International Journal of Advanced Culture Technology

  • 제7권2호
  • /
  • Pages.195-200
  • /
  • 2019
  • /
  • 2288-7202(pISSN)
  • /
  • 2288-7318(eISSN)
국제문화기술진흥원 (The International Promotion Agency of Culture Technology)
권호 표지
DOI QR코드

DOI QR Code

Interaction art using Video Synthesis Technology

  • 투고 : 2019.04.22
  • 심사 : 2019.05.20
  • 발행 : 2019.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Media art, which is a combination of media technology and art, is making a lot of progress in combination with AI, IoT and VR. This paper aims to meet people's needs by creating a video that simulates the dance moves of an object that users admire by using media art that features interactive interactions between users and works. The project proposed a universal image synthesis system that minimizes equipment constraints by utilizing a deep running-based Skeleton estimation system and one of the deep-running neural network structures, rather than a Kinect-based Skeleton image. The results of the experiment showed that the images implemented through the deep learning system were successful in generating the same results as the user did when they actually danced through inference and synthesis of motion that they did not actually behave.

키워드

E1GMBY_2019_v7n2_195_f0001.png 이미지

Figure 1. Structure of GAN

E1GMBY_2019_v7n2_195_f0002.png 이미지

Figure 2. vid2vid sample

E1GMBY_2019_v7n2_195_f0003.png 이미지

Figure 3. System Process diagram

E1GMBY_2019_v7n2_195_f0004.png 이미지

Figure 4. Realtime Multi-Person 2D Human Pose Estimation

E1GMBY_2019_v7n2_195_f0005.png 이미지

Figure 5. Synthesised Process sample

E1GMBY_2019_v7n2_195_f0006.png 이미지

Figure 6. Bit Tracking to Particle Nodes

E1GMBY_2019_v7n2_195_f0007.png 이미지

Figure 7. Result of Proposed System

참고문헌

  1. Cho Sung-hee and Kim Eun-jung. The Fourth Industrial Revolution : A Classification of Reality-Virtual Media Connection System and Case Studies on Dance Performing Arts (2018). the Fourth industrial revolution Written by the Korea Content Association, 18(9), 544-554. https://doi.org/10.5392/JKCA.2018.18.09.544
  2. Lim Yi Jun, Lim Chan, Interactive advertising with VVVV and Kinect, Art and Humanities Convergence Multi-media paper, Vol.8, No10, p.481-489
  3. Young Eun Kim, Mi Gyung Lee, Sang Hun Nam, Jin Wan Park, User Interface of Interactive Media Art in a Stereoscopic Environment, Lecture Notes in Computer Science, vol. 8018, pp. 219-227, (2013).
  4. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, Generative Adversarial Networks, Department of Informatics and Operational Research University of Toronto, (2014)
  5. Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Guilin Liu, Andrew Tao, Jan Kautz, Bryan Catanzaro. ,Video-to-Video Synthesis, Computer Vision and Pattern Recognition (2018).
  6. Caroline Chan, Shiry Ginosar, Tinghui Zhou, Alexei A. Efros, Everybody Dance Now. Computer Vision and Pattern Recognition (2014).
  7. Qifei Wang, Gregorij Kurillo, Ferda Ofli, Ruzena Bajcsy ,Evaluation of Pose Tracking Accuracy in the First 8and Second Generations of Microsoft Kinect, IEEE International Conference on Healthcare Informatics (2015).
  8. Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition(2014).
  9. Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh, Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields, Computer Vision and Pattern Recognition (2017).
  10. Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, Bryan Catanzaro, High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs, Computer Vision and Pattern Recognition (2018).