Group and Single Pedestrian Behavior in Crowd Dynamics

Ouyang

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

et al. 2019

453

282

In crowd scenarios, reliable trajectory prediction of pedestrians requires insightful understanding of their social behaviors. These behaviors have been well investigated by plenty of studies, while it is hard to be fully expressed by hand-craft rules. Recent studies based on LSTM networks have shown great ability to learn social behaviors. However, many of these methods rely on previous neighboring hidden states but ignore the important current intention of the neighbors. In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism. To effectively extract the social effect of neighbors, we further introduce a social-aware information selection mechanism consisting of an element-wise motion gate and a pedestrian-wise attention to select useful message from neighboring pedestrians. Experimental results on two public datasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed SR-LSTM and we achieves state-of-the-art results.

Section: Introductionmentioning

confidence: 99%

SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory Prediction

Ouyang

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

et al. 2019

453

282

J of Advced Transportation

“…BACKGROUND From a behavioural understanding and modelling point of view, pedestrian crowd flow has been considered in the literature from different angles. Some studies have been dedicated to the understanding of certain phenomena that emerge from crowd collective motion (such as panic, stampede, fasteris-slower effect; stop-and-go and social group effect to name a few) [3,[10][11][12][13]. Some other studies, however, including the current work, have focused on the behaviour of individual pedestrians in a crowd.…”

Section: Introductionmentioning

confidence: 99%

Pedestrian crowd tactical‐level decision making during emergency evacuations

Haghani

Sarvi

2016

Self Cite

This paper investigates pedestrian crowd tactical-level decision making during emergency evacuations. Of particular interest is crowd exit-choice behaviour. Two sources of stated choice data are collected and combined. One data set is derived from an experiment linked to a real-life exit choice experience of participants (in a non-evacuation setting). We examine aspects that have often been taken for granted in the literature in connection with egress behaviour of crowds during emergencies. We quantify evacuees' trade-off between "distance", "density", "exit visibility" and "directional density" as well as the interactive effect between exit visibility and tendency to follow others. A comprehensive random-utility analysis is conducted ranging from traditionally practiced models to the state-of-the-practice methods such as random-coefficient nested logit. Our findings suggest that (i) unless evacuees face certain levels of uncertainty in the escape environment; flows of crowd are unlikely to be followed. Otherwise, most evacuees perceive other individuals as potential sources of congestion and extra delay (generalisation to situations where crowd is completely unfamiliar with the egress geometry, however, may require careful scrutiny). (ii) Evacuees mostly prefer visible exits over the exits whose congestion level is unknown to them (i.e. the tendency to minimise ambiguity). (iii) The presence of attribute uncertainty (e.g. exit visibility) significantly changes the impact of observing decisions of others on each individual choice maker. We also found out that (iv) spatial distribution of exits has a significant influence on evacuees' decisions (presenting itself in the form of violating the IIA assumption). (v) The marginal weights that different individuals place upon attributes of exits are significantly heterogeneous. (vi) There is meaningful correlation between certain utility weights of individual evacuees. These behavioural findings can provide significant behavioural insight essential for safe evacuation planning and accurate forecast of evacuees' behaviour.All other model estimation results were obtained from NLOGIT 5.

“…There has been an awful lot of effort towards the former type of decisions in the modern literature. A number of data provision approaches and methods have been employed ranging from experiments with stressed insects (typically, ants) [15–21] or mice [15, 22, 23] to controlled laboratory experiments [24–26] and video-analysis of pedestrian movements in naturally-occurring environments (although not necessarily during evacuations) [27, 28]. Also, a number of influential theoretical works have proposed adequately-defined modeling frameworks validated or calibrated based upon empirical observations [29, 30].…”

Section: Introductionmentioning

confidence: 99%

How Simple Hypothetical-Choice Experiments Can Be Utilized to Learn Humans’ Navigational Escape Decisions in Emergencies

et al. 2016

Self Cite

How humans resolve non-trivial tradeoffs in their navigational choices between the social interactions (e.g., the presence and movements of others) and the physical factors (e.g., spatial distances, route visibility) when escaping from threats in crowded confined spaces? The answer to this question has major implications for the planning of evacuations and the safety of mass gatherings as well as the design of built environments. Due to the challenges of collecting behavioral data from naturally-occurring evacuation settings, laboratory-based virtual-evacuation experiments have been practiced in a number of studies. This class of experiments faces the traditional question of contextual bias and generalizability: How reliably can we infer humans’ behavior from decisions made in hypothetical settings? Here, we address these questions by making a novel link between two different forms of empirical observations. We conduct hypothetical emergency exit-choice experiments framed as simple pictures, and then mimic those hypothetical scenarios in more realistic fashions through staging mock evacuation trials with actual crowds. Econometric choice models are estimated based on the observations made in both experimental contexts. The models are contrasted with each other from a number of perspectives including their predictions as well as the sign, magnitude, statistical significance, person-to-person variations (reflecting individuals’ perception/preference differences) and the scale (reflecting context-dependent decision randomness) of their inferred parameters. Results reveal a surprising degree of resemblance between the models derived from the two contexts. Most strikingly, they produce fairly similar prediction probabilities whose differences average less than 10%. There is also unexpected consensus between the inferences derived from both experimental sources on many aspects of people’s behavior notably in terms of the perception of social interactions. Results show that we could have elicited peoples’ escape strategies with fair precision without observing them in action (i.e., simply by using only hypothetical-choice data as an inexpensive, practical and non-invasive experimental technique in this context). As a broader application, this offers promising evidence as to the potential applicability of the hypothetical-decision experiments to other decision contexts (at least for non-financial decisions) when field or real-world data is prohibitively unavailable. As a practical application, the behavioral insights inferred from our observations (reflected in the estimated parameters) can improve how accurately we predict the movement patterns of human crowds in emergency scenarios arisen in complex spaces. Fully-generic-in-parameters, our proposed models can even be directly introduced to a broad range of crowd simulation software to replicate navigation decision making of evacuees.