TY - JOUR
T1 - AMSense: How Mobile Sensing Platforms Capture Pedestrian/Cyclist Spatiotemporal Properties in Cities
AU - Vial, Alphonse
AU - Daamen, Winnie
AU - Ding, Aaron Yi
AU - van Arem, Bart
AU - Hoogendoorn, Serge
N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
PY - 2020
Y1 - 2020
N2 - We present a design for a novel mobile sensing system (AMSense) that uses vehicles as mobile sensing nodes in a network to capture spatiotemporal properties of pedestrians and cyclists (active modes) in urban environments. In this dynamic, multi-sensor approach, real-time data, algorithms, and models are fused to estimate presence, positions and movements of active modes with information generated by a fleet of mobile sensing platforms. AMSense offers a number of advantages over the traditional methods using stationary sensor systems or more recently crowd-sourced data from mobile and wearable devices, as it represents a scalable system that provides answers to spatiotemporal resolution, intrusiveness, and dynamic network conditions. In this paper, we motivate the need and show the potential of such a sensing paradigm, which supports a host of new research and application development, and illustrate this with a practical urban sensing example. We propose a first design, elaborate on a variety of requirements along with functional challenges, and outline the research to be performed with the generated data.
AB - We present a design for a novel mobile sensing system (AMSense) that uses vehicles as mobile sensing nodes in a network to capture spatiotemporal properties of pedestrians and cyclists (active modes) in urban environments. In this dynamic, multi-sensor approach, real-time data, algorithms, and models are fused to estimate presence, positions and movements of active modes with information generated by a fleet of mobile sensing platforms. AMSense offers a number of advantages over the traditional methods using stationary sensor systems or more recently crowd-sourced data from mobile and wearable devices, as it represents a scalable system that provides answers to spatiotemporal resolution, intrusiveness, and dynamic network conditions. In this paper, we motivate the need and show the potential of such a sensing paradigm, which supports a host of new research and application development, and illustrate this with a practical urban sensing example. We propose a first design, elaborate on a variety of requirements along with functional challenges, and outline the research to be performed with the generated data.
UR - http://www.scopus.com/inward/record.url?scp=85081291222&partnerID=8YFLogxK
U2 - 10.1109/MITS.2019.2953509
DO - 10.1109/MITS.2019.2953509
M3 - Article
SN - 1939-1390
VL - 14 (2022)
SP - 29
EP - 43
JO - IEEE Intelligent Transportation Systems Magazine
JF - IEEE Intelligent Transportation Systems Magazine
IS - 1
ER -