Anovel framework for automatic passenger counting

Mukherjee, Satarupa; Saha, BaidyaNath; Jamal, Iqbal; Leclerc, Richard; Ray, Nilanjan

doi:10.1109/icip.2011.6116284

Cited by 31 publications

(12 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After defining the test dataset, to verify the effectiveness of the proposed algorithm in passenger number estimation, we compare it to two methods: SaCNN [25] and MCNN [26]. To account for the performances of the different detection models, we used the mean absolute error (MAE) and root mean squared error (RMSE), as shown in Equations (7) and (8), to evaluate the effectiveness of models based on the references [28][29][30], respectively. N img is the number of test images, x i g is the actual number of passengers in the test image, andx i p is the number of passengers on the bus estimated by the different methods.…”

Section: Evaluation Of Passenger Number Estimationmentioning

confidence: 99%

“…Torriti and Landau proposed radio-frequency identification technology to implement passenger counting, although the recognition result is susceptible to the position of the RF antenna and the direction of radiation [2]. With the popularity of surveillance cameras and advances in computer vision technology, image-based people-counting methods have been continuously proposed [3][4][5][6][7][8][9][10]. References [3][4][5]10] employed images from actual buses as experimental scenes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of the Number of Passengers in a Bus Using Deep Learning

Hsu

Chen

Perng

2020

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Evaluation Of Passenger Number Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of the Number of Passengers in a Bus Using Deep Learning

Hsu

Chen

Perng

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The method is efficient when the object size is large, with sparse crowd and limited or no occlusion, because large object size helps in the detection due to the presence of enough image pixels depicting the object. Tracking is successful for overhead FOVs where little or no occlusion is present [17], but succumbs to failure in the case of whole body views, where partial occlusion is present. Applying the detection-tracking approach becomes difficult in dense crowds, where each person is depicted by only a few image pixels and people occlude each other.…”

Section: Introductionmentioning

confidence: 94%

“…The detection and tracking-based approaches [9][10][11]17] count people by detecting individuals on an image and creating corresponding trajectories by tracking them. The number of trajectories in an interval of time accounts for the number of people.…”

Section: Introductionmentioning

confidence: 99%

Unique people count from monocular videos

2014

Self Cite

View full text Add to dashboard Cite

Counting unique number of people in a video (i.e., counting a person only once while the person passes through the field of view) is required in many video analytic applications, such as transit passenger and pedestrian volume count in railway stations, malls, and road intersections. The principal roadblock here is occlusion. To avoid this bottleneck, we adopt a combination of (a) a radical new approach of unique influx and outflux count (UIOC) of people within a region of interest (ROI), which is adopted from computational fluidics, (b) a nonlinear regressor to estimate the number of people within a ROI, and (c) ROI boundary tracking (as opposed to object or feature tracking) for a short period. In UIOC, we compute influx/outflux rate, i.e., number of people entering or exiting the ROI per unit time. Then, we sum the influx/outflux rate between any two time points to estimate the number of people that entered and/or left the ROI within that time interval. Our framework is validated on 19 publicly available datasets, with abundant occlusion, obtaining more than 95 % accuracy for each video. Our framework is online and real time. Our framework is comparatively inexpensive to install and operate as only one camera is used. These features make the proposed framework suitable for low-cost, smallbusiness/residential and/or commercial applications. We also extend our framework beyond monocular videos and apply it on multiple views of a publicly available dataset with about 99 % accuracy.

show abstract

“…Hejin [6] apresentou um método para estimar o fluxo de passageiros de ônibus baseado em trajetória de clustering. Mukherjee et al [7] desenvolveram um framework para contagem de passageiros em uma estação ferroviária. O framework possui três componentes: detecção de pessoas, rastreamento e validação.…”

Section: Introductionunclassified

Modelo estimativo do fluxo de embarque e desembarque de passageiros em sistemas de monitoramento metroferroviário com base em técnicas de visão computacional

Souza¹,

Fonseca²,

Belo³

2017

Anais De XXXV Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Resumo-A falta de monitoramento adequado do fluxo de usuários nos sistemas de transporte público metroviários, pode comprometer à segurança e o bem-estar dos passageiros. Nesse artigo, é proposto um modelo estimativo em tempo real, automático e contínuo, do fluxo de passageiros do sistema metroviário da CBTU (Companhia Brasileira de Trens Urbanos) de Recife, utilizando técnicas de visão computacional. Para este fim, foi proposto um modelo que envolve análise e reconhecimento de padrões de cabeças e ombros de passageiros. Pretende-se, em uma implementação futura, detectar e prever pontos críticos de multidões, de forma a garantir a segurança, gerar prognósticos para o planejamento estratégico operacional e evitar futuras aglomerações.

show abstract

Anovel framework for automatic passenger counting

Cited by 31 publications

References 4 publications

Estimation of the Number of Passengers in a Bus Using Deep Learning

Estimation of the Number of Passengers in a Bus Using Deep Learning

Unique people count from monocular videos

Modelo estimativo do fluxo de embarque e desembarque de passageiros em sistemas de monitoramento metroferroviário com base em técnicas de visão computacional

Contact Info

Product

Resources

About