Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks

JS Wijnands; J Thompson; KA Nice; GDPA Aschwanden; M Stevenson

Journal article

Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks

JS Wijnands, J Thompson, KA Nice, GDPA Aschwanden, M Stevenson

Neural Computing and Applications | SPRINGER LONDON LTD | Published : 2020

DOI: 10.1007/s00521-019-04506-0

Download PDF

Abstract

Driver drowsiness increases crash risk, leading to substantial road trauma each year. Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a mobile phone. Phone applications reduce the need for specialised hardware and hence, enable a cost-effective roll-out of the technology across the driving population. While it has been shown that three-dimensional (3D) operations are more suitable for spatiotemporal feature learning, current methods for drowsiness detection commonly use frame-based, multi-step approaches. However, computationally expensive techniques that achieve superior results on action reco..

View full abstract

University of Melbourne Researchers

Jason Thompson Author

Kerry Nice Author

Mark Stevenson Author

Related Projects (4)

Designing injury rehabilitation schemes for transport systems of tomorrow

This project aims to develop new models for understanding the effect of road transport system design on injury insurance, compensation and r..

CARS AND CITIES: REDUCING ROAD TRAUMA AND ENHANCING POPULATION HEALTH

The aim of this Fellowship is to generate novel research findings to inform and facilitate reductions in the burden of road injury in Austra..

EFFECTS OF FEEDBACK AND INCENTIVE-BASED INSURANCE ON DRIVING BEHAVIOURS

This project aims to examine the extent to which direct-feedback and incentive-based insurance modify a drivers’ behaviour. The project plan..

A HIGH-PERFORMANCE CLOUD RESOURCE FOR COMPUTATIONAL MODELLING

This project aims to build a relatively low-cost graphical-processing-unit-based cloud-accessible facility. Much current cutting-edge resear..

Grants

Awarded by Transport Accident Commission

Funding Acknowledgements

This work was supported by the Australian Research Council [Grant No. LP150100680]; QBE; and the Transport Accident Commission. Further, this research was undertaken using the LIEF HPC-GPGPU Facility hosted at the University of Melbourne [Grant No. LE170100200]. M.S. is supported by a National Health and Medical Research Council (Australia) Fellowship [Grant No. APP1136250]. J.T. is supported by an Australian Research Council Discovery Early Career Research Award [Grant No. DE180101411]. The authors would like to acknowledge Katherine Scully for her assistance with the literature review, and the anonymous reviewers for their valuable feedback, which helped improve the quality of the original manuscript.