Passenger Counting Research Articles

IABACUS: A Wi-Fi-Based Automatic Bus Passenger Counting System

Since the early stages of the Internet-of-Things (IoT), one of the application scenarios that have been affected the most by this new paradigm is mobility. Smart Cities have greatly benefited from the awareness of some people’s habits to develop efficient mobility services. In particular, knowing how people use public transportation services and move throughout urban infrastructure is crucial in several areas, among which the most prominent are tourism and transportation. Indeed, especially for Public Transportation Companies (PTCs), long- and short-term planning of the transit network requires having a thorough knowledge of the flows of passengers in and out vehicles. Thanks to the ubiquitous presence of Internet connections, this knowledge can be easily enabled by sensors deployed on board of public transport vehicles. In this paper, a Wi-Fi-based Automatic Bus pAssenger CoUnting System, named iABACUS, is presented. The objective of iABACUS is to observe and analyze urban mobility by tracking passengers throughout their journey on public transportation vehicles, without the need for them to take any action. Test results proves that iABACUS efficiently detects the number of devices with an active Wi-Fi interface, with an accuracy of 100% in the static case and almost 94% in the dynamic case. In the latter case, there is a random error that only appears when two bus stops are very close to each other.

Investigating the Impact of Dwell Time on the Reliability of Urban Light Rail Operations

The present study investigates the determinants of vehicle dwell time at stations in urban light rail networks. Using data collected from an on-board automatic passenger counting system of the tramway network of the French city of Nantes over a long period, the study performs graphical and statistical analyses enabling the identification of cause-and-effect relationships of a number of attributes on the dwell time and its reliability. The results confirm the significance of the boarding and alighting passenger volumes, as well as of the on-board passenger loading, on the dwell time. Additional effects on dwell time are found from the vehicle type (low- or high-floor), the time of day (peak, off-peak, inter-peak) and the location of the station (city centre, proximity to points of interest). Also, it is found that operations are not symmetrical, and dwell times tend to be higher in one direction than the other of the same line. Finally, the results suggest that dwell time reliability is lower for stations located further from the starting terminal, or for stations located in the city centre.

Towards Better Railway Service: Passengers Counting in Railway Compartment

Counting passengers in railway compartments is an essential problem for improving service quality, user experience, public security, and disaster relief in the railway system. Considering many limitations in the compartment, the infrared sensor, 3D camera, etc. are not practical in this scene. Due to the flexibility and lower cost, solutions with standard cameras attract much attention in real applications. However, since the problem with scale variation in the narrow space is different from universal detection or counting problems, the specific benchmark of dataset and methods should be provided and proposed for this task. In this paper, we provide a passenger counting dataset. Relying on this dataset, we propose a passenger counting method. The solution contains a motion supervised multi-scale representation method which provides proposals against scale variation, a spatially-temporally enhanced counting which provides precise counting numbers, and a partial proposal method which conducts methods to be utilized in reality. With the proposed solution, the passengers counting task is solved in higher accuracy and practicable in the compartment environment. In experiments, the results show that all the modules in our solution are useful and efficient, and our method outperforms in comparison with others in the compartment scene.

PASSENGER DETECTION AND COUNTING FOR PUBLIC TRANSPORT SYSTEM

Implementing accurate and reliable passenger detection and counting system is an important task for the correct distribution of available transport system. The aim of this paper is to develop an accurate computer vision-based system to track and count passengers. The proposed passenger detection system incorporates the ideas of well-established detection techniques and is optimally customised for both indoor and outdoor scenarios. The candidate foreground regions (inside an image) are extracted in the proposed method and are described using the histograms of oriented gradient descriptor. These features are trained and tested using support vector machine classifier and the detected passengers are tracked using a filter. The proposed counting system is used to count passengers automatically when they pass through a virtual line of interest. Accuracies ranging 91.2 percent to 86.24 percent were found for passenger detection using the proposed passenger detection and counting system whereas relative counting errors varied ten percent to thirteen percent.

Dwell Time Estimation Using Real-Time Train Operation and Smart Card-Based Passenger Data: A Case Study in Seoul, South Korea

Dwell time is a critical factor in constructing and adjusting railway timetables for efficient and accurate operation of railways. This paper develops dwell time estimation models for a Shinbundang line (S line) in Seoul, South Korea using support vector regression (SVR), multiple linear regression (MLR), and random forest (RF) techniques utilizing archived real-time metro operation data along with smart card-based passenger information. In the first phase of this research, the collected data are processed to extract boarding and alighting passenger counts and observed dwell times of each train at all stations of the S line under the current operational environment. In the second phase, we develop SVR, MLR, and RF-based dwell time estimation models. It is found that the SVR-based model successfully estimates the dwell times within 10 s of differences for 84.4% of observed data. The results of this paper are especially beneficial for autonomous railway operations that need constructing and maintaining dynamic railway timetables that require reliable dwell time predictions in real-time.

Impacts of COVID-19 on Public Transport Ridership in Sweden: Analysis of Ticket Validations, Sales and Passenger Counts

The paper analyses the impacts of COVID-19 on daily public transport ridership in Sweden during spring 2020, in particular the three most populated regions Stockholm, Västra Götaland and Skåne. The analysis is based on ticket validations, sales and passenger counts data. Public transport ridership has been hit particularly severely compared with other transport modes. Of the three regions, the decrease in ridership was the largest in Stockholm (ca 60 %) and the smallest in Västra Götaland (ca. 40 %). The reduction stems primarily from a lower number of active public transport travellers. Data from both Stockholm and Västra Götaland show that travellers switched from 30-day period tickets to single tickets and travel funds, while the use and the sales of short period tickets, used predominantly by tourists and other short-term visitors, dropped to almost zero. One-year period tickets and school tickets increased from mid-April, which could indicate that the travellers using these tickets are particularly captive to the public transport system. Comparison with data from international mobility service providers shows that proxy indicators based on human proximity to public transport stations and travel planner queries have overestimated the recovery of public transport ridership during the months following the outbreak. Collaborative effort is required to put the results in the international context.

Public Transport Occupancy Estimation using WLAN Probing and Mathematical Modeling

The rapid urbanization and consequent metropolization of cities are phenomena present in many countries around the World. This increment in urban population causes changes in personal relationships and in the physical structure of cities. Among the transformations caused by metropolization, the most noteworthy are the changes in urban mobility systems. In emerging countries, the problems generated by this situation are exacerbated, since the social, environmental and, mainly, economic characteristics make the solution of problems related to urban transportation very difficult. As consequences, it is common to have daily commutes happening mostly by road transport, absence of effective public policies and poor transport data acquisition. Common ways to achieve quality in public transportation systems are to estimate the public transport occupancy (PTO) rate and the origin-destination matrix for a given area. This paper presents a formulation and study for the use of a low cost and reduced computational complexity system, capable of counting in real time the amount of passengers inside a public transportation unit (bus or metro composition). This system performs passenger counting through users’ smartphones electronic fingerprints and uses a mathematical model to adjust the acquired raw values. The applicability of this approach is demonstrated through case studies carried out in 3 different bus lines in the city of Belo Horizonte, Brazil, as an alternative to collect field data for the management of public transportation. It is demonstrated that the suggested system presents good accuracy and is a reduced complexity alternative for the estimation of PTO in emerging countries.

An objective model for collaborative flight scheduling in a single mega-hub network

ABSTRACTSingle mega-hub (SMH) airports are among the highest passenger volume airports in the world. Eight operational features that distinguish an SMH airport are identified, including collaborative flight scheduling between the airline and airport. This paper develops an objective function to direct collaborative flight scheduling. Three cost objectives are modeled, each of which focusses on a specific variable cost to the airport: passenger waiting time, passenger volume in the terminal, and ground activity imbalance. The scheduling objective is modeled as a function of (i) waiting time for each passenger, (ii) passenger count in the airport terminal, and (iii) the ground activity peak deviation from the balanced rate. Model application is demonstrated on the schedule of an airline operating 184 daily departures from a SMH. Results show the model can be used to reduce the airport’s variable costs. Rescheduling departure times for 6.5% of flights generated a 2.8% cost reduction.

Bus passenger counts using Wi-Fi signals: some cautionary findings

Analisa-se a viabilidade de pesquisas sobre usuários de ônibus com base na detecção de endereços MAC WiFi de dispositivos portáteis. A motivação para o estudo decorre da aparente contradição entre casos de sucesso publicados na literatura e resultados de experimentos de campo que realizamos. Requisitos para identificação adequada de passageiros de ônibus são usados como base para avaliar as capacidades do hardware e software de detecção comumente disponíveis. Mais especificamente, os intervalos de tempo decorridos entre as detecções do mesmo dispositivo são tomados como requisito para a determinação do estado do portador do dispositivo e, portanto, a identificação deste como passageiro. Por exemplo, ao realizar pesquisas de embarque e desembarque com equipamentos de detecção instalados a bordo, é necessário que várias detecções ocorram logo após o embarque do passageiro e antes do desembarque, permitindo assim uma estimativa precisa da origem e destino da viagem. Resultados experimentais em ensaios controlados e não controlados indicam que os componentes disponíveis no mercado com software de código aberto podem não fornecer detecções bem-sucedidas. No experimento controlado, encontramos tempos de 40 s para a primeira detecção de 86% dos dispositivos e uma média de 80 s para a segunda detecção de dispositivos. Para o experimento não controlado de viagens em ônibus com carregamento médio, foram encontradas diferenças significativas entre as contagens manuais e os dispositivos detectados. Como resultado dessas observações empíricas, recomenda-se uma avaliação cuidadosa dos esquemas de detecção existentes usados nas pesquisas de número de passageiros.

Network–wide prediction of public transportation ridership using spatio–temporal link–level information

Public transportation is a key element to vivid city life. Understanding the dynamics and driving forces of public transportation ridership can be a very rewarding task. It is, however, a highly complex construct. In this research, we focus on a spatial viewpoint, which has seen little attention: the link level. It represents the trip of a vehicle between directly connected stations. Additionally, we put emphasis on the impact of exogenous events. In order to assess their spatio–temporal influences, a temporal resolution of 30 min complements the spatial link level. Ridership data for trams and buses is provided by Stadtwerke München (SWM), which is the operator of the public transportation network in Munich, Germany, including 82 bus and 17 tram lines. About 30% of trams and 50% of buses are equipped with automatic passenger counting sensors, which capture boarding and alighting at each individual station. The equipped vehicles are strategically placed by SWM to obtain a meaningful view on the whole system. The raw sensor data is cleaned and sanitized. The data we are using spans a 4–year period (2014–2017). Following a pre–processing step, ∼59.79% of the data is considered, which equates to ∼97 million observations. There are 693 tram links and 2944 bus links, which makes 3637 links in total. We distinguish the analysis in ridership prediction and inference. For prediction, we specify one model functional form and build this model for each link, using 5–fold cross–validation to avoid overfitting. We employ decision trees, combining them with bagging and boosting. We then perform inference, i.e. attempt to understand the relationship between the variables that emerged in the predictive models. Ridership is assessed for each link separately and visualized together in order to construct network views and maps. Conclusions are drawn, and recommendations for future research are formulated.

Passenger flow counting in buses based on deep learning using surveillance video

An efficient traffic management system is crucial for public transportation. If the passenger flow can be detected accurately and instantaneously, the routes and schedules for public transportation can be effectively improved. However, previous research identified many challenges in passenger counting, such as messy image background, variations in lighting, and occlusions. In this paper, we propose a passenger flow counting model for buses, based on deep learning. First, we design a straightforward way to understand the opening state of the door. Next, a single shot multibox detector is used to learn the features of passengers and detect them. Finally, a particle filter with a three-step cascaded data association scheme is used for passenger tracking. To demonstrate the performance of the proposed algorithm, surveillance videos of three different situations, i.e., day, night, and a rainy day, are selected. Additionally, to make the system applicable to real cases, a few special scenes such as different objects worn by the passengers, passenger occlusions, and dense crowds, are considered. According to the experimental results, our method exhibits better performance than some existing methods.

Robust Network-Wide Bus Scheduling With Transfer Synchronizations

Travel time and demand disturbances lead to unreliable bus operations and missed passenger transfers. This study formulates the multi-line synchronization problem as a robust min(i)max problem that considers the fluctuations of the travel and dwell times of bus trips. Given the infeasibility of the multi-line synchronization problem in extreme cases of travel/dwell time disturbances, we introduce a flexible problem formulation that incorporates the constraint violations into the objective function. To produce a robust schedule, the dispatching times of trips are our design variables and the travel and dwell time fluctuations are the environmental variables which have an adversarial role in our minimax problem. We validate our approach in the bus network of The Hague using 1 month of actual vehicle location and passenger counting data. There, we demonstrate the potential improvement in terms of service regularity and increased synchronizations in common case and extreme case conditions.

Counting crowds using a scale-distribution-aware network and adaptive human-shaped kernel

Intelligent bus system plays a key role in the modern smart city. The number of passengers in the buses or at the stations is necessary for making an optimal scheduling policy of public buses. We develop a crowd counting algorithm to provide the counting information for a bus dispatch system in a human–machine system. In consideration of the challenges (e.g., pedestrian occlusions, non-uniform crowd distributions, and scale variations) existed in hand-crafted features based crowd counting, a scale-distribution-aware multi-column convolutional neural network (SDA-MCNN) is presented to count crowds by summing up the output (denoted as the density map) of the SDA-MCNN. The SDA-MCNN is robust to scale variations by processing a crowd image with multiple convolutional neural network (CNN) columns and minimizing the per-scale loss. A weighted Euclidean loss is proposed to handle non-uniform crowd distributions. The loss can increase activations in dense regions and restrain activations in backgrounds. A new approach to estimate perspective maps of dense crowds is put forward to offer necessary information for generating density maps with human-shaped kernels. Evaluations on benchmarks are performed with other state-of-the-art counting approaches using deep neural networks. Comparative results verify the accuracy of our counting approach in challenging crowds. Evaluations on the real world BUS data reveal the accuracy of the proposed approach in counting passengers in spite of the complex environment.

A fast hybrid computer vision technique for real-time embedded bus passenger flow calculation through camera

Bus passenger flow calculation system is a critical part of the smart public transportation framework. Bus passenger flow information can help to make data statistics report of the passenger at a bus station which can be used by public transport operator to evaluate the quality of the transportation. Statistics report of crowded passengers in the bus station help managers to understand the bus transit operations, can provide the database for the intelligent transportation scheduling, help to provide more and better services for passengers, overall data statistics of passengers has important practical significance to improve public transport environment. This paper presents a passenger counting algorithm based on hybrid machine learning approach. In the first step, an advanced method is used to extract the Histogram of oriented gradients (HOG) feature of passenger’s heads. Classification of head features is done by using support vector machine (SVM) as a classifier for the liner model. Heads are detected successfully after performing all steps. In next step Kanade-Lucas-Tomasi (KLT) is used to reality head tracking, the multiple target tracking is achieved and the head motion trajectory of passenger target is captured stably. At last, the trajectory is analyzed and the automatic counting of bus passenger flow is realized. In the last step, the proposed algorithm is move to embedded system for practical implementation. In this paper, the algorithm intends to use ADSP-BF609 embedded platform for transplantation. The experimental results demonstrate that the statistical accuracy of the proposed algorithm is enhanced successfully; especially during the daytime with the good illustration, the effective counting of the passenger flow is achieved and the inward and outward passenger counting can be realized. In this paper three feature extraction models are used namely local binary patterns, histograms of oriented gradients and binarized statistical image in order to get accurate features. Furthermore, three common classification techniques including naive bayes classifier, boosted tress and support vector machines are used for fine classification of extracted vectors obtained from different features extractors model. 94.50% accuracy is achieved when support vector machine (SVM) classifies the features extracted using Histogram of oriented gradients (HOG). SVM surpasses the accuracy obtained by Boosted tree namely 81.30% using Histogram of oriented gradients (HOG) features.

GIS-based transit trip allocation methods converting stop-level boarding and alighting trips into TAZ trips

ABSTRACTThis study introduces a framework to improve the utilization of new data sources such as automated vehicle location (AVL) and automated passenger counting (APC) systems in transit ridership forecasting models. The direct application of AVL/APC data to travel forecasting requires an important intermediary step that links stops and activities – boarding and alighting – to the actual locations (at the traffic analysis zone (TAZ) level) that generated/attracted these trips. GIS-based transit trip allocation methods are developed with a focus on considering the case when the access shed spans multiple TAZs. The proposed methods improve practical applicability with easily obtained data. The performance of the proposed allocation methods is further evaluated using transit on-board survey data. The results show that the methods can effectively handle various conditions, particularly for major activity generators. The average errors between observed data and the proposed method are about 8% for alighting trips and 18% for boarding trips.

Artificial Neural Networks for Forecasting Passenger Flows on Metro Lines.

Forecasting user flows on transportation networks is a fundamental task for Intelligent Transport Systems (ITSs). Indeed, most control and management strategies on transportation systems are based on the knowledge of user flows. For implementing ITS strategies, the forecast of user flows on some network links obtained as a function of user flows on other links (for instance, where data are available in real time with sensors) may provide a significant contribution. In this paper, we propose the use of Artificial Neural Networks (ANNs) for forecasting metro onboard passenger flows as a function of passenger counts at station turnstiles. We assume that metro station turnstiles record the number of passengers entering by means of an automatic counting system and that these data are available every few minutes (temporal aggregation); the objective is to estimate onboard passengers on each track section of the line (i.e., between two successive stations) as a function of turnstile data collected in the previous periods. The choice of the period length may depend on service schedules. Artificial Neural Networks are trained by using simulation data obtained with a dynamic loading procedure of the rail line. The proposed approach is tested on a real-scale case: Line 1 of the Naples metro system (Italy). Numerical results show that the proposed approach is able to forecast the flows on metro sections with satisfactory precision.

Low-cost deployment proposal to urban mobility in smart cities

Rational use of cars in smart cities can represent an economical and cheaper way to decrease the quantity of cars on the roads to better the life quality of the populations. This paper presents a low-cost deployment proposal called “URCa project” to reach these goals and proposes a paradigm change by sharing the cars considering some logistic aspects including car ride mechanism. Technical feasibility to deploy this solution was checked by means of a proof of concept. The concept was proven by passenger counting and license plate that are essential information in this solution were obtained taking photographs, applying two types of recognition algorithms and sending the results to be stored and evaluated by analytic data processes of a transit regulatory agency showing that this project is technically viable. The low-cost solution was justified by a financial analysis based on both costs (URCa solution and a bridge) that has shown a ratio of 1:10,000.

Transit Route Origin–Destination Matrix Estimation using Compressed Sensing

The development of an origin–destination (OD) demand matrix is crucial for transit planning. With the help of automated data, it is possible to estimate a stop-level OD matrix. We propose a novel method for estimating transit route OD matrix using automatic passenger count (APC) data. The method uses [Formula: see text] norm regularizer, which leverages the sparsity in the actual OD matrix. The technique is popularly known as compressed sensing (CS). We also discuss the mathematical properties of the proposed optimization program and the complexity of solving it. We used simulation to assess the accuracy and efficiency of the method and found that the proposed method is able to recover the actual matrix within small errors. With increased sparsity in the actual OD matrix, the solution gets closer to the actual value of the matrix. The method was found to perform more efficiently even for different demand patterns. We also present a real numerical example of OD estimation of the A Line Bus Rapid Transit (BRT) route in Twin Cities, MN.

Multi-constrained bus holding control in time windows with branch and bound and alternating minimization

This work proposes a periodic bus holding control method where the bus holding times of all running trips are computed simultaneously within each optimization time period; thus, increasing the coordination among running buses for avoiding bus bunching. This paper considers the adverse effects of the bus holding control in the in-vehicle travel times of on-board passengers and performs holistic bus holding decisions by modelling the bus holding problem as a discrete, nonlinear, constrained optimization problem. Given the computational complexity of the bus holding problem, an alternating minimization approach is introduced for computing the optimal holding times at each optimization instance. The performance of the periodic control method is evaluated against the performance of event-based control methods using 5-month automated vehicle location and automated passenger count data from bus line 1 in Stockholm for contacting simulation-based experiments.

Validation of automatic passenger counting: introducing the t-test-induced equivalence test

Automatic passenger counting (APC) in public transport has been introduced in the 1970s and has been rapidly emerging in recent years. Still, real-world applications continue to face events that are difficult to classify. The induced imprecision needs to be handled as statistical noise and thus methods have been defined to ensure that measurement errors do not exceed certain bounds. Various recommendations for such an APC validation have been made to establish criteria that limit the bias and the variability of the measurement errors. In those works, the misinterpretation of non-significance in statistical hypothesis tests for the detection of differences (e.g. Student’s t-test) proves to be prevalent, although existing methods which were developed under the term equivalence testing in biostatistics (i.e. bioequivalence trials, Schuirmann in J Pharmacokinet Pharmacodyn 15(6):657–680, 1987) would be appropriate instead. This heavily affects the calibration and validation process of APC systems and has been the reason for unexpected results when the sample sizes were not suitably chosen: Large sample sizes were assumed to improve the assessment of systematic measurement errors of the devices from a user’s perspective as well as from a manufacturers perspective, but the regular t-test fails to achieve that. We introduce a variant of the t-test, the revised t-test, which addresses both type I and type II errors appropriately and allows a comprehensible transition from the long-established t-test in a widely used industrial recommendation. This test is appealing, but still it is susceptible to numerical instability. Finally, we analytically reformulate it as a numerically stable equivalence test, which is thus easier to use. Our results therefore allow to induce an equivalence test from a t-test and increase the comparability of both tests, especially for decision makers.