CoChat

The DOI matches its Crossref record; 93 of the 93 references it cites were found in a registry or an index; 25 of the 100 sources its claims cite were checked for support.

A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning

Open access

Abstract

The accurate counting of passengers in public transport systems is crucial for optimizing operations, improving service quality, and planning infrastructure. It can also contribute to reducing the number of public transport lines where a high number of vehicles is not needed in certain periods during the year, but also by increasing the number of lines where the need is increased. This paper provides a comprehensive review of current methodologies and technologies used for passenger counting, without the actual implementation of the automatic passenger counting system (APC), but with a proposal based on image processing and machine learning techniques and concepts, since it represents one of the most used approaches. The research explores various technologies and algorithms, like card swiping, infrared, weight and ultrasonic sensors, RFID, Wi-Fi, Bluetooth, LiDAR, thermos cameras, including CCTV cameras and traditional computer vision methods, and advanced deep learning approaches, highlighting their strengths and limitations. By analyzing recent advancements and case studies, this review aims to offer insights into the effectiveness, scalability, and practicality of different passenger counting solutions and offers a solution proposal. The research also analyzed the current General Data Protection Regulation (GDPR) that applies to the European Union and how it affects the use of systems like this. Future research directions and potential areas for technological innovation are also discussed to guide further developments in this field.

Overview

CoChat Summary

TL;DR

This paper reviews passenger-counting technologies for public transport and proposes an image-processing/machine-learning APC concept using CCTV cameras, YOLO v11, and COCO. It reports that CCTV with ML achieves the highest typical precision (92–99%) and recommends multi-camera, GDPR-compliant deployment with continuous retraining.

Key findings

  • Across 43 reviewed studies, CCTV cameras were the most common technology (23 works, 15 combined with ML), mostly in buses. Table 2 reports typical precision ranges: CCTV with ML 92–99%, LiDAR 95–96%, RFID 82–98%, IR 80–95%, Wi-Fi 75–94%, Bluetooth 73–77%, card swiping 70–90%, thermal cameras 70–98%, and ultrasonic sensors 88–89%.
  • The proposed solution recommends a CCTV IP camera at each door, ceiling-mounted to capture passengers’ heads, using YOLO v11 with COCO pre-training. It advises collecting several thousand to tens of thousands of images, splitting data 80/20 for training/validation, applying augmentation, and continuously retraining.
  • GDPR and EU AI Act compliance require anonymization/blurring, data minimization, DPIAs, encryption, and not storing private biometric data. Edge processing, 5G, and Wi-Fi offloading are suggested to reduce bandwidth and privacy risks.
  • A benchmark analysis cited in the paper found that APC systems often advertise accuracies of 95% or higher, but interviews with transport companies reveal a 20–30% drop in real-world accuracy.

Methods

  • Design: literature review of 43 state-of-the-art APC studies plus a solution proposal; the paper states it does not include actual implementation of an APC system.
  • Data/sample: reviewed technologies include card swiping, IR, weight sensors, RFID, Wi-Fi, Bluetooth, CCTV, LiDAR, thermal cameras, and ultrasonic sensors; Table 1 maps references to public transport vehicle type and technology used.
  • Analysis: compares technologies by typical precision, computational complexity, real-time performance, and hardware requirements; then proposes camera placement, network infrastructure, image preprocessing, ML training, and GDPR compliance practices.

Limitations

  • The paper states the proposed solution has not yet been implemented; it provides guidelines and recommendations only.
  • The paper states dataset collection is time-consuming and challenging across lighting, crowding, weather, seasons, and passenger demographics; many existing studies collected data only during the day, not at night or in rain.
  • Evident from the text: the precision ranges are compiled from heterogeneous studies and may not be directly comparable, and the paper itself notes that advertised accuracies can drop 20–30% in real conditions because verification often occurs in laboratory or simulated settings.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/eng5040172

Cites

93 of 93 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

19 Valid · 13 Not valid · 60 Not checked · 136 Own results and interpretations

57 more claims · 1 with their cited sources checked

Create a free account to see all 228 claims and to verify the 13 references still open.

See all claims — free account
  • It may state two separate claims as one. 88
  • Probably not a substantial claim. 124

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Research works printed but not linked: 3

  1. Mohammed, T., and Fujiyama, T. (2018, January 23–25). Investigating Paper Ticket Usage on London Underground’s Network. Proceedings of the 14th Conference on Advanced Systems in Public Transport (CASPT), Brisbane, Australia.
  2. Lale, 2021, Passengers Monitoring System with Infrared Sensors and Microcontroller, TURBO, VIII, 4
  3. Kim, 2022, Development of a Real-Time Automatic Passenger Counting System using Head Detection Based on Deep Learning, J. Inf. Process. Syst., 18, 428

Cited by

See all 24

Metadata

Authors
Radovan, A., Mršić, L., Đambić, G., & Mihaljević, B.
Affiliations
  • Algebra Bernays University (HR)
  • Rochester Institute of Technology (US)
Corresponding author
Radovan, Aleksander
Venue
Eng
Publisher
MDPI AG
Published
2024-12-10
Volume
5
Issue
4
Pages
3284-3315
ISSN
2673-4117 (ISSN-L)
OpenAlex
W4405234389
Cited by
24
References
87
Citations by year
2026: 13 · 2025: 10 · 2024: 1
FWCI
3.38
Type
journal article
Language
en
Open access
Locations
  • Eng—Advances in Engineering (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Civil and Structural Engineering › Urban Transport Systems Analysis
Keywords
passenger counting, public transport, automatic passenger counting, image processing, computer vision, deep learning, infrared sensors, RFID, LiDAR, thermal camera, CCTV cameras, GDPR, data privacy, vehicle scheduling

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.