Human Recognition by Appearance and Gait

This work is focused on person identification task in video sequences. For this task we propose two complementing solutions, which can be applied in different cases: gait and visual recognition. For gait recognition three kinds of features are used: anthropometric features, based on the length of the skeleton segments; relative distance features, based on relative distances between the skeleton joints; and motion features, based on the movement of a joint between two frames. Two versions of the gait recognition algorithm are presented: the first one uses the depth data alongside with the images while the other one uses only the video sequence. For visual recognition from appearance we propose a deep learning algorithm that returns binary image features. Each algorithm was tested on two datasets. Furthermore, we perform experiments on transfer from one dataset to another to check trained model transferability.

Keywords

Received

01.10.2018

Publication date

07.10.2018

Number of characters

1000

Cite Download pdf To download PDF you should sign in

GOST	Arseev S., Lutov V., Konushin A. Human Recognition by Appearance and Gait // Programmirovanie – 2018. – Issue 4 C. 97-106 [Electronic resource]. URL: http://ras.jes.su/progr/s000523100000515-0-1-en (circulation date: 05.05.2024). DOI: 10.31857/S000523100000515-0
MLA	Arseev, Sergey, Lutov, Vladimir, Konushin, Anton "Human Recognition by Appearance and Gait." Programmirovanie 4 (2018):97-106. DOI: 10.31857/S000523100000515-0
APA	Arseev S., Lutov V., Konushin A. (2018). Human Recognition by Appearance and Gait. Programmirovanie (4), pp.97-106 DOI: 10.31857/S000523100000515-0

Размещенный ниже текст является ознакомительной версией и может не соответствовать печатной

Readers community rating: votes 0

1. Kuplyakov D., Shalnov E., Konushin A. Markov chain Monte Carlo based video tracking algorithm, Program. Comput. Software, 2017, vol. 43, no. 4, pp. 224–229.

2. Shalnov E., Gringauz A., Konushin A. Estimation of the people position in the world coordinate system for video surveillance, Program. Comput. Software, 2016, vol. 42, no. 6, pp. 361–366.

3. Srikrishna Karanam, Mengran Gou, Ziyan Wu, et al. A systematic evaluation and benchmark for person reidentification: Features, metrics, and datasets, 2016, Preprint arXiv:1605.09653.

4. Man Ju, Bhanu Bir. Individual recognition using gait energy image, IEEE Trans. Pattern Anal. Mach. Intell., 2006, vol. 28, no. 2, pp. 316–322.

5. Chhatrala Risil, Jadhav Dattatray V. Gait recognition based on curvelet transform and PCANet, Pattern Recognit. Image Anal., 2017, vol. 27, no. 3, pp. 525–531.

6. Bobick A.F., Johnson A.Y. Gait recognition using static, activity-specific parameters, in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), Kauai, Hawaii, IEEE, 2001, vol. 1, pp. I-423–I-430.

7. Lee L., Grimson W., Eric L. Gait analysis for recognition and classification, IEEE Proc. of the Fifth Conf. Automatic Face and Gesture Recognition, 2002, pp. 155–162.

8. Dimitris Kastaniotis, Ilias Theodorakopoulos, Christos Theoharatos, et al. A framework for gait-based recognition using Kinect, Pattern Recognit. Lett., 2015, vol. 68, pp. 327–335.

9. Rouzbeh Sohrab, Babael Mahdi. Human gait recognition using body measures and joint angles, Int. J., 2015, vol. 6, no. 4, pp. 2305–1493.

10. Yang K., Dou Y., Lv S., et al. Relative distance features for gait recognition with Kinect, J. Visual Commun. Image Representation, 2016, vol. 39, pp. 209–217.

11. Lin K., Yang H.-F., Hsiao J.-H., et al. Deep learning of binary hash codes for fast image retrieval, in IEEE Proc. of the Conference on Computer Vision and Pattern Recognition Workshops, 2015, pp. 27–35.

12. Zheng L., Yang Y., Hauptmann A.G. Person reidentification: Past, present and future, 2016, Preprint arXiv:1610.02984.

13. Matsukawa T., Okabe T., Suzuki E., Sato Y. Hierarchical Gaussian descriptor for person reidentification, in IEEE Proc. of the Conference on Computer Vision and Pattern Recognition, IEEE, 2016, pp. 1363–1372.

14. Hermans A., Beyer L., Leibe B. In defense of the triplet loss for person re-identification, 2017, Preprint arXiv:1703.07737.

15. Zhang Y., Xiang T., Hospedales T.M., et al. Deep Mutual Learning, 2017, Preprint arXiv:1706.00384.

16. Morozov F., Konushin A. Background subtraction using a convolutional neural network, Proceedings of the 26th International Conference on Computer Graphics and Vision GraphiCon, 2016, pp. 445–447.

17. Lin W., Yang W. Structured deep hashing with convolutional neural networks for fast person reidentification, 2017, Preprint arXiv:1702.04179.

18. Breiman L. Random forests, Mach. Learn., 2001, vol. 45, no. 1, pp. 5–32.

19. Halko N., Martinsson P.G., Tropp J.A. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions, SIAM Rev., 2011, vol. 53, no. 2, pp. 217–288.

20. Liu L., Rahimpour A., Taalimi A., et al. End-to-end binary representation learning via direct binary embedding, 2017, Preprint arXiv:1703.04960.

21. Ioffe S., Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proceedings of the 32nd International Conference on Machine Learning, 2015, pp. 448–456.

22. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition, 2014, Preprint arXiv:1409.1556.

23. Zheng L., Shen L., Tian L., et al. Scalable person reidentification: A benchmark, in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1116–1124.

24. Dozat T. Incorporating Nesterov momentum into adam, 2016. http://cs229.stanford.edu/proj2015//054_report.pdf.

25. Hofmann M., Geiger J., Bachmann S., et al. The TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traits, J. Visual Commun. Image Representation, 2014, vol. 25, no. 1, pp. 195–206.

26. Andersson V., Ara’ujo R. Person identification using anthropometric and gait data from kinect sensor, in Proceedings of the Twenty-Ninth Association for the Advancement of Artificial Intelligence Conference, AAAI, 2015, pp. 425–431.

27. Li W., Zhao R., Xiao T., et al. Deepreid: Deep filter pairing neural network for person re-identification, in IEEE Proceedings of the International Conference on Computer Vision and Pattern Recognition, Columbus, 2014, pp. 152–159.

28. Wikipedia contributors, Information retrieval — Wikipedia. The Free Encyclopedia, 2017. Accessed January 18, 2018. https://en.wikipedia.org/w//index.php?title=Information_retrievaloldid=815034293.