Journal of Broadcast Engineering (방송공학회논문지)

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

DOI QR Code

Real-time Violence Video Detection based on Movement Change Characteristics

움직임 변화 특성기반의 실시간 폭력영상 검출

  • Kim, Kwangsoo (Dept. of Electronics and Control Engineering, Hanbat National University) ;
  • Kim, Ungtae (Dept. of Electronics and Control Engineering, Hanbat National University) ;
  • Kwak, Sooyeong (Dept. of Electronics and Control Engineering, Hanbat National University)
  • 김광수 (한밭대학교 전자.제어공학과) ;
  • 김웅태 (한밭대학교 전자.제어공학과) ;
  • 곽수영 (한밭대학교 전자.제어공학과)
  • Received : 2017.02.01
  • Accepted : 2017.03.13
  • Published : 2017.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

A real-time violence detection algorithm based on a new descriptor using the magnitude and direction changes of movement in images is proposed. The descriptor was developed from the observation that the changes of violent actions are much larger than those of normal movements. Descriptor feature vectors consisting of descriptor values during several frames are obtained and these are inputs to SVM(Support Vector Machine) classifier for discriminating violence actions from and non-violence actions. Comparison experiments between the ViF(Violent Flow) and the proposed algorithm were conducted with three different types of datasets. The experimental results show that the proposed algorithm outperforms the ViF in every case.

본 논문에서는 비디오 영상내 사물의 움직임의 방향과 크기의 변화를 이용한 새로운 서술자를 정의하고 이를 기반으로 하여 실시간으로 폭력 영상을 검출하는 방법을 제안한다. 새로 정의된 서술자는 폭력 행위의 움직임의 크기 및 방향 변화량이 일반적인 움직임에 비해 매우 크다는 관찰에 착안한 것이다. 일정한 프레임 동안의 서술자 값으로 이루어진 서술자 특징 벡터를 얻었고, 이것은 SVM(Support Vector Machine)으로 학습된 분류기를 통하여 폭력행위와 비폭력행위를 구별하는 데에 사용되었다. 제안하는 방법의 성능을 검증하기 위해 ViF(Violent Flow) 알고리즘과 세 종류의 데이터셋을 이용하여 비교 실험을 수행하였고, 모든 경우에서 더 우수한 성능을 보임을 확인하였다.

Keywords

References

  1. G. Gerbner, and L. Gross, "Living with television: The violence profile," Journal of Communication, Vol. 26, No. 2, pp. 172-194, 1976. https://doi.org/10.1111/j.1460-2466.1976.tb01397.x
  2. Korea Press Foundation, "Survey of media audience," 2013
  3. J. Kang, and S. Kwak "Violent Behavior Detection using Motion Analysis in Surveillance Video", Journal of broadcast engineering, Vol. 20 No. 3, pp. 430-439, 2015 https://doi.org/10.5909/JBE.2015.20.3.430
  4. E.B. Nievas, O.D. Suarez, G.B. Garcia, and R. Sukthankar, "Violence detection in video using computer vision techniques," Proceeding of International Conference on Computer Analysis of Images and Patterns, pp 332-339, 2011
  5. T. Hassner, Y. Itcher, and O. Kliper-Gross, "Violent Flows: Real-time detection of violent crowd behavior," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1-6, 2012
  6. K. Wang, Z. Zhang, and L. Wang, "Violence Video Detection by Discriminative Slow Feature Analysis," Communications in Computer and Information Science, Vol. 321, pp. 137-144, 2012
  7. I. Laptev and T. Lindeberg, "Space-time Interest Points," International Journal of Computer Vision, Vol 64, No. 2, pp. 107-123. 2005 https://doi.org/10.1007/s11263-005-1838-7
  8. I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld, ,"Learning Human Actions from Movies," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008