The Journal of Korean Institute of Next Generation Computing (한국차세대컴퓨팅학회논문지)

Korean Institute of Next Generation Computing (한국차세대컴퓨팅학회)
권호 표지

Violence Recognition using Deep CNN for Smart Surveillance Applications

스마트 감시 애플리케이션을 위해 Deep CNN을 이용한 폭력인식

  • Received : 2018.09.12
  • Accepted : 2018.10.16
  • Published : 2018.10.31

⟨ Previous Next ⟩

Abstract

Due to the recent developments in computer vision technology, complex actions can be recognized with reasonable accuracy in smart cities. In contrast, violence recognition such as events related to fight and knife, has gained less attention. The capability of visual surveillance can be used for detecting fight in streets or in prison centers. In this paper, we proposed a deep learning-based violence recognition method for surveillance cameras. A convolutional neural network (CNN) model is trained and fine-tuned on available benchmark datasets of fights and knives for violence recognition. When an abnormal event is detected, an alarm can be sent to the nearest police station to take immediate action. Moreover, when the probabilities of fight and knife classes are predicted very low, this situation is considered as normal situation. The experimental results of the proposed method outperformed other state-of-the-art CNN models with high margin by achieving maximum 99.21% accuracy.

최근 컴퓨터 비전 기술의 발전으로 스마트도시에서는 합리적인 정확도로 복잡한 동작을 인식할 수 있다. 이와는 대조적으로, 싸움과 칼에 관련된 사건과 같은 폭력적인 인식은 관심을 덜 이끌었다. 시각적인 감시 능력은 거리나 교도소에서의 싸움을 감지하는데 사용될 수 있다. 이 논문에서 우리는 감시 카메라에 대한 심층 학습 기반의 폭력 인식 방법을 제안했다. 컨볼루션 뉴럴 네트워크(CNN) 모델은 폭력 인식을 위한 싸움과 칼의 벤치마크 데이터 셋에 대해 훈련하고 세부적으로 조정된다. 비정상적인 이벤트가 감지되면 가장 가까운 경찰서로 경보를 보내는 즉각적인 조치를 취할 수 있다. 제안된 방법의 실험 결과는 99.21%의 정확도를 달성함으로써 다른 최첨단 CNN모델을 능가했다.

Keywords

Acknowledgement

Supported by : National Research Foundation of Korea (NRF)

References

  1. Nievas, E.B., et al. Violence detection in video using computer vision techniques. in International conference on Computer analysis of images and patterns. 2011. Springer.
  2. Bilinski, P. and F. Bremond. Human violence recognition and detection in surveillance videos. in 2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). 2016. IEEE.
  3. Giannakopoulos, T., A. Pikrakis, and S. Theodoridis. A multi-class audio classification method with respect to violent content in movies using bayesian networks. in Multimedia Signal Processing, 2007. MMSP 2007. IEEE 9th Workshop on. 2007. IEEE.
  4. Zajdel, W., et al. CASSANDRA: audio-video sensor fusion for aggression detection. in Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Conference on. 2007. IEEE.
  5. Nam, J., M. Alghoniemy, and A.H. Tewfik. Audio-visual content-based violent scene characterization. in Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on. 1998. IEEE.
  6. Datta, A., M. Shah, and N.D.V. Lobo. Personon-person violence detection in video data. in Pattern Recognition, 2002. Proceedings. 16th International Conference on. 2002. IEEE.
  7. Lin, J., Y. Sun, and W. Wang. Violence detection in movies with auditory and visual cues. in Computational Intelligence and Security (CIS), 2010 International Conference on. 2010. IEEE.
  8. Sajjad, M., et al., Raspberry Pi Assisted Facial Expression Recognition Framework for Smart Security in Law-Enforcement Services. Information Sciences, 2018.
  9. Giannakopoulos, T., et al. Violence content classification using audio features. in Hellenic Conference on Artificial Intelligence. 2006. Springer.
  10. Ullah, A., et al., Action recognition in video sequences using deep Bi-directional LSTM with CNN features. IEEE Access, 2018. 6: p. 1155-1166.
  11. Sjoberg, M., et al. The MediaEval 2014 Affect Task: Violent Scenes Detection. in MediaEval. 2014.
  12. Grega, M., et al., Automated detection of firearms and knives in a CCTV image. Sensors, 2016. 16(1): p. 47. https://doi.org/10.3390/s16010047
  13. Demarty, C.-H., et al., VSD, a public dataset for the detection of violent scenes in movies: design, annotation, analysis and evaluation. Multimedia Tools and Applications, 2015. 74(17): p. 7379-7404. https://doi.org/10.1007/s11042-014-1984-4
  14. Zhou, P., et al. Violent Interaction Detection in Video Based on Deep Learning. in Journal of Physics: Conference Series. 2017. IOP Publishing.
  15. Veenendaal, A., et al., Fight and Aggression Recognition using Depth and Motion Data. Computer Science and Emerging Research Journal, 2016. 4.