Detecting inter-sectional accuracy differences in driver drowsiness detection algorithms

Mkhuseli Ngxande, Jules Raymond Tapamo, Michael Burke

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

Convolutional Neural Networks (CNNs) have been used successfully across a broad range of areas including data mining, object detection, and in business. The dominance of CNNs follows a breakthrough by Alex Krizhevsky which showed improvements by dramatically reducing the error rate obtained in a general image classification task from 26.2% to 15.4%. In road safety, CNNs have been applied widely to the detection of traffic signs, obstacle detection, and lane departure checking. In addition, CNNs have been used in data mining systems that monitor driving patterns and recommend rest breaks when appropriate. This paper presents a driver drowsiness detection system and shows that there are potential social challenges regarding the application of these techniques, by highlighting problems in detecting dark-skinned drivers faces. Unfortunately, publicly available datasets are often captured in different cultural contexts, and therefore do not cover all ethnicities, which can lead to false detections or racially biased models. Results presented here show that models trained using publicly available datasets suffer extensively from over-fitting, and can exhibit racial bias, as shown by testing on a more representative dataset. We propose a novel visualisation technique that can assist in identifying groups of people where there might be the potential of discrimination, using Principal Component Analysis (PCA) to produce a grid of faces sorted by similarity, and combining these with a model accuracy overlay.

Original languageEnglish
Title of host publication2020 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)
EditorsFred Nicolls
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Chapter62-67
Number of pages6
ISBN (Electronic)9781728141626
ISBN (Print)9781728141633
DOIs
Publication statusPublished - 2020
Externally publishedYes
EventSouthern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa 2020 - Cape Town, South Africa
Duration: 29 Jan 202031 Jan 2020
https://ieeexplore-ieee-org.ezproxy.lib.monash.edu.au/xpl/conhome/9033509/proceeding (Proceedings)
https://web.archive.org/web/20200204014809/http://www.prasa.org/ (Website)

Conference

ConferenceSouthern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa 2020
Abbreviated titleSAUPEC/RobMech/PRASA 2020
CountrySouth Africa
CityCape Town
Period29/01/2031/01/20
Internet address

Keywords

  • Biased models
  • CNNs
  • Drowsiness Detection
  • Road Safety

Cite this