingly used in the field of digital entertainment such as movie, TV, advertisement, documentary, music video, etc centering around the game. However, in spite of such an advantage, problems such as too much advance preparation work in digital image expressions using motion capture, marker attachment, compensation of motion data, motion retargeting and lack of professional human resources, etc. are becoming a prominent figure. Accordingly, this study intends to suggest the way of more effective production of motion capture digital image through finding the problems and their draft possible solutions in the production process based on the image production examples using motion capture.

  • PDF

Documentation of Intangible Cultural Heritage Using Motion Capture Technology Focusing on the documentation of Seungmu, Salpuri and Taepyeongmu (부록 3. 모션캡쳐를 이용한 무형문화재의 기록작성 - 국가지정 중요무형문화재 승무·살풀이·태평무를 중심으로 -)

  • Park, Weonmo;Go, Jungil;Kim, Yongsuk
    • Korean Journal of Heritage: History & Science
    • /
    • v.39
    • /
    • pp.351-378
    • /
    • 2006
  • With the development of media, the methods for the documentation of intangible cultural heritage have been also developed and diversified. As well as the previous analogue ways of documentation, the have been recently applying new multi-media technologies focusing on digital pictures, sound sources, movies, etc. Among the new technologies, the documentation of intangible cultural heritage using the method of 'Motion Capture' has proved itself prominent especially in the fields that require three-dimensional documentation such as dances and performances. Motion Capture refers to the documentation technology which records the signals of the time varing positions derived from the sensors equipped on the surface of an object. It converts the signals from the sensors into digital data which can be plotted as points on the virtual coordinates of the computer and records the movement of the points during a certain period of time, as the object moves. It produces scientific data for the preservation of intangible cultural heritage, by displaying digital data which represents the virtual motion of a holder of an intangible cultural heritage. National Research Institute of Cultural Properties (NRICP) has been working on for the development of new documentation method for the Important Intangible Cultural Heritage designated by Korean government. This is to be done using 'motion capture' equipments which are also widely used for the computer graphics in movie or game industries. This project is designed to apply the motion capture technology for 3 years- from 2005 to 2007 - for 11 performances from 7 traditional dances of which body gestures have considerable values among the Important Intangible Cultural Heritage performances. This is to be supported by lottery funds. In 2005, the first year of the project, accumulated were data of single dances, such as Seungmu (monk's dance), Salpuri(a solo dance for spiritual cleansing dance), Taepyeongmu (dance of peace), which are relatively easy in terms of performing skills. In 2006, group dances, such as Jinju Geommu (Jinju sword dance), Seungjeonmu (dance for victory), Cheoyongmu (dance of Lord Cheoyong), etc., will be documented. In the last year of the project, 2007, education programme for comparative studies, analysis and transmission of intangible cultural heritage and three-dimensional contents for public service will be devised, based on the accumulated data, as well as the documentation of Hakyeonhwadae Habseolmu (crane dance combined with the lotus blossom dance). By describing the processes and results of motion capture documentation of Salpuri dance (Lee Mae-bang), Taepyeongmu (Kang seon-young) and Seungmu (Lee Mae-bang, Lee Ae-ju and Jung Jae-man) conducted in 2005, this report introduces a new approach for the documentation of intangible cultural heritage. During the first year of the project, two questions have been raised. First, how can we capture motions of a holder (dancer) without cutoffs during quite a long performance? After many times of tests, the motion capture system proved itself stable with continuous results. Second, how can we reproduce the accurate motion without the re-targeting process? The project re-created the most accurate motion of the dancer's gestures, applying the new technology to drew out the shape of the dancers's body digital data before the motion capture process for the first time in Korea. The accurate three-dimensional body models for four holders obtained by the body scanning enhanced the accuracy of the motion capture of the dance.