Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-14931
For citation please use:
Main Title: NAPC: A Neural Algorithm for Automated Passenger Counting in Public Transport on a Privacy-Friendly Dataset
Author(s): Seidel, Robert
Jahn, Nico
Seo, Sambu
Goerttler, Thomas
Obermayer, Klaus
Type: Article
URI: https://depositonce.tu-berlin.de/handle/11303/16157
http://dx.doi.org/10.14279/depositonce-14931
License: https://creativecommons.org/licenses/by/4.0/
Abstract: Real-time load information in public transport is of high importance for both passengers and service providers. Neural algorithms have shown a high performance on various object counting tasks and play a continually growing methodological role in developing automated passenger counting systems. However, the publication of public-space video footage is often contradicted by legal and ethical considerations to protect the passengers’ privacy. This work proposes an end-to-end Long Short-Term Memory network with a problem-adapted cost function that learned to count boarding and alighting passengers on a publicly available, comprehensive dataset of approx. 13,000 manually annotated low-resolution 3D LiDAR video recordings (depth information only) from the doorways of a regional train. These depth recordings do not allow the identification of single individuals. For each door opening phase, the trained models predict the correct passenger count (ranging from 0 to 67) in approx. 96% of boarding and alighting, respectively. Repeated training with different training and validation sets confirms the independence of this result from a specific test set.
Subject(s): neural networks
laser radar
convolutional neural networks
cameras
three-dimensional displays
task analysis
feature extraction
intelligent transportation
long short-term memory
boarding and alighting passenger counting
privacy
range imaging
LiDAR
Issue Date: 2021
Date Available: 18-Jan-2022
Language Code: en
DDC Class: 006 Spezielle Computerverfahren
Sponsor/Funder: DFG, 414044773, Open Access Publizieren 2021 - 2022 / Technische Universität Berlin
Journal Title: IEEE open journal of intelligent transportation systems
Publisher: IEEE
Publisher DOI: 10.1109/OJITS.2021.3139393
EISSN: 2687-7813
TU Affiliation(s): Fak. 4 Elektrotechnik und Informatik » Inst. Softwaretechnik und Theoretische Informatik » FG Neuronale Informationsverarbeitung
Appears in Collections:Technische Universität Berlin » Publications


Item Export Bar

This item is licensed under a Creative Commons License Creative Commons