A Full-Scale Hardware Solution for Crowd Evacuation via Multiple Cameras

  • Dimitrios Portokalidis
  • Ioakeim G. Georgoudas
  • Antonios Gasteratos
  • Georgios Ch. SirakoulisEmail author


Crowd evacuation is thoroughly investigated in recent years. All efforts focus on improving safety standards of such a process. Past and latest life-threatening incidents related to evacuation procedures justify both the growing scientific interest as well as the interdisciplinary character of most research approaches. In this chapter, we describe the hardware implementation of a management system that aims at acting anticipatively against crowd congestion during evacuation. The system consists of two structural components. The first one relies on an elaborated form of the Viola et al. [55] detection and tracking algorithm, which incorporates both appearance and motion in real-time. Being supported by cameras, this algorithm realises the initialisation process. In principal, it consists of simple sum-of-pixel filters that are boosted into a strong classifier. A linear combination of these filters properly set thresholds, thus succeeding detection. The second part consists of a Cellular Automata (CA) based route estimation model. Presumable congestion in front of exits during crowd egress, leads to the prompt activation of sound and optical signals that guide pedestrians towards alternative escaping points. The CA model, as well as the tracking algorithm are implemented by means of Field Programmable Gate Array (FPGA) logic. Hardware accelerates the response of the model by exploiting the distinct feature of parallelism that CA structures inherently possess. Furthermore, implementing the model on an FPGA device takes advantage of their natural parallelism, thus reaching significant speed-ups with respect to software simulation. The incorporation of the design as a fast processing module of an embedded system dedicated to surveillance is also advantageous in terms of compactness, portability and low cost.


Field Programmable Gate Array Cellular Automaton Dynamic Scene Cellular Automaton Model Back Propagation Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Altera: Quartus II handbook version 13.1. Altera Corporation (2013).
  2. 2.
    Altshuler E, Ramos O, Nunez Y, Fernandez J, Batista-Leyva AJ, Noda C (2005) Symmetry breaking in escaping ants. Am Nat 166(6):643–649CrossRefGoogle Scholar
  3. 3.
    Bandini S, Federici ML, Vizzari G (2007) Situated cellular agents approach to crowd modeling and simulation. Cybern Syst 38:729–753CrossRefzbMATHGoogle Scholar
  4. 4.
    Girau B, Tisserand A (1996) On-line arithmetic based reprogrammable hardware implementation of multilayer perceptron back-propagation. Technical report, Ecole Normale Superieure de LyonGoogle Scholar
  5. 5.
    Bonabeau E (2002) Agent-based modeling: methods and techniques for simulating human systems. Proc Natl Acad Sci USA (PNAS) 99(3):7280–7287CrossRefGoogle Scholar
  6. 6.
    Brand M, Kettnaker V (2000) Discovery and segmentation of activities in video. IEEE Trans Pattern Anal Mach Intell 22:844–851CrossRefGoogle Scholar
  7. 7.
    Burstedde C, Klauck K, Schadschneider A, Zittartz J (2001) Simulation of pedestrian dynamics using a two-dimensional cellular automaton. Physica A 295:507–525CrossRefzbMATHGoogle Scholar
  8. 8.
    Vihas C, Georgoudas IG, Sirakoulis GC (2013) Cellular automata incorporating follow-the-leader principles to model crowd dynamics. J Cell Autom 8(5–6):333–346MathSciNetGoogle Scholar
  9. 9.
    Coifman B, Beymer D, McLauchlan P, Malik J (1998) A real-time computer vision system for vehicle tracking and traffic surveillance. Transp Res: Part C 6(4):271–288Google Scholar
  10. 10.
    Cutler R, Davis LS (2000) Robust real-time periodic motion detection, analysis, and applications. IEEE Trans Pattern Anal Machine Intell 22:781–796CrossRefGoogle Scholar
  11. 11.
    Georgoudas IG, Sirakoulis GC, Andreadis I (2007) An intelligent cellular automaton model for crowd evacuation in fire spreading conditions. In: Proceedings of the 19th IEEE international conference on tools with artificial intelligence (ICTAI 2007), vol 1, pp 36–43Google Scholar
  12. 12.
    Georgoudas IG, Kyriakos P, Sirakoulis GC, Andreadis I (2010) An fpga implemented cellular automaton crowd evacuation model inspired by the electrostatic-induced potential fields. Microprocess Microsyst 34(7–8):285–300CrossRefGoogle Scholar
  13. 13.
    Georgoudas IG, Sirakoulis GC, Andreadis I (2007) Modelling earthquake activity features using cellular automata. Math Comput Model 46(1–2):124–137CrossRefGoogle Scholar
  14. 14.
    Georgoudas IG, Sirakoulis GC, Andreadis I (2011) An anticipative crowd management system preventing clogging in exits during pedestrian evacuation processes. IEEE Syst 5(1):129–141CrossRefGoogle Scholar
  15. 15.
    Goldstone RL, Janssen MA (2005) Computational models of collective behavior. Trends Cognitive Sci 9(9):424–430CrossRefGoogle Scholar
  16. 16.
  17. 17.
    Haldera C, Madeja L, Pietrzyka M (2014) Discrete micro-scale cellular automata model for modelling phase transformation during heating of dual phase steels. Arch Civil Mech Eng 14:96–103CrossRefGoogle Scholar
  18. 18.
    Haritaoglu I, Harwood D, Davis LS (2000) W4: Real-time surveillance of people and their activities. IEEE Trans Pattern Anal Machine Intell 22(8):809–822CrossRefGoogle Scholar
  19. 19.
    Helbing D, Farkas I, Vicsek T (2000) Simulating dynamical features of escape panic. Nature 407:487–490CrossRefGoogle Scholar
  20. 20.
    Howarth RJ, Buxton H (1992) Analogical representation of space and time. Image Vis Comput 10:467–478CrossRefGoogle Scholar
  21. 21.
    Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans Syst Man Cybern - C: Appl Rev 34(3):334–352Google Scholar
  22. 22.
    Hu WHW, Tan TTT, Wang LWL, Maybank SMS (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans Syst Man Cybern C 34:334–352Google Scholar
  23. 23.
    Hughes R (2002) A continuum theory for the flow of pedestrians. Transp Res B 36:507–535Google Scholar
  24. 24.
    Kilger M (1992) A shadow handler in a video-based real-time traffic monitoring system. In: Proceedings of the IEEE workshop applications of computer vision. IEEE, Palm Springs, pp 11–18Google Scholar
  25. 25.
    Kirchner A, Klupfel H, Nishinari K, Schadschneider A, Schreckenberg M (2003) Simulation of competitive egress behavior: comparison with aircraft evacuation data. Physica A 324:689–697CrossRefzbMATHGoogle Scholar
  26. 26.
    Kuno Y, Watanabe T, Shimosakoda Y, Nakagawa S (1996) Automated detection of human for visual surveillance system. In: Proceedings of the international conference on pattern recognition, pp 865–869Google Scholar
  27. 27.
    Li J, Yang L, Zhao D (2005) Simulation of bi-direction pedestrian movement in corridor. Physica A 354:619–628CrossRefGoogle Scholar
  28. 28.
    Lo SM, Huang HC, Wang P, Yuen KK (2006) A game theory based exit selection model for evacuation. Fire Saf J 41:364–369CrossRefGoogle Scholar
  29. 29.
    Lou JG, Yang H, Hu WM, Tan TN (2002) Visual vehicle tracking using an improved ekf. In: Proceedings of the Asian conference on computer vision, pp 296–301Google Scholar
  30. 30.
    Schultz M, Lehmann S, Fricke H (2007) A discrete microscopic model for pedestrian dynamics to manage emergency situations in airport terminals. In: Waldau N, Gattermann P, Knoflacher H, Schreckenberg M (eds) Pedestrian andevacuation dynamics 2005. Springer, Berlin, pp 369–375CrossRefGoogle Scholar
  31. 31.
    Mackay M, Benhabib B (2007) A multi-camera active-vision system for dynamic form recognition. In: Proceedings of international conference on computer, information, and systems sciences, and engineering (CISSE2007)Google Scholar
  32. 32.
    Mackay M, Fenton RG, Benhabib B (2008) Time-varying-geometry object surveillance using a multi-camera active-vision system. Int J Smart Sens Intell Syst 1(3):679–704Google Scholar
  33. 33.
    Mackay M, Fenton RG, Benhabib B (2011) Multi-camera active surveillance of an articulated human form - an implementation strategy. Comput Vis Image Underst 115:1395–1413CrossRefGoogle Scholar
  34. 34.
    McKenna S, Jabri S, Duric Z, Rosenfeld A, Wechsler H (2000) Tracking groups of people. Comput Vis Image Underst 80(1):42–56CrossRefzbMATHGoogle Scholar
  35. 35.
    Mehran R (2011) Analysis of behaviors in crowd videos. Ph.D. thesis, University of Central Florida.
  36. 36.
    Meyer D, Denzler J, Niemann H (1998) Model based extraction of articulated objects in image sequences for gait analysis. In: Proceedings of the IEEE international conference on image processing, pp 78–81Google Scholar
  37. 37.
    Meyer D, Denzler J, Niemann H (1998) Model based extraction of articulated objects in image sequences for gait analysis. In: Proceedings of the IEEE international conference on image processing, pp 78–81Google Scholar
  38. 38.
    Mita T, Kaneko T, Hori O (2005) Joint haar-like features for face detection. Multimed Lab Corp Res Dev Cent Toshiba Corp 2:1619–1626Google Scholar
  39. 39.
    Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans Pattern Recognit Machine Intell 23:349–361CrossRefGoogle Scholar
  40. 40.
    Nalpantidis L, Sirakoulis GC, Gasteratos A (2011) Non-probabilistic cellular automata-enhanced stereo vision simultaneous localisation and mapping (slam). Meas Sci Technol 22(11):114027CrossRefGoogle Scholar
  41. 41.
    Orts-Escolano S, Garcia-Rodriguez J, Morell V, Cazorla M, Azorin J, Garcia-Chamizo JM (2014) Parallel computational intelligence-based multi-camera surveillance system. J Sens Actuator Netw 3:95–112CrossRefGoogle Scholar
  42. 42.
    Panagiotakis C, Tziritas G (2004) Recognition and tracking of the members of a moving human body. In: Perales FJ, Draper BA (eds) AMDO 2004, LNCS 3179, Springer, pp 86–98Google Scholar
  43. 43.
    Papers AW (2007) Video surveillance implementation using FPGAs. Altera Corporation.
  44. 44.
    Parisi D, Dorso C (2005) Microscopic dynamics of pedestrian evacuation. Physica A 354:606–618CrossRefGoogle Scholar
  45. 45.
    Recatala G, Carloni R, Melchiorri C, Sanz PJ, Cervera E, del Pobil AP (2008) Vision-based grasp tracking for planar objects. IEEE Trans Syst Man Cybern - C: Appl Rev 38(6):844–849Google Scholar
  46. 46.
    Remagnino P, Tan T, Baker K (1998) Agent orientated annotation in model based visual surveillance. In: Proceedings of the IEEE international conference on computer vision, pp 857–862Google Scholar
  47. 47.
    Rother C, Kolmogorov V, Blake A (2004) Grabcut: interactive foreground extraction using iterated graph cuts. In: Proceeding ACM SIGGRAPH ’04. ACM, pp 309–314Google Scholar
  48. 48.
    Roy A, Sural S (2009) A fuzzy interfacing system for gait recognition. In: Proceedings of the 28th north american fuzzy information processing society annual conference, pp 1–6Google Scholar
  49. 49.
    Shiwakoti N, Sarvi M, Rose G, Burd M (2011) Animal dynamics based approach for modeling pedestrian crowd egress under panic conditions. Transp Res B: Methodol 45(9):1433–1449Google Scholar
  50. 50.
    Tarabanis KA, Allen PK, Tsai RY (1995) A survey of sensor planning in computer vision. IEEE Trans Robot Autom 11(1):86–104CrossRefGoogle Scholar
  51. 51.
    Toffoli T (1984) Cam: a high-performance cellular automaton machine. Physica D 10(1–2):195–204CrossRefMathSciNetGoogle Scholar
  52. 52.
    Varas A, Cornejo M, Mainemer D, Toledo B, Rogan J, Munoz V, Valdivia JA (2007) Cellular automaton model for evacuation process with obstacles. Physica A 382:631–642Google Scholar
  53. 53.
    Velastin S, Remagnino P, (2006) Intelligent distributed video surveillance systems., IEE Computing Series, Institution of Engineering and Technology, StevenageGoogle Scholar
  54. 54.
    Viola P, Jones M (2001) Fast and robust classification using asymmetric adaboost and a detector cascade. In: Advances in Neural Information Processing System, vol 14. MIT Press, Cambridge, pp 1311–1318Google Scholar
  55. 55.
    Viola P, Jones MJ, Snow D (2003) Detecting pedestrians using patterns of motion and appearance. In: Proceedings of the IEEE international conference on computer vision, pp 734–741Google Scholar
  56. 56.
    Vlassopoulos N, Fates NA, Berry H, Girau B (2010) An fpga design for the stochastic greenberg-hastings cellular automata. In: International conference on high performance computing & simulation - HPCS, IEEE Computer Society, pp 565–574Google Scholar
  57. 57.
    Wang X, Wang S, Bi D (2009) Distributed visual-target-surveillance system in wireless sensor networks. IEEE Trans Syst Man Cybern - B: Cybern 39(5):1134–1146Google Scholar
  58. 58.
    Yuan WF, Tan KH (2007) An evacuation model using cellular automata. Phys A 384:549–66CrossRefGoogle Scholar
  59. 59.
    Zhang W, Tong R, Dong J (2009) Boosting 2-thresholded weak classifiers over scattered rectangle features for object detection. Institute of Artificial Intelligence Zhejiang University Hangzhou, pp 397–404Google Scholar
  60. 60.
    Zhao D, Yang L, Li J (2006) Exit dynamics of occupant evacuation in an emergency. Physica A 363:501–511CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Dimitrios Portokalidis
    • 1
  • Ioakeim G. Georgoudas
    • 1
  • Antonios Gasteratos
    • 2
  • Georgios Ch. Sirakoulis
    • 1
    Email author
  1. 1.Department of Electrical and Computer EngineeringDemocritus University of ThraceXanthiGreece
  2. 2.Department of Production and Management EngineeringDemocritus University of ThraceXanthiGreece

Personalised recommendations