Journal of Broadcast Engineering (방송공학회논문지)

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

DOI QR Code

Using Skeleton Vector Information and RNN Learning Behavior Recognition Algorithm

스켈레톤 벡터 정보와 RNN 학습을 이용한 행동인식 알고리즘

  • Kim, Mi-Kyung (Dept. of Electronics Engineering, Pusan National University) ;
  • Cha, Eui-Young (Dept. of Computer Science and Engineering, Pusan National University)
  • 김미경 (부산대학교 전자공학과) ;
  • 차의영 (부산대학교 정보컴퓨터공학과)
  • Received : 2018.04.23
  • Accepted : 2018.08.31
  • Published : 2018.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

행동 인식은 데이터를 통해 인간의 행동을 인식하는 기술로서 비디오 감시 시스템을 통한 위험 행동과 같은 어플리케이션에 활용되어 질 수 있다. 기존의 행동 인식 알고리즘은 2차원 카메라를 통한 영상이나 다중모드 센서, 멀티 뷰와 같은 장비를 이용한 방법을 사용하거나 3D 장비를 이용하여 이루어져 왔다. 2차원 데이터를 사용한 경우 3차원 공간의 행위 인식에서는 가려짐과 같은 현상으로 낮은 인식율을 보였고 다른 방법은 복잡한 장비의 구성이나 고가의 추가적인 장비로 인한 어려움이 많았다. 본 논문은 RGB와 Depth 정보만을 이용하여 추가적인 장비 없이 CCTV 영상만으로 인간의 행동을 인식하는 방법을 제안한다. 먼저 RGB 영상에서 스켈레톤 추출 알고리즘을 적용하여 관절과 신체부위의 포인트를 추출한다. 이를 식을 적용하여 변위 벡터와 관계 벡터를 포함한 벡터로 변형한 후 RNN 모델을 통하여 연속된 벡터 데이터를 학습한다. 학습된 모델을 다양한 데이터 세트에 적용하여 행동 인식 정확도를 확인한 결과 2차원 정보만으로 3차원 정보를 이용한 기존의 알고리즘과 유사한 성능을 입증할 수 있었다.

Keywords

References

  1. C. Jung,and D. Kang,"A Recognition Algorithm of Suspicious Human Behaviors using Hidden Markov Models in an Intelligent Surveillance System, " Journal of multimedia information system, Vol.11, No.11, pp.1491-1500,Nov. 2008.
  2. TRAN, Du, et al. "Learning spatiotemporal features with 3d convolutional networks. arXiv preprint arXiv:1412.0767, 2014.
  3. LI, Wanqing, ZHANG, Zhengyou, LIU, Zicheng. "Action recognition based on a bag of 3d points". Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on. IEEE, p. 9-14.2010.
  4. HU, Jian-Fang, et al. "Jointly learning heterogeneous features for RGB-D activity recognition. " Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 5344-5352. 2015.
  5. INSAFUTDINOV, Eldar, et al. ArtTrack: "Articulated multi-person tracking in the wild," IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.
  6. Diogo Carbonera Luvizon, Hedi Tabia, David Picard, "Learning features combination for human action recognition from skeleton sequences," Pattern Recognition Letters, Volume 99, pp 13-20, ISSN 0167-8655. 2017. https://doi.org/10.1016/j.patrec.2017.02.001
  7. CHO, Kyunghyun, et al. "Learning phrase representations using RNN encoder-decoder for statistical machine translation," arXiv preprint arXiv:1406.1078, 2014.
  8. IOFFE, Sergey, SZEGEDY, Christian, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," International Conference on Machine Learning. pp. 448-456. 2015.
  9. SRIVASTAVA, Nitish, et al. Dropou, "A simple way to prevent neural networks from overfitting," Journal of machine learning research, 15.1: 1929-1958. 2014.
  10. KINGMA, Diederik; BA, Jimmy. Adam: "A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
  11. NAIR, Vinod, HINTON, Geoffrey E, "Rectified linear units improve restricted boltzmann machines," Proceedings of the 27th international conference on machine learning (ICML-10). pp. 807-814. 2010.
  12. KLAMBAUER,Günter,et al."Self-Normalizing Neural Networks," arXiv preprint arXiv: 1706.02515, 2017.
  13. CHANG, Chih-Chung, LIN, Chih-Jen. LIBSVM, "A library for support vector machines," ACM transactions on intelligent systems and technology (TIST), 2.3: 27, 2011.
  14. LI, Ruonan, ZICKLER, Todd. "Discriminative virtual views for cross-view action recognition," Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, pp. 2855-2862. 2012.
  15. LI, Binlong;CAMPS, Octavia I.;SZNAIER, Mario."Cross-view activity recognition using hankelets," Computer Vision and Pattern Recognition(CVPR),2012 IEEE Conference on. IEEE, pp.1362-1369. 2012.
  16. SADANAND, Sreemanananth, CORSO, Jason J. Action bank "A high-level representation of activity in video,". Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, pp. 1234-1241. 2012.
  17. MAJI, Subhransu, BOURDEV, Lubomir, MALIK, Jitendra. "Action recognition from a distributed representation of pose and appearance," Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, pp. 3177-3184. 2011.
  18. WANG, Jiang, et al. "Cross-view action modeling, learning and recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2649-2656. 2014.
  19. OREIFEJ, Omar, LIU, Zicheng. Hon4d "Histogram of oriented 4d normals for activity recognition from depth sequences," Computer vision and pattern recognition (CVPR), 2013 IEEE conference on. IEEE, pp. 716-723. 2013.
  20. CAO, Liangliang, et al. "Heterogeneous feature machines for visual recognition," Computer Vision, 2009 IEEE 12th International Conference on. IEEE, pp. 1095-1102. 2009.
  21. CAI, Zhuowei, et al. "Multi-view super vector for action recognition," Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. pp. 596-603. 2014.
  22. ZHANG, Yu; YEUNG, Dit Yan. "Multi-task learning in heterogeneous feature spaces," 25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference, AAAI-11/IAAI-11, San Francisco, CA, United States, 7-11 August 2011, Code 87049, Proceedings of the National Conference on Artificial Intelligence. pp. 574. 2011.
  23. S.Shin, and J.Cha, "Human Activity Recognition System Using Multimodal Sensor and Deep Learning Based on LSTM,", Transactions of the Korean Society of Mechanical Engineers-A 42(2), pp 111-121. 2018.2,
  24. S.Jo, H.Kang, "Real-time object tracking in Multi-Camera environments,", Journal of Computing Science and Engineering, 2004.10, Vol. 31, No. 2 (II),pp691-693