NAPC: A Neural Algorithm for Automated Passenger Counting in Public Transport on a Privacy-Friendly Dataset
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LiDAR offers high precision in complex and crowded environments and is less susceptible to occlusion compared to infrared systems.
“LiDAR offers high precision in complex and crowded environments and is less susceptible to occlusion compared to infrared systems.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [10]
The Abstract reports approximately 96% correct passenger counts using 3D LiDAR recordings, supporting high accuracy for this particular counting system overall. But “D. CHALLENGING SEQUENCES AND RARE EVENTS” reports accuracy falling to 55% for dense flows or passenger jams. The paper does not establish that LiDAR is less susceptible to occlusion than infrared systems; page numbers are unavailable in our copy. (LLM, conf=0.88)
Experimental — accuracy not yet measuredLiDAR can differentiate between individuals and objects.
“It can also differentiate between individuals and objects.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [10]
The Abstract describes a neural system that counts passengers from 3D LiDAR depth recordings, which supports detecting people in those recordings. But “D. Challenging Sequences and Rare Events” reports that bicycles and other large objects reduced counting accuracy by about seven percentage points; the paper does not establish that LiDAR itself reliably differentiates individuals from objects. No page number is available in our copy. (LLM, conf=0.83)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 50 · Cited by 28
Research works printed but not linked: 5
- L. Boominathan, S. Kruthiventi, and R. Babu, "CrowdNet: A deep convolutional network for dense crowd counting," in Proc. 24th ACM Int. Conf. Multimedia (MM), 2016, pp. 640-644.
- D. Shen et al., "Medical image computing and computer assisted intervention-MICCAI," in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Interv., vol. 11764. Shenzhen, China, 2019.
- A. van den Oord et al., "WaveNet: A generative model for raw audio," in Proc. 9th ISCA Speech Synth. Workshop, Sunnyvale, CA, USA, Sep. 2016, p. 125. [Online]. Available: http://www.isca-speech.org/archive/SSW_2016/abstracts/ssw9_DS- 4_van_den_Oord.html
- A. L. Maas, A. Y. Hannun, and A. Y. Ng, "Rectifier nonlinearities improve neural network acoustic models," in Proc. 30th Int. Conf. Mach. Learn., 2013, pp. 1-6.
- D. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proc. 3rd Int. Conf. Learn. Represent., 2015, pp. 1-15.
- Authors
- Seidel, R., Jahn, N., Seo, S., Goerttler, T., & Obermayer, K.
- Affiliations
- Technische Universität Berlin (DE)
- Venue
- IEEE Open Journal of Intelligent Transportation Systems
- Published
- 2022
- Volume
- 3
- Pages
- 33-44
- ISSN
- 2687-7813 (ISSN-L)
- OpenAlex
- W4206062372
- Cited by
- 28
- References
- 50
- Citations by year
- 2026: 5 · 2025: 6 · 2024: 7 · 2023: 6 · 2022: 4
- FWCI
- 1.53
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Open Journal of Intelligent Transportation Systems (publishedVersion, other-oa)
- DepositOnce (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Technische Universität Berlin – Universitätsbibliothek (cc-by)
- Funders
- European Regional Development Fund (10167006)
- German Science Foundation
- Open Access Publication Fund of the Technische Universität Berlin
- 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 › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- public transport, long short-term memory networks, depth information, passenger boarding and alighting, train doors, privacy preservation, end-to-end learning, cost function design
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.
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
