The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Estimation of the Number of Passengers in a Bus Using Deep Learning
Open accessAbstract
For the development of intelligent transportation systems, if real-time information on the number of people on buses can be obtained, it will not only help transport operators to schedule buses but also improve the convenience for passengers to schedule their travel times accordingly. This study proposes a method for estimating the number of passengers on a bus. The method is based on deep learning to estimate passenger occupancy in different scenarios. Two deep learning methods are used to accomplish this: the first is a convolutional autoencoder, mainly used to extract features from crowds of passengers and to determine the number of people in a crowd; the second is the you only look once version 3 architecture, mainly for detecting the area in which head features are clearer on a bus. The results obtained by the two methods are summed to calculate the current passenger occupancy rate of the bus. To demonstrate the algorithmic performance, experiments for estimating the number of passengers at different bus times and bus stops were performed. The results indicate that the proposed system performs better than some existing methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deep learning algorithms can handle crowded environments and complex passenger behaviors, making them more robust than traditional methods.”
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 [12]
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.
Citations
Cites
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Zhang, Y., Zhou, D., Chen, S., Gao, S., & Ma, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.70 · Cited by 2,241 · cited 6×
“The authors in [30] proposed a multi-column multi-task CNN (MMCNN), which defines the input image as a single channel of 960 × 960 when training the network model image.”
BackgroundMethodInfluentialStacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
Masci, J., Meier, U., Cireşan, D., & Schmidhuber, J. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_7 · Cited by 1,955 · cited 1×
“proposed a deep neural network architecture CAE in 2011 [33].”
BackgroundCSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
Li, Y., Zhang, X., & Chen, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00120 · Cited by 1,698
Learning To Count Objects in Images
Lempitsky, V., & Zisserman, A. (2010) · Oxford University Research Archive (ORA) (University of Oxford) · Cited by 1,448
Privacy preserving crowd monitoring: Counting people without people models or tracking
Chan, A. B., Liang, Z.-S. J., & Vasconcelos, N. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587569 · Cited by 1,172
Cross-scene crowd counting via deep convolutional neural networks
Zhang, C., Li, H., Wang, X., & Yang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298684 · Cited by 1,121
Multi-source Multi-scale Counting in Extremely Dense Crowd Images
Idrees, H., Saleemi, I., Seibert, C., & Shah, M. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.329 · Cited by 1,031 · cited 1×
“In [19], the image is first divided into small blocks one by one, and multiple information sources are used to overcome the problem of overly dense and complex background environments.”
BackgroundGenerating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs
Sindagi, V. A., & Patel, V. M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.206 · Cited by 700
Feature Mining for Localised Crowd Counting
Chen, K., Loy, C. C., Gong, S., & Xiang, T. (2012) · Procedings of the British Machine Vision Conference 2012 · doi:10.5244/c.26.21 · Cited by 666
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting
Sindagi, V. A., & Patel, V. M. (2017) · 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078491 · Cited by 536
Research works printed but not linked: 1
- Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
Cited by
When Intelligent Transportation Systems Sensing Meets Edge Computing: Vision and Challenges
Zhou, X. C., Ke, R., Yang, H., & Liu, C. (2021) · Applied Sciences · doi:10.3390/app11209680 · Cited by 119
“…learning tasks, such as driver and passenger classification using smart phone data [36], K-means clustering for truck bottleneck identification using GPS data [37], estimation of the number of bus passengers using deep learning [38], and faulty detection in vehicular cyber-physical systems [39].”
MethodDriving Behavior Analysis of City Buses Based on Real-Time GNSS Traces and Road Information
Yang, Y., Yan, J., Guo, J., Kuang, Y., Yin, M., Wang, S., & Ma, C. (2021) · Sensors · doi:10.3390/s21030687 · Cited by 37
“, passenger capacity and coverage) [14], performance (i.”
BackgroundCrowd Analysis in Video Surveillance: A Review
Tomar, A., Kumar, S., & Pant, B. (2022) · 2022 International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa54658.2022.9765008 · Cited by 29
Seidel, R., Jahn, N., Seo, S., Goerttler, T., & Obermayer, K. (2022) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2021.3139393 · Cited by 28
“In contrast, [22] used CNN-autoencoder feature extraction in an algorithm estimating passenger occupancy in crowds of passengers on a bus.”
MethodPronello, C., & Garzón Ruiz, X. R. (2023) · Sensors · doi:10.3390/s23187719 · Cited by 24
A Distributed Acoustic Sensor System for Intelligent Transportation using Deep Learning
Chiang, C.-Y., Zhong, R., Jaber, M., & Hayward, P. (2024) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2300287 · Cited by 20
“Infrared sensor; 3. radar sensors CCTV is commonly used in monitoring real-time visual In [5], two CCTV cameras were deployed board of a bus to capture the sophisticated enough to deal with light exposure in blurred and obstructed areas.”
MethodRadovan, A., Mršić, L., Đambić, G., & Mihaljević, B. (2024) · Eng · doi:10.3390/eng5040172 · Cited by 24
Online Public Transit Ridership Monitoring Through Passive WiFi Sensing
Chang, W., Huang, B., Jia, B., Li, W., & Xu, G. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3257835 · Cited by 18
“Thereafter, many camera based solutions were developed, in which Hsu et al. [16] utilized a zenithal camera, and introduced a convolutional autoencoder to estimate ridership, however, it suffered from the occlusion and the poor illumination at night.”
BackgroundMethodA Real-Time Machine Learning-Based Public Transport Bus-Passenger Information System
Skhosana, M., & Ezugwu, A. E.-S. (2021) · International Journal of Sustainable Development and Planning · doi:10.18280/ijsdp.160703 · Cited by 13
Kulkarni, K., Schneider, F. A., Gowda, T., Jayasuriya, S., & Middel, A. (2022) · Frontiers in Environmental Science · doi:10.3389/fenvs.2022.866240 · Cited by 13
“YOLOv3 has a mAP (mean Average purpose) of around 57 (Redmon and Farhadi, 2018) and has been proven to be efficient in crowd places (Hsu et al., 2020).”
BackgroundDeep Learning-Based Passenger Counting System Using Surveillance Cameras
Rawat, N., Rai, A., & Agarwal, A. (2024) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets59351.2024.10426937 · Cited by 13
“Approaches that integrate the You Only Look Once (YOLO) model with other techniques are explored in [8], which combines convolutional autoencoder and YOLOv3 techniques for assessing passenger occupancy in various situations.”
MethodImpact of Posture and Social Features on Pedestrian Road-Crossing Trajectory Prediction
Kao, I.-H., & Chan, C. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3139691 · Cited by 13
Spatio-Temporal Visual Analysis for Urban Traffic Characters Based on Video Surveillance Camera Data
Zou, H., Cao, K., & Jiang, C. W. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10030177 · Cited by 10
Estimating Congestion in a Fixed-Route Bus by Using BLE Signals
Kanamitsu, Y., Taya, E., Tachibana, K., Nakamura, Y., Matsuda, Y., Suwa, H., & Yasumoto, K. (2022) · Sensors · doi:10.3390/s22030881 · Cited by 15
“Hsu et al. proposed a method to estimate the number of passengers using a deep learning algorithm based on video data obtained from two cameras installed in a bus [1].”
MethodFeng, F., Zou, Z., Liu, C., Zhou, Q., & Liu, C. (2023) · Sustainability · doi:10.3390/su15043296 · Cited by 14
“Hsu (2020) [18] combined convolutional autoencoder and YOLOv3 architecture for deep learning to obtain real-time information on passenger density on buses.”
BackgroundA lightweight bus passenger detection model based on YOLOv5
Li, X., Wu, Y., Fu, Y., Zhang, L., & Hong, R. (2023) · IET Image Processing · doi:10.1049/ipr2.12908 · Cited by 9
A comprehensive review of on-board action recognition models in public transportation systems
Meurie, C., & Lézoray, O. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128311 · Cited by 10
Fall Detection Inside An Autonomous Driving Bus: - Examination of Image Processing Algorithms-
Dakare, A. A., Wu, Y., Hashimoto, N., Kumagai, T., & Miura, T. (2023) · International Conference on Consumer Electronics · doi:10.1109/icce56470.2023.10043518 · Cited by 6
“Hsu et al. [3] apply deep learning to estimate passenger occupancy in different scenarios.”
BackgroundA Bus Crowdedness Sensing System Using Deep-Learning Based Object Detection
Huang, W., Tsuge, A., Yin, C. H. E. N., Okoshi, T., & Nakazawa, J. (2022) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2022pcp0007 · Cited by 5
“Anchor frames: [7 , 16] , [8 , 21] , [9 , 18] [10 , 24] , [11 , 21] , [12 , 26] [15 , 32] , [18 , 39] , [25 , 32] In the training process, the neural network do the prediction then compares it with the ground truth of the dataset, calculates the loss between them, and then reversely updates and…”
BackgroundMethodInfluentialSelf-citationDeep Learning Based Efficient Crowd Counting System
Al-Ghanem, W. K., Qazi, E.-U.-H., Faheem, M. H., & Quadri, S. S. A. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.048208 · Cited by 4
“Furthermore, the authors in [51] propose a deep learning-based method, utilizing a convolutional autoencoder and YOLOv3 architecture, to estimate passenger occupancy on buses in real-time, improving scheduling for transport operators and enhancing travel convenience for passengers but the proposed…”
Using BLE Signals to Estimate Objective and Subjective Crowdedness Levels on Fixed-Route Buses
Ikenaga, T., Matsuda, Y., Goto, I., Ueda, K., Suwa, H., & Yasumoto, K. (2025) · IEEE Access · doi:10.1109/access.2025.3558988 · Cited by 4
“Hsu et al. suggested a system that filters out all non-passenger objects in video data from cameras installed inside buses, using a convolutional autoencoder to count passengers [26].”
Context-Aware Multi-Scale Aggregation Network for Congested Crowd Counting
Huang, L., Shen, S., Zhu, L., Shi, Q., & Zhang, J. (2022) · Sensors · doi:10.3390/s22093233 · Cited by 5
“This research topic has been receiving much attention due to its enormous value in practical applications such as video surveillance [1,2], public safety [3,4], human behavior analysis [5], and traffic control [6].”
BackgroundDAEAR-DETR: DETR With Dual-Attention and Echo Accumulative Residual for Bus Passenger Detection
Jie, H., Liu, H., Xiao, W., & Liu, J. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3547325 · Cited by 4
Salas, E., Navarro, P., Rosique, F., Benavente, J., & Rivadeneira, A. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06954-9 · Cited by 5
Context-Aware Automated Passenger Counting Data Denoising
Cherrier, N., Rérolle, B., Graive, M., Dib, A., & Schmitt, É. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422561 · Cited by 7
“Raw sensor data is first processed online and in a technology-specific manner: computer vision techniques apply to video streams [4], [5], [6], statistical methods to time-of-flight systems [7], among various other cleaning techniques [8], [9], [10].”
MethodBoarding Alighting Counting in Different Transit Vehicles under Crowded Conditions
Rawat, N., Jeengar, K., Agarwal, A., & Kaur Chahal, R. J. (2024) · 2024 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct62155.2024.10677074 · Cited by 2
“( C) Training the model on the generic dataset, i.e., CrowdHuman, in contrast to past studies such as [6], [7], makes it more robust and adaptable to a wide range of real-world situations rather than using specific labeled images from the buses.”
BackgroundMethodAn Approach of Enhancing the Quality of Public Transportation Service in Sri Lanka using IoT
Weligamage, H. D., Wijesekara, S., Chathwara, M. D. S., Kavinda, H. G. I., Amarasena, N. C., & Gamage, N. (2022) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon56893.2022.9946624 · Cited by 2
“There are lots of previous researchers on passenger counting concept as in [11].”
BackgroundMethodIntegrating Object Detection and Wide Area Network Infrastructure for Sustainable Ferry Operation
Musaddiq, A., Mozart, D., Maleki, N., Olsson, T., & Ahlgren, F. (2023) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist59124.2023.10355690 · Cited by 3
“Using visual detection and deep learning, posed a mechanism that counts the number of passengers on a bus [13].”
BackgroundKim, K., Ahn, T.-K., & Kim, S. H. (2025) · IEEE Access · doi:10.1109/access.2025.3597708 · Cited by 1
“Liang et al. introduced a multi-scale representation technique to enhance estimation accuracy [21], and Hsu et al. suggested a convolutional autoencoder combined with YOLOv3 to improve detection performance in crowded bus environments [22].”
Sipetas, C., Roncoli, C., Chandakas, E., & Kaparias, I. (2026) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2026.105607 · Cited by 2
Vahan Samvedak: a comprehensive real-time college bus tracking and safety system
Chauhan, Y., Dhiman, S., Negi, S., Bamola, J., Pandey, K., Tripathi, N., Goyal, S., Gupta, S., & Kumar, M. (2026) · Scientific Reports · doi:10.1038/s41598-026-48862-z · Cited by 1
“However, unlike a traditional image processing approach, Hsu et al. 7 discovered that deep learning models are the most promising means of correcting flaws and improving the accuracy and reliability of passenger count.”
Grandhe, P., Ravindran, B. Y., Kumari, D. A., Thakur, E., Godala, S., & Babu, Y. R. (2026) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei68323.2026.11541631 · Cited by 1
Initial Estimation Passenger Number using YOLO-NAS
Sari, M. I., Ibnugraha, P. D., Sani, M. I., Rizal, M. F., Hanifa, F. H., & Kurniawan, A. P. (2023) · International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and Data Analytics (ICoABCD) · doi:10.1109/icoabcd59879.2023.10390917 · Cited by 1
Indoor Positioning System for Occupation Density Control
Stojanović, D., Vujović, M., & Miloradović, B. (2020) · ACADIA quarterly · doi:10.52842/conf.acadia.2020.1.102 · Cited by 1
Passenger counting in minivan-taxis using crowd-sourcing and hierarchical clustering
Adjaidoo, T.-S., Akowuah, E. K., Obeng, D. A., Dzisi, E. K. J., & Ackaah, W. (2021) · Scientific African · doi:10.1016/j.sciaf.2021.e00842
Deligiannidis, L. (2021) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci54926.2021.00064
“Or they are used to simply count people in stores, on busses, etc. [7][8][9][10].”
BackgroundHasimoto-Beltrán, R., Eufracio, O., & Calderon-Damian, B. (2022) · Intelligent systems reference library · doi:10.1007/978-3-031-06307-7_2
Predicting Passenger Occupancy of Commercial Buses Using Regression Approach of Machine Learning
Laksana, A. E., & Santoso, B. J. (2023) · International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation (ICAMIMIA) · doi:10.1109/icamimia60881.2023.10427639
“Hsu et al. in [5] propose a deep learning-based approach to estimate the number of passengers in a bus.”
BackgroundVerrell, C., Sentosa, V. V., Alam, I. N., & Wulandhari, L. A. (2024) · International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) · doi:10.1109/icimcis63449.2024.10956981
“Hsu et al. [10] proposed a method that combines YOLOv3 and CAE architecture.”
Enhancing Mobility in Smart Cities: People Counting and Characteristics Detection in Public Buses
Amirgaliyev, B., Mussabek, M., Zhumadillayeva, А., & Baishemirov, Z. D. (2025) · IEEE European Technology and Engineering Management Summit (E-TEMS) · doi:10.1109/e-tems64751.2025.11239138
“Cameras inside buses can be used for different tasks including: face mask detection [2], driver vigilance detection [3] and people counting [4], This research has been funded by the Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (Grant No.”
Vision-Based Real-Time Occupancy Mapping for Zone-Specific HVAC Optimization in Airport Buses
Pothi, N., Wanthong, I., Kosiyanurak, A., Numanoy, N., & Srisertpol, J. (2025) · International Conference on Data Science and Intelligent Systems (DSIS) · doi:10.1109/dsis67228.2025.11390659
“This enables optimized scheduling and route planning, as well as HVAC control based on actual passenger counts per trip [13].”
Metadata
- Authors
- Hsu, Y.-W., Chen, Y.-W., & Perng, J.-W.
- Affiliations
- National Sun Yat-sen University (TW)
- Corresponding author
- Perng, Jau-Woei
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2020-04-12
- Volume
- 20
- Issue
- 8
- Pages
- 2178
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7218726
- OpenAlex
- W3015764638
- Cited by
- 41
- References
- 33
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 6 · 2023: 9 · 2022: 8 · 2021: 7 · 2020: 1
- FWCI
- 2.43
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- 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
- passenger counting, convolutional autoencoder, YOLOv3, head detection, intelligent transportation systems, bus 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.
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.