An Automatic Detection Algorithm of Metro Passenger Boarding and Alighting Based on Deep Learning and Optical Flow

Liu, Quanli; Guo, Qiang; Wang, Wei; Zhang, Yuanqing; Kang, Qiang

doi:10.1109/tim.2021.3054627

Cited by 24 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides these methodologies related to the neural network and signal mode decompensation, there are other algorithms such as the fuzzy logic method [18], Physical-Virtual Collaboration Modeling [19], time series analysis [20], automatic detection algorithm [21], improved gravity model [22], support vector machine model [23], and selforganizing data mining [24].…”

Section: Passenger Flow Prediction Under Normal Conditionsmentioning

confidence: 99%

Short-Term Interval Prediction of Inbound Passenger Flow of Subway Station under Failure Events

Pu,

Xu,

Fan

et al. 2024

Journal of Advanced Transportation

View full text Add to dashboard Cite

Accurate forecasting of subway passenger flows is considered essential for the development of efficient train schedules. However, transport capacity constraints as well as station congestion can be caused by unexpected concerns with trains or power supply, which endanger passenger safety. Predicting passenger flows at the time of a fault is particularly challenging due to the low probability of failure and the complexity of the factors involved. In addition, deviation from the observed value may be resulted by the point-in-time prediction of passenger flow, thus affecting the efficiency of passenger flow control measures. To address this concern, a three-stage A-LSTM prediction model utilizing an attention mechanism and a double-layer LSTM (Long Short-Term Memory) neural network has been proposed. The model is used to map the impact of fault events on subway transport capacity with respect to delays onto the inbound passenger flow. By analyzing the data from the subway system in a metropolitan city of China, the range of passenger flow fluctuations in 10-minute intervals will be precisely predicted and applied to different subway stations.

show abstract

Section: Passenger Flow Prediction Under Normal Conditionsmentioning

confidence: 99%

Short-Term Interval Prediction of Inbound Passenger Flow of Subway Station under Failure Events

Pu,

Xu,

Fan

et al. 2024

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Passenger monitoring applications are an emerging research area that involves detecting passenger intents of boarding and alighting and warning of dangerous behavior in public transportation [60]. However, this field has not yet received much attention due to the lack of available datasets and the difficulty of monitoring multiple users simultaneously.…”

Section: A In-vehicle Human Monitoringmentioning

confidence: 99%

A Survey of Federated Learning for Connected and Automated Vehicles

Chellapandi¹,

Yuan²,

Zak³

et al. 2023

Preprint

View full text Add to dashboard Cite

Connected and Automated Vehicles (CAVs) are one of the emerging technologies in the automotive domain that has the potential to alleviate the issues of accidents, traffic congestion, and pollutant emissions, leading to a safe, efficient, and sustainable transportation system. Machine learningbased methods are widely used in CAVs for crucial tasks like perception, motion planning, and motion control, where machine learning models in CAVs are solely trained using the local vehicle data, and the performance is not certain when exposed to new environments or unseen conditions. Federated learning (FL) is an effective solution for CAVs that enables a collaborative model development with multiple vehicles in a distributed learning framework. FL enables CAVs to learn from a wide range of driving environments and improve their overall performance while ensuring the privacy and security of local vehicle data. In this paper, we review the progress accomplished by researchers in applying FL to CAVs. A broader view of the various data modalities and algorithms that have been implemented on CAVs is provided. Specific applications of FL are reviewed in detail, and an analysis of the challenges and future scope of research are presented.

show abstract

“…The basic idea of object detection is to detect objects by processing video or image. For example, the object detection algorithm can be used to detect and classify road vehicles [1], and the object detection of passengers in the scene of rail transit station based on deep learning and optical flow method [2]. However, the existing rail transit-related study only focuses on passenger flow detection but ignores the statistics of passenger flow in different scenarios within the station, which makes it difficult to carry out more refined passenger flow management according to the number of passenger flow.…”

Section: Introductionmentioning

confidence: 99%

Computer vision-based detection model for passenger flows inside urban rail transit stations

Chen

2023

Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022)

View full text Add to dashboard Cite

The study of short-term passenger flow of rail transit is based on the passenger flow data, usually taking the station as the smallest unit and can only grasp the passenger flow law between stations macroscopically. In order to study the microscopic passenger flow law in different scenes within the station, it is necessary to obtain the passenger flow sequence of the corresponding scene. Therefore, we propose an end-to-end refined short-term passenger flow identification model based on computer vision named PAX-Detect. The structure of the model are as follows: (1) Take pictures of the scene in the station and manually mark the passenger's head. (2) Using annotated datasets to train the YOLOv5 algorithm and pruning optimization. (3) YOLOv5 and Deep SORT algorithm are used to detect and track passengers in the video, and the statistical results of the number of passengers are output in real-time. The experiment is carried out on the video data of the escalator entrance of a subway station in Beijing. The experimental results show that the accuracy of the real-time statistical algorithm for passenger numbers reaches 99.4% in the test scenario. The proposed model can identify the microscopic passenger flow in the scene of the rail transit station in real-time and has a certain application prospect.

show abstract

An Automatic Detection Algorithm of Metro Passenger Boarding and Alighting Based on Deep Learning and Optical Flow

Cited by 24 publications

References 41 publications

Short-Term Interval Prediction of Inbound Passenger Flow of Subway Station under Failure Events

Short-Term Interval Prediction of Inbound Passenger Flow of Subway Station under Failure Events

A Survey of Federated Learning for Connected and Automated Vehicles

Computer vision-based detection model for passenger flows inside urban rail transit stations

Contact Info

Product

Resources

About