A large-scale real-life crowd steering experiment via arrow-like stimuli

Abstract

We introduce "Moving Light": an unprecedented real-life crowd steering experiment that involved about 140.000 participants among the visitors of the Glow 2017 Light Festival (Eindhoven, NL). Moving Light targets one outstanding question of paramount societal and technological importance: "can we seamlessly and systematically influence routing decisions in pedestrian crowds?" Establishing effective crowd steering methods is extremely relevant in the context of crowd management, e.g. when it comes to keeping floor usage within safety limits (e.g. during public events with high attendance) or at designated comfort levels (e.g. in leisure areas). In the Moving Light setup, visitors walking in a corridor face a choice between two symmetric exits defined by a large central obstacle. Stimuli, such as arrows, alternate at random and perturb the symmetry of the environment to bias choices. While visitors move in the experiment, they are tracked with high space and time resolution, such that the efficiency of each stimulus at steering individual routing decisions can be accurately evaluated a posteriori. In this contribution, we first describe the measurement concept in the Moving Light experiment and then we investigate quantitatively the steering capability of arrow indications.

Pedestrian orientation dynamics from high-fidelity measurements

“…1 and Ref. 6 ). Overhead depth data, not only allows privacy respectful data acquisition, but enables also accurate position measurements even in high-density conditions (for a highly-accurate algorithm leveraging on machine learning-based analyses see, e.g.…”

“…The inset reports the ratio between the standard deviation, , and the average, , of the delay as a function of . The measurements considered are 78k trajectories ( of data, all not exceeding a maximum orientation of ), acquired during the GLOW event 6 . …”

“…In ( a , b ) we report, respectively, a front and an aerial view of a data acquisition setup (similar to that in Ref. 6 ). The sensors, of which the typical view cone is reported in ( a ), are represented in ( b ) as thick segments.…”

Accurate pedestrian localization in overhead depth images via Height-Augmented HOG

“…• The Glow festival in Eindhoven during November in 2017 [7], see Figure 4, featuring a set of twelve cameras, yielding a challenge for computational performance. For instance, the clustering method becomes too computationally expensive to use on images of this size without severely compromising localization accuracy.…”

Stampnet: Unsupervised Multi-Class Object Discovery

“…We consider here a reduced depth dataset from the reallife crowd tracking experiment [22], annotated with bounding boxes (image size: 80 × 80, bounding boxes size 40 × 40. See sample on the left side of Figure 2h, which displays a pedestrian on the left side and a wall on the right side).…”