DOI QR코드

DOI QR Code

Design of detection method for smoking based on Deep Neural Network

딥뉴럴네트워크 기반의 흡연 탐지기법 설계

  • 이상현 (한국과학기술원 정보보호대학원) ;
  • 윤현수 (한국과학기술원 정보보호대학원) ;
  • 권현 (육군사관학교 전자공학과)
  • Received : 2021.01.11
  • Accepted : 2021.03.26
  • Published : 2021.03.31

Abstract

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

컴퓨팅 기술의 발전과 데이터를 저장할 수 있는 클라우드 환경, 그리고 스마트폰의 보급으로 인하여 많은 데이터가 생산되는 환경에서 인공지능 기술이 발전되고 있다. 이러한 인공지능 기술 중에서 딥뉴럴네트워크는 이미지 인식, 이미지 분류 등에서 탁월한 성능을 제공하고 있다. 기존에는 이러한 딥뉴럴네트워크를 이용하여 산불 및 화재 예방을 위한 이미지 탐지에 대해 많은 연구가 있었지만 흡연 탐지에 대한 연구는 미흡한 실정이었다. 한편 군 부대에서는 각종 시설에 대한 감시체계를 CCTV를 통해 구축하고 있는데 화재, 폭발사고 예방을 위해 탄약고 주변에서의 흡연이나 금연구역에서의 흡연을 CCTV로 탐지하는 것이 필요한 상황이다. 본 논문에서는 딥뉴럴네트워크를 이용하여 흡연 여부를 탐지하는 방법에 대한 성능 분석을 하였으며 활성화함수, 학습률 등 실험적으로 최적화된 수치를 반영하여 흡연사진과 비흡연사진을 두 가지 경우로 탐지하는 것을 하였다. 실험 데이터로는 인터넷 상에 공개되어 있는 흡연 및 비흡연 사진을 크롤링하여 데이터를 구축하였으며, 실험은 머신러닝 라이브러리를 이용하였다. 실험결과로 학습률 0.004로 최적화 알고리즘 Adam을 사용하였을 때, 93%의 accuracy와 92%의 F1-score를 갖는 것을 볼 수 있었다. 또한 이로써 이미지의 연속인 CCTV 영상도 딥뉴럴네트워크를 이용하여 흡연 여부를 탐지할 수 있음을 알 수 있었다.

Keywords

Acknowledgement

본 논문은 화랑대연구소의 2021년도(21-군학-5) 저술활동비 지원을 받아 연구되었음.

References

  1. 대한민국 국방부, "2020 국방백서", 대한민국 국방부, 2020
  2. 정춘일, "4차 산업혁명과 군사혁신 4.0", 전략연구, 제24권, 제2호, pp. 183-211, 2017.
  3. Kim, Young-Jin, and Eun-Gyung Kim, "Image based fire detection using convolutional neural network", Journal of the Korea Institute of Information and Communication Engineering, Vol. 20, No. 9, pp. 1649-1656, 2016. https://doi.org/10.6109/JKIICE.2016.20.9.1649
  4. F Rosenblatt, "The perceptron: a probabilistic model for information storage and organization in the brain.", Psychological review, Vol. 65, No. 6, pp. 386-408, 1958. https://doi.org/10.1037/h0042519
  5. GE Hinton, S Osindero, YW Teh, "A fast learning algorithm for deep belief nets", Neural computation, Vol. 18, No. 7, pp. 1527-1554, 2006. https://doi.org/10.1162/neco.2006.18.7.1527
  6. SM Ahn, "Deep Learning Architectures and Applications", Journal of Intelligence and Information Systems, Vol. 22, No. 2, pp. 127-142, 2016 https://doi.org/10.13088/JIIS.2016.22.2.127
  7. Inoue, H., "Image-based smoke detection with k-Subspaces clustering", Proc. of 2009 RISP International Workshop on Nonlinear Circuits and Signal Processing (NCSP'09), pp. 321-324, 2009.
  8. Wu, Pin, et al., "Human smoking event detection using visual interaction clues", 2010 International Conference on Pattern Recognition IEEE, pp. 4344-4347, 2010.
  9. Odetallah, Amjad D., and Sos S. Agaian., "Human visual system-based smoking event detection", Mobile Multimedia/Image Processing, Security, and Applications 2012, Vol. 8406, 2012.
  10. Bien, Tse-Lun, and Chang Hong Lin., "Detection and recognition of indoor smoking events", Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies, Vol. 8784, 2013.
  11. Agarap, Abien Fred., "Deep learning using rectified linear units (relu)", arXiv preprint arXiv:1803.08375, 2018.
  12. Marreiros, A. C., Daunizeau, J., Kiebel, S. J., & Friston, K. J., "Population dynamics: variance and the sigmoid activation function", Neuroimage, Vol. 42, No. 1, pp. 147-157, 2008. https://doi.org/10.1016/j.neuroimage.2008.04.239
  13. Joulin, Armand, et al., "Efficient softmax approximation for gpus", Proceedings of the 34th International Conference on Machine Learning, PMLR, Vol. 70, pp. 1302-1310, 2017.
  14. Qin, Zhenyue, Dongwoo Kim, and Tom Gedeon, "Rethinking softmax with cross-entropy: Neural network classifier as mutual information estimator" arXiv preprint arXiv:1911.10688. 2019.
  15. Du, Simon, et al., "Gradient descent finds global minima of deep neural networks" Proceedings of the 36th International Conference on Machine Learning, PMLR, Vol. 97, pp. 1675-1685, 2019.
  16. Kalchbrenner, Nal, Edward Grefenstette, and Phil Blunsom, "A convolutional neural network for modelling sentences" arXiv preprint arXiv:1404.2188, 2014.
  17. Sandler, Mark, et al., "MobileNetV2: Inverted residuals and linear bottlenecks" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 4510-4520, 2018.
  18. Kingma, Diederik P., and Jimmy Ba., "Adam: A method for stochastic optimization" arXiv preprint arXiv:1412.6980, 2014.
  19. Kwon, Hyun, et al. "Optimal cluster expansion-based intrusion tolerant system to prevent denial of service attacks." Applied Sciences 7.11 (2017): 1186. https://doi.org/10.3390/app7111186
  20. Kwon, Hyun, et al. "Classification score approach for detecting adversarial example in deep neural network." Multimedia Tools and Applications (2020): 1-22.
  21. Kwon, Hyun, and Jun Lee. "AdvGuard: Fortifying Deep Neural Networks against Optimized Adversarial Example Attack." IEEE Access (2020).
  22. Kwon, Hyun, Hyunsoo Yoon, and Ki-Woong Park. "Acoustic-decoy: Detection of adversarial examples through audio modification on speech recognition system." Neurocomputing 417 (2020): 357-370. https://doi.org/10.1016/j.neucom.2020.07.101