Abstract
Simulating crowds requires controlling a very large number of trajectories and is usually performed using crowd motion algorithms for which appropriate parameter values need to be found. The study of the relation between parametric values for simulation techniques and the quality of the resulting trajectories has been studied either through perceptual experiments or by comparison with real crowd trajectories. In this paper, we integrate both strategies. A quality metric, QF, is proposed to abstract from reference data while capturing the most salient features that affect the perception of trajectory realism. QF weights and combines cost functions that are based on several individual, local and global properties of trajectories. These trajectory features are selected from the literature and from interviews with experts. To validate the capacity of QF to capture perceived trajectory quality, we conduct an online experiment that demonstrates the high agreement between the automatic quality score and non-expert users. To further demonstrate the usefulness of QF, we use it in a data-free parameter tuning application able to tune any parametric microscopic crowd simulation model that outputs independent trajectories for characters. The learnt parameters for the tuned crowd motion model maintain the influence of the reference data which was used to weight the terms of QF.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, A Perceptually-Validated Metric for Crowd Trajectory Quality Evaluation
- A. Alahi, K. Goel, V. Ramanathan, A. Robicquet, L. Fei-Fei, and S. Savarese. 2016. Social LSTM: Human Trajectory Prediction in Crowded Spaces. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Las Vegas, NV, USA, 961--971. https://doi.org/10.1109/CVPR.2016.110Google Scholar
- Javad Amirian, Wouter van Toll, Jean-Bernard Hayet, and Julien Pettré. 2019. Data-Driven Crowd Simulation with Generative Adversarial Networks. In Proceedings of the 32nd International Conference on Computer Animation and Social Agents (Paris, France) (CASA '19). Association for Computing Machinery, New York, NY, USA, 7--10. https://doi.org/10.1145/3328756.3328769Google Scholar
Digital Library
- Glen Berseth, Mubbasir Kapadia, Brandon Haworth, and Petros Faloutsos. 2014. SteerFit: Automated Parameter Fitting for Steering Algorithms. In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation (Copenhagen, Denmark) (SCA '14). Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, 113--122. http://dl.acm.org/citation.cfm?id=2849517.2849536Google Scholar
- Panayiotis Charalambous and Yiorgos Chrysanthou. 2014. The PAG crowd: A graph based approach for efficient data-driven crowd simulation. Computer Graphics Forum 33, 8 (2014), 95--108.Google Scholar
Digital Library
- Panayiotis Charalambous, Ioannis Karamouzas, Stephen Guy, and Yiorgos Chrysanthou. 2014. A Data-Driven Framework for Visual Crowd Analysis. Computer Graphics Forum 33 (10 2014). https://doi.org/10.1111/cgf.12472Google Scholar
- Ujjal Chattaraj, Armin Seyfried, and Partha Chakroborty. 2009. Comparison of Pedestrian Fundamental Diagram Across Cultures. Advances in Complex Systems (ACS) 12 (06 2009), 393--405. https://doi.org/10.1142/S0219525909002209Google Scholar
- Teófilo Dutra, Ricardo Marques, Joaquim Cavalcante-Neto, Creto Vidal, and Julien Pettre. 2017. Gradient-based steering for vision-based crowd simulation algorithms. Computer Graphics Forum 36 (05 2017). https://doi.org/10.1111/cgf.13130Google Scholar
- A. Gupta, J. Johnson, L. Fei-Fei, S. Savarese, and A. Alahi. 2018. Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Las Vegas, NV, USA, 2255--2264.Google Scholar
- Stephen J Guy, Jatin Chhugani, Sean Curtis, Pradeep Dubey, Ming C Lin, and Dinesh Manocha. 2010. PLEdestrians: A Least-Effort Approach to Crowd Simulation, In Eurographics/ ACM SIGGRAPH Symposium on Computer Animation. Proc. of Eurographics/ACM SIGGRAPH Symposium on Computer Animation 2010, 1, 119--128. https://doi.org/10.2312/SCA/SCA10/119-128Google Scholar
- Stephen J Guy, Jur Van Den Berg, Wenxi Liu, Rynson Lau, Ming C Lin, and Dinesh Manocha. 2012. A statistical similarity measure for aggregate crowd dynamics. ACM Transactions on Graphics 31, 6 (2012), 1--11.Google Scholar
Digital Library
- Dirk Helbing and Péter Molnár. 1995. Social force model for pedestrian dynamics. Physical Review E 51, 5 (may 1995), 4282--4286. https://doi.org/10.1103/PhysRevE.51.4282Google Scholar
Cross Ref
- Ludovic Hoyet, Anne-Hélène Olivier, Richard Kulpa, and Julien Pettre. 2016. Perceptual Effect of Shoulder Motions on Crowd Animations. ACM Transactions on Graphics 35 (07 2016), 1--10. https://doi.org/10.1145/2897824.2925931Google Scholar
- Roger L Hughes. 2003. The flow of human crowds. Annual review of fluid mechanics 35, 1 (2003), 169--182. Asja Jelić, Cecile Appert-Rolland, Samuel Lemercier, and Julien Pettre. 2012. Properties of pedestrians walking in line: Fundamental diagrams. Physical review. E, Statistical, nonlinear, and soft matter physics 85 (03 2012), 036111. https://doi.org/10.1103/PhysRevE.85.036111Google Scholar
- Mubbasir Kapadia, Shawn Singh, Brian Allen, Glenn Reinman, and Petros Faloutsos. 2009. SteerBug: An Interactive Framework for Specifying and Detecting Steering Behaviors. In Proceedings of the 2009 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (New Orleans, Louisiana) (SCA '09). Association for Computing Machinery, New York, NY, USA, 209--216. https://doi.org/10.1145/1599470.1599497Google Scholar
Digital Library
- Mubbasir Kapadia, Matt Wang, Shawn Singh, Glenn Reinman, and Petros Faloutsos. 2011. Scenario Space: Characterizing Coverage, Quality, and Failure of Steering Algorithms. In Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (Vancouver, British Columbia, Canada) (SCA '11). Association for Computing Machinery, New York, NY, USA, 53--62. https://doi.org/10.1145/2019406.2019414Google Scholar
Digital Library
- Ioannis Karamouzas, Peter Heil, Pascal Beek, and Mark H. Overmars. 2009. A Predictive Collision Avoidance Model for Pedestrian Simulation. In Proceedings of the 2nd International Workshop on Motion in Games (Zeist, The Netherlands) (MIG '09). Springer-Verlag, Berlin, Heidelberg, 41--52. https://doi.org/10.1007/978-3-642-10347-6_4Google Scholar
- Ioannis Karamouzas, Brian Skinner, and Stephen J. Guy. 2014. Universal Power Law Governing Pedestrian Interactions. Physical Review Letters 113, 23 (dec 2014), 238701. https://doi.org/10.1103/PhysRevLett.113.238701Google Scholar
Cross Ref
- Richard Kulpa, Anne-Hélène Olivier, Jan Ondřej, and Julien Pettré. 2011. Imperceptible Relaxation of Collision Avoidance Constraints in Virtual Crowds. ACM Trans. Graph. 30, 6 (Dec. 2011), 1--10. https://doi.org/10.1145/2070781.2024172Google Scholar
Digital Library
- Alon Lerner, Yiorgos Chrysanthou, and Dani Lischinski. 2007. Crowds by Example. Computer Graphics Forum 26, 3 (2007), 655--664. https://doi.org/10.1111/j.1467-8659.2007.01089.x arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1467-8659.2007.01089.xGoogle Scholar
Cross Ref
- Rachel McDonnell, Michéal Larkin, Simon Dobbyn, Steven Collins, and Carol O'Sullivan. 2008. Clone attack! Perception of crowd variety. ACM Transactions on Graphics 27 (08 2008). https://doi.org/10.1145/1360612.1360625Google Scholar
- Rachel McDonnell, Michéal Larkin, Benjamin Hernandez, Isaac Rudomin, and Carol O'Sullivan. 2009. Eye-catching Crowds: Saliency based Selective Variation. ACM Transactions on Graphics 28 (08 2009). https://doi.org/10.1145/1531326.1531361Google Scholar
Digital Library
- Jan Ondřej, Julien Pettré, Anne-Hélène Olivier, and Stéphane Donikian. 2010. A synthetic-vision based steering approach for crowd simulation. ACM Transactions on Graphics 29, 4 (2010), 123.Google Scholar
Digital Library
- Sébastien Paris, Julien Pettre, and Stéphane Donikian. 2007. Pedestrian Reactive Navigation for Crowd Simulation: a Predictive Approach Abstract. Comput. Graph. Forum 26 (09 2007), 665--674. https://doi.org/10.1111/j.1467-8659.2007.01090.xGoogle Scholar
- Craig W. Reynolds. 1987. Flocks, Herds and Schools: A Distributed Behavioral Model. SIGGRAPH Comput. Graph. 21, 4 (Aug. 1987), 25--34. https://doi.org/10.1145/37402.37406Google Scholar
Digital Library
- Adrien Treuille, Seth Cooper, and Zoran Popović. 2006. Continuum Crowds. ACM Trans. Graph. 25, 3 (July 2006), 1160--1168. https://doi.org/10.1145/1141911.1142008Google Scholar
Digital Library
- A. Turnwald, S. Eger, and D. Wollherr. 2015. Investigating similarity measures for locomotor trajectories based on the human perception of differences in motions. In 2015 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO). 2015 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), Lyon, France, 1--6. https://doi.org/10.1109/ARSO.2015.7428196Google Scholar
- J. van den Berg, Ming Lin, and D. Manocha. 2008. Reciprocal Velocity Obstacles for real-time multi-agent navigation. In 2008 IEEE International Conference on Robotics and Automation. IEEE, New York, NY, 1928--1935. https://doi.org/10.1109/ROBOT.2008.4543489Google Scholar
- D. Wolinski, S. J. Guy, A.-H. Olivier, M. Lin, D. Manocha, and J. Pettré. 2014. Parameter Estimation and Comparative Evaluation of Crowd Simulations. Comput. Graph. Forum 33, 2 (May 2014), 303--312. https://doi.org/10.1111/cgf.12328Google Scholar
Index Terms
A Perceptually-Validated Metric for Crowd Trajectory Quality Evaluation
Recommendations
Trajectory Query Based on Trajectory Segments with Activities
UrbanGIS'17: Proceedings of the 3rd ACM SIGSPATIAL Workshop on Smart Cities and Urban AnalyticsSearching trajectories with activities has attracted much attention in the last decade. Existing studies tend to find trajectories with activities matched to the required keywords. However, returned trajectories may have a satisfying textual matching ...
Private Trajectory Data Publication for Trajectory Classification
Web Information Systems and ApplicationsAbstractTrajectory classification (TC), i.e., predicting the class labels of moving objects based on their trajectories and other features, has many important real-world applications. Private trajectory data publication is to anonymize trajectory data, ...
A Perceptually Relevant MSE-Based Image Quality Metric
Image quality metrics (IQMs), such as the mean squared error (MSE) and the structural similarity index (SSIM), are quantitative measures to approximate perceived visual quality. In this paper, through analyzing the relationship between the MSE and the ...






Comments