Detecting inter-sectional accuracy differences indriver drowsiness detection algorithms.

Mkhuseli Ngxande, Jules-Raymond Tapamo, Michael Burke

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Convolutional Neural Networks (CNNs) have been used successfully across a broad range of areas including datamining, 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. This is a particularly important challenge in African contexts, where there are more dark-skinned drivers. 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. This work evaluates the performance obtained when training convolutional neural network models on commonly used driver drowsiness detection datasets and testing on datasets specifically chosen for broader representation. Results 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 publicationProceedings of the Southern African Universities Engineering Conference/RobMech/Pattern Recognition Association of South Africa 2020
Place of PublicationCape Town, South Africa
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-6
Number of pages6
ISBN (Electronic)978-1-7281-4162-6
ISBN (Print)978-1-7281-4163-3
DOIs
Publication statusPublished - 19 Mar 2020
EventSouthern African Universities Engineering Conference/RobMech/Pattern Recognition Association of South Africa 2020 - Cape Town, South Africa
Duration: 29 Jan 202031 Jan 2020
http://www.prasa.org/

Conference

ConferenceSouthern African Universities Engineering Conference/RobMech/Pattern Recognition Association of South Africa 2020
Abbreviated titleSAUPEC/RobMech/PRASA 2020
Country/TerritorySouth Africa
CityCape Town
Period29/01/2031/01/20
Internet address

Keywords / Materials (for Non-textual outputs)

  • CNNs
  • Road Safety
  • Drowsiness Detection
  • Biased models

Fingerprint

Dive into the research topics of 'Detecting inter-sectional accuracy differences indriver drowsiness detection algorithms.'. Together they form a unique fingerprint.

Cite this