A specific perspective: Subway driver behaviour recognition using CNN and time‐series diagram
Authors:
Open Access
- 28 January 2021
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 15 (3) , 387-395
Abstract
Urban rail transit, especially the subway, has been booming in China for a decade, imposing safety challenges on all related parties. Drivers’ behaviours are particularly crucial. Typically, drivers’ actions are recorded by cameras, and the surveillance videos are evaluated manually. Current driver behaviour recognition methods mostly target the bus or car drivers and can hardly be implemented for subways, because subway drivers follow a rigid working code that needs a time sequence of movements to describe. In this study, we propose a recognition model to automatically recognise behaviours from single‐frame images that are extracted from surveillance videos; second, we convert the recognition results into time series diagrams, thus the recognised behaviours can be interpreted and analysed statistically and effectively. The validation experiments demonstrate that the convolutional neural network model can recognise 96.20% driver behaviours, and time series diagrams add time information to the behaviours, providing a convincible reference for subway driver evaluation.Keywords
Funding Information
- National Natural Science Foundation of China (61703308)
- Sichuan Provincial Science and Technology Support Program (2019YFG0040)
This publication has 16 references indexed in Scilit:
- Going deeper into action recognition: A surveyImage and Vision Computing, 2017
- Driver behavior recognition based on deep convolutional neural networks2016
- Video-Based Classification of Driving Behavior Using a Hierarchical Classification System with Multiple FeaturesInternational Journal of Pattern Recognition and Artificial Intelligence, 2016
- Image Classification by Selective Regularized Subspace LearningIEEE Transactions on Multimedia, 2015
- Determinants of Train Service Costs in Metro OperationsTransportation Research Record: Journal of the Transportation Research Board, 2015
- Head, Eye, and Hand Patterns for Driver Activity Recognition2014
- Action Recognition with Improved Trajectories2013
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Action recognition by dense trajectories2011
- A survey on vision-based human action recognitionImage and Vision Computing, 2010