Large-Scale Crowd Analysis through the Use of Passive Radio Sensing Networks

Abstract

The creation of an automatic crowd estimation system capable of providing reliable, real-time estimates of human crowd sizes would be an invaluable tool for organizers of large-scale events, particularly so in the context of safety management. We describe a set of experiments in which we installed a passive Radio Frequency (RF) sensor network in different environments containing thousands of human individuals and discuss the accuracy with which the resulting measurements can be used to estimate the sizes of these crowds. Depending on the selected training approach, a median crowd estimation error of 184 people could be obtained for a large scale environment which contained 3227 people at its peak. Additionally, we look into the potential benefits of dividing one of our experimental environments into multiple subregions and open up a potentially interesting new topic of research regarding the estimation of crowd flows. Finally, we investigate the combination of our measurements with another sources of crowd-related data: sales data from drink stands within the environment. In doing so, we aim to integrate the concept of an automatic RF-based crowd estimation system into the broader domain of crowd analysis.

MAMPI-UWB—Multipath-Assisted Device-Free Localization with Magnitude and Phase Information with UWB Transceivers

“…Equation (13) calculates the probable error, i.e., half of the values of this error distribution lie inside the interval γ ≈ 2 3 σ l . The feature vectors r p r and r p o are separated by a distance of d 1 (r p o , r p r ).…”

“…In the simulation, we assume a 5 × 5 m corridor with two walls (y = 0 and y = 5) that create reflections. We place the transmitter Tx at (0, 2.5) and the receiver Rx at (5,2). This asymmetrical geometry prevents that the simulated MPCs becomes identical, leading to multiple minima in the nearest neighbor algorithm.…”

“…Typical applications for device-free localization are elderly care [ 1 ], intrusion detection, crowd estimations [ 2 ], and smart-home applications. Therefore, device-free localization systems monitor the alteration of the radio-frequency channel by accessing the above-mentioned channel measurements.…”

An IPv6 Passive‐Aware Network Routing Algorithm Based on Utility Value Combined with Deep Neural Network

“…The passive sensing network refers to a network composed of passive sensing nodes. Its nodes are not equipped with themselves or are not mainly dependent on their own power supply equipment for power supply, but support their computing, sensing, communication, and networking by obtaining energy from the environment [5,6]. Since passive nodes can maintain the operation of the network by capturing the energy of the surrounding environment, they can adapt to many application scenarios with limited energy supply and are a very promising network form in the Internet of Things.…”

Beyond Tracking in Crowd: Analyzing Crowd based on Physical Characteristics

“…Considering the challenge of tracking [11][12], we partition complete frame into smaller patches, and extract motion pattern to demonstrate the motion in each individual patch. For this purpose, our work takes into account KLT corners as consolidated features [13][14] to describe moving regions and track these features by considering optical flow method. To embed motion patterns, we develop and consider the distribution of all motion information in a patch as Gaussian distribution, and formulate parameters of Gaussian model as our motion pattern descriptor.…”