Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Conflict Transition Scene Using Character Regions

인물 면적을 이용한 갈등 전환 장면 검출

  • Park, Seung-Bo (Inha University, Dept. of Software Convergence Engineering) ;
  • Lee, Chang-Hyun (Inha University, Dept. of Material Processing and Engineering)
  • 박승보 (인하대학교 소프트웨어융합공학과) ;
  • 이창현 (인하대학교 첨단소재공정공학과)
  • Received : 2021.08.30
  • Accepted : 2021.09.07
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The story is formed by the flow of the development and resolution of the conflict between the characters. Namely, the story consists of conflict setting, development, and resolution. Character region is an important expression technique to describe the emotions or states of characters and the relationship between characters and the environment. The purpose of this paper is to propose a method for detecting the transition of conflict from the graph of character region's change. To this end, we present a method of generating a change graph of a character region in a movie by calculating the character region and a method of detecting a conflict transition scene from a graph of character region's change. To verify the performance of the proposed method, an experiment was conducted to extract conflict transition scenes for 7 movies, and performance evaluation results of 73.57% accuracy and 77.26% recall were obtained. This proves that it is possible to extract conflict transition scenes based on the character region.

스토리는 인물들 간의 갈등의 전개와 해소의 흐름에 의해 형성된다. 갈등의 설정, 전개, 해결의 흐름이 스토리이다. 인물 면적은 인물의 감정 또는 상태, 인물 간 관계인물과 환경과의 관계를 묘사하는 중요한 표현 기법이다. 본 논문은 인물 면적의 변화 그래프로부터 갈등의 전환 지점을 검출하는 방법을 제안하는 것이 목적이다. 이를 위해 인물 면적을 계산하여 영화의 인물 면적 변화 그래프를 생성하는 방법과 인물 면적 변화 그래프로부터 갈등 전환 장면을 검출하는 방법을 제시한다. 제안하는 방법의 성능을 검증하기 위해 7개의 영화에 대해 갈등 전환 장면을 추출하는 실험을 진행하여 정확도 73.57%, 재현율 77.26%의 성능 평가 결과를 얻었다. 이를 통해 인물 면적에 기반하여 갈등 전환 장면을 추출하는 것이 가능하다는 것을 증명하였다.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2020R1F1A1076156).

References

  1. S.-B. Park, and J.K. Kim, "Distribution of Close-up Shots by Narrative Structure," Proceeding of 2012 Autumn Conference of Korea Information Processing Society, pp. 22-23, 2012.
  2. Y.M. Lim, "The Climax Expression Analysis Based on the Shot-list Data of Movies," Journal of Broadcast Engineering, Vol. 21, No. 6, pp. 965-976, 2016. https://doi.org/10.5909/JBE.2016.21.6.965
  3. S.H. Kang, S.-B. Park, Y.H. Kim, and E.S. You, "Quantification of The Conflict in Film Narrative : Focusing on Comparison of Characters' Face Area," Journal of Broadcast Engineering, Vol. 24, No 1, pp. 153-163, 2019. https://doi.org/10.5909/JBE.2019.24.1.153
  4. E.H. Jo, Writing animation scenarios from concept to script, RH Korea, 2008.
  5. C.-H. Lee, H.-J. Lee, S.-H. Lee, J.-T. Oh, and S.-B. Park, "Face Detection Using Shapes and Colors in Various Backgrounds," Journal of The Korea Society of Computer and Information, Vol. 26, No. 7, pp.19-27, 2021. https://doi.org/10.9708/JKSCI.2021.26.07.019
  6. Robert Mckee, Story substance, structure, style, and the principle of screenwriting, 1997.
  7. Protagonist, Namuwiki, https://namu.wiki/w/주인공 (accessed Sept. 7, 2021).
  8. Antagonist, Namuwiki, https://namu.wiki/w/반동인물(accessed Sept. 7, 2021).
  9. S.-B. Park, Y. B. Jeon, J. Park, and E. S. You, "Helper Classification via Three Dimensional Visualization of Character-net," Journal of Broadcast Engineering, Vol. 23, No. 1, pp. 53-62, 2018. https://doi.org/10.5909/JBE.2018.23.1.53
  10. Steven D. Katz, Film Directing Shot by Shot: Visualizing from Concept to Screen, Michael Wiese Productions, 1991
  11. Video shot and scene segmentation tool, MKLAB, https://mklab.iti.gr/results/video-shot-and-scene-segmentation/ (accessed Aug. 24, 2021).