Identification of social relation within pedestrian dyads


Autoři: Zeynep Yucel aff001;  Francesco Zanlungo aff002;  Claudio Feliciani aff003;  Adrien Gregorj aff001;  Takayuki Kanda aff002
Působiště autorů: Department of Computer Science, Okayama University, Okayama, Japan aff001;  Intelligent Robotics and Communication Laboratory, ATR, Kyoto, Japan aff002;  Research Center for Advanced Science and Technology, The University of Tokyo, Tokyo, Japan aff003;  Department of Social Informatics, Kyoto University, Kyoto, Japan aff004
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article
doi: 10.1371/journal.pone.0223656

Souhrn

This study focuses on social pedestrian groups in public spaces and makes an effort to identify the type of social relation between the group members. As a first step for this identification problem, we focus on dyads (i.e. 2 people groups). Moreover, as a mutually exclusive categorization of social relations, we consider the domain-based approach of Bugental, which precisely corresponds to social relations of colleagues, couples, friends and families, and identify each dyad with one of those relations. For this purpose, we use anonymized trajectory data and derive a set of observables thereof, namely, inter-personal distance, group velocity, velocity difference and height difference. Subsequently, we use the probability density functions (pdf) of these observables as a tool to understand the nature of the relation between pedestrians. To that end, we propose different ways of using the pdfs. Namely, we introduce a probabilistic Bayesian approach and contrast it to a functional metric one and evaluate the performance of both methods with appropriate assessment measures. This study stands out as the first attempt to automatically recognize social relation between pedestrian groups. Additionally, in doing that it uses completely anonymous data and proves that social relation is still possible to recognize with a good accuracy without invading privacy. In particular, our findings indicate that significant recognition rates can be attained for certain categories and with certain methods. Specifically, we show that a very good recognition rate is achieved in distinguishing colleagues from leisure-oriented dyads (families, couples and friends), whereas the distinction between the leisure-oriented dyads results to be inherently harder, but still possible at reasonable rates, in particular if families are restricted to parent-child groups. In general, we establish that the Bayesian method outperforms the functional metric one due, probably, to the difficulty of the latter to learn observable pdfs from individual trajectories.

Klíčová slova:

Bayesian method – Behavior – Collective human behavior – Human families – Probability density – Social networks – Social psychology – Velocity


Zdroje

1. Zanlungo F, Yücel Z, Brščić D, Kanda T, Hagita N. Intrinsic group behaviour: Dependence of pedestrian dyad dynamics on principal social and personal features. PLOS One. 2017;12(11):e0187253. doi: 10.1371/journal.pone.0187253 29095913

2. Yücel Z, Zanlungo F, Shiomi M. Walk the talk: Gestures in mobile interaction. In: International Conference on Social Robotics. Springer; 2017. p. 220–230.

3. Yücel Z, Zanlungo F, Feliciani C, Gregorj A, Kanda T. The effect of social roles on group behaviour. In: Proc. Pedestrian and Evacuation Dynamics. Springer; 2018.

4. Yücel Z, Zanlungo F, Kanda T. Gender profiling of pedestrian dyads. In: Proc. Traffic and Granular Flow, TGF 2019. Springer; 2019.

5. Moussaïd M, Perozo N, Garnier S, Helbing D, Theraulaz G. The walking behaviour of pedestrian social groups and its impact on crowd dynamics. PLOS One. 2010;5(4):e10047. doi: 10.1371/journal.pone.0010047

6. Hall E. The Hidden Dimension Garden City, NY: Doubleday; 1966.

7. Zanlungo F, Ikeda T, Kanda T. Potential for the dynamics of pedestrians in a socially interacting group. Physical Review E. 2014;89(1):012811. doi: 10.1103/PhysRevE.89.012811

8. Adrian J, Bode N, Amos M, Baratchi M, Beermann M, Boltes M, et al. A glossary for research on human crowd dynamics. Collective Dynamics. 2019;4:1–13. doi: 10.17815/CD.2019.19

9. von Krüchten C, Schadschneider A. Empirical study on social groups in pedestrian evacuation dynamics. Physica A: Statistical Mechanics and its Applications. 2017;475:129–141. doi: 10.1016/j.physa.2017.02.004

10. Shao J, Change Loy C, Wang X. Scene-independent group profiling in crowd. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition; 2014. p. 2219–2226.

11. McPhail C, Wohlstein RT. Using film to analyze pedestrian behavior. Sociological Methods & Research. 1982;10(3):347–375. doi: 10.1177/0049124182010003007

12. Schultz M, Rößger L, Fricke H, Schlag B. Group dynamic behavior and psychometric profiles as substantial driver for pedestrian dynamics. In: Pedestrian and Evacuation Dynamics 2012. Springer; 2014. p. 1097–1111.

13. Köster G, Seitz M, Treml F, Hartmann D, Klein W. On modelling the influence of group formations in a crowd. Contemporary Social Science. 2011;6(3):397–414. doi: 10.1080/21582041.2011.619867

14. Reuter V, Bergner BS, Köster G, Seitz M, Treml F, Hartmann D. On modeling groups in crowds: empirical evidence and simulation results including large groups. In: Pedestrian and Evacuation Dynamics 2012. Springer; 2014. p. 835–845.

15. Vizzari G, Manenti L, Ohtsuka K, Shimura K. An agent-based approach to pedestrian and group dynamics: experimental and real world scenarios. In: Proc. International Workshop on Agents in Traffic and Transportation; 2012. p. 1–9.

16. Cheng L, Yarlagadda R, Fookes C, Yarlagadda PK. A review of pedestrian group dynamics and methodologies in modelling pedestrian group behaviours. World Journal of Mechanical Engineering. 2014;1(1):002–013.

17. Zanlungo F, Brščić D, Kanda T. Spatial-size scaling of pedestrian groups under growing density conditions. Physical Review E. 2015;91(6):062810. doi: 10.1103/PhysRevE.91.062810

18. Zanlungo F, Kanda T. A mesoscopic model for the effect of density on pedestrian group dynamics. EPL. 2015;111(3):38007. doi: 10.1209/0295-5075/111/38007

19. Yücel Z, Zanlungo F, Shiomi M. Modeling the impact of interaction on pedestrian group motion. Advanced Robotics. 2018;32(3):137–147. doi: 10.1080/01691864.2017.1421481

20. Templeton A, Drury J, Philippides A. From mindless masses to small groups: conceptualizing collective behavior in crowd modeling. Review of General Psychology. 2015;19(3):215–229. doi: 10.1037/gpr0000032 26388685

21. Willis A, Gjersoe N, Havard C, Kerridge J, Kukla R. Human movement behaviour in urban spaces: Implications for the design and modelling of effective pedestrian environments. Environment and Planning B: Planning and Design. 2004;31(6):805–828. doi: 10.1068/b3060

22. Costa M. Interpersonal distances in group walking. Journal of Nonverbal Behavior. 2010;34(1):15–26. doi: 10.1007/s10919-009-0077-y

23. Yücel Z, Zanlungo F, Ikeda T, Miyashita T, Hagita N. Deciphering the crowd: Modeling and identification of pedestrian group motion. Sensors. 2013;13(1):875–897. doi: 10.3390/s130100875 23344382

24. Schultz M, Schulz C, Fricke H. Passenger dynamics at airport terminal environment. In: Pedestrian and Evacuation Dynamics 2008. Springer; 2010. p. 381–396.

25. Gorrini A, Vizzari G, Bandini S. Age and group-driven pedestrian behaviour: from observations to simulations. Collective Dynamics. 2016;1:1–16. doi: 10.17815/CD.2016.3

26. Bandini S, Crociani L, Gorrini A, Vizzari G. An agent-based model of pedestrian dynamics considering groups: A real world case study. In: Proc. IEEE Conference on Intelligent Transportation Systems. IEEE; 2014. p. 572–577.

27. Reafee W, Salim N, Khan A. The Power of Implicit Social Relation in Rating Prediction of Social Recommender Systems. PLOS One. 2016;11(5):1–20. doi: 10.1371/journal.pone.0154848

28. Luan J, Yao Z, Bai Y. How Social Ties Influence Consumer: Evidence from Event-Related Potentials. PLOS One. 2017;12(1):1–15. doi: 10.1371/journal.pone.0169508

29. Dibeklioglu H. Visual transformation aided contrastive learning for video-based kinship verification. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 2459–2468.

30. Wang X, Guo G, Merler M, Codella NC, Rohith M, Smith JR, et al. Leveraging multiple cues for recognizing family photos. Image and Vision Computing. 2017;58:61–75. doi: 10.1016/j.imavis.2016.07.006

31. Wang G, Gallagher A, Luo J, Forsyth D. Seeing people in social context: Recognizing people and social relationships. In: Proc. European Conference on Computer Vision. Springer; 2010. p. 169–182.

32. Wang Y, Cottrell GW. Bikers are like tobacco shops, formal dressers are like suits: Recognizing urban tribes with caffe. In: Proc. IEEE Winter Conference on Applications of Computer Vision. IEEE; 2015. p. 876–883.

33. Aguirre E, Mahr D, Grewal D, de Ruyter K, Wetzels M. Unraveling the personalization paradox: The effect of information collection and trust-building strategies on online advertisement effectiveness. Journal of Retailing. 2015;91(1):34–49. doi: 10.1016/j.jretai.2014.09.005

34. Wu Z, Wang Z, Wang Z, Jin H. Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study. In: Proc. European Conference on Computer Vision; 2018. p. 606–624.

35. Oh SJ, Benenson R, Fritz M, Schiele B. Faceless person recognition: Privacy implications in social media. In: Proc. European Conference on Computer Vision. Springer; 2016. p. 19–35.

36. Joon Oh S, Fritz M, Schiele B. Adversarial Image Perturbation for Privacy Protection–A Game Theory Perspective. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 1482–1491.

37. Kelley HH, Holmes JG, Kerr NL, Reis HT, Rusbult CE, Van Lange PA. An atlas of interpersonal situations. Cambridge University Press; 2003.

38. Haslam N. Categories of social relationship. Cognition. 1994;53(1):59–90. doi: 10.1016/0010-0277(94)90077-9 7988106

39. Fiske AP. The four elementary forms of sociality: framework for a unified theory of social relations. Psychological Review. 1992;99(4):689. doi: 10.1037/0033-295x.99.4.689 1454904

40. Clark MS, Mills J. Interpersonal attraction in exchange and communal relationships. Journal of Personality and Social Psychology. 1979;37(1):12. doi: 10.1037/0022-3514.37.1.12

41. Foa EB, Foa UG. Resource theory. In: Social Exchange. Springer; 1980. p. 77–94.

42. Bugental DB. Acquisition of the algorithms of social life: A domain-based approach. Psychological Bulletin. 2000;126(2):187. doi: 10.1037/0033-2909.126.2.187 10748640

43. Sun Q, Schiele B, Fritz M. A domain based approach to social relation recognition. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2017. p. 435–444.

44. Wang Z, Chen T, Ren J, Yu W, Cheng H, Lin L. Deep reasoning with knowledge graph for social relationship understanding. arXiv preprint arXiv:180700504. 2018.

45. Li J, Wong Y, Zhao Q, Kankanhalli MS. Visual Social Relationship Recognition. arXiv preprint arXiv:181205917. 2018.

46. Brscic D, Kanda T, Ikeda T, Miyashita T. Person tracking in large public spaces using 3-D range sensors. IEEE Transactions on Human-Machine Systems. 2013;43(6):522–534. doi: 10.1109/THMS.2013.2283945

47. ATR-IRC. Dataset: Pedestrian tracking with group annotations;. Available from: http://www.irc.atr.jp/sets/groups/.

48. Zanlungo F, Yücel Z, Brščić D, Kanda T, Hagita N. S4 Appendix. Coder reliability; 2017. https://doi.org/10.1371/journal.pone.0187253.s013.

49. Ministry of Education, Culture, Sports, Science and Technology. Official Health Statistics Survey;. Available from: http://www.mext.go.jp/component/b_menu/other/__icsFiles/afieldfile/2014/03/28/1345147_1.pdf.

50. Solera F, Calderara S, Cucchiara R. Socially constrained structural learning for groups detection in crowd. IEEE transactions on pattern analysis and machine intelligence. 2015;38(5):995–1008. doi: 10.1109/TPAMI.2015.2470658

51. Brščić D, Zanlungo F, Kanda T. Modelling of pedestrian groups and application to group recognition. In: Proc. International Convention on Information and Communication Technology, Electronics and Microelectronics. IEEE; 2017. p. 564–569.

52. Zanlungo F, Chigodo Y, Ikeda T, and Kanda T. Experimental study and modelling of pedestrian space occupation and motion pattern in a real world environment. Pedestrian and Evacuation Dynamics 2012 (pp. 289–304), Springer (2014).

53. Kreyszig E. Introductory Functional Analysis with Applications. Wiley New York; 1978.

54. Cohen S, Guibasm L. The earth mover’s distance under transformation sets. In: Proc. IEEE International Conference on Computer Vision. vol. 2. IEEE; 1999. p. 1076–1083.

55. Briani M, Cristiani E, Iacomini E. Sensitivity analysis of the LWR model for traffic forecast on large networks using Wasserstein distance. arXiv preprint arXiv:1608.00126. 2016.

56. Serratosa F, Sanroma G. A fast approximation of the earth-movers distance between multidimensional histograms. International Journal of Pattern Recognition and Artificial Intelligence. 2008;22(08):1539–1558. doi: 10.1142/S0218001408006880


Článek vyšel v časopise

PLOS One


2019 Číslo 10