Video-based driver distraction detection using transfer learning: Bangladesh perspective

Md Muhaiminul Kabir, Md Abrar Nawar, Mehedi Islam Remon, Nishi Kanta Paul, Hanif Bhuiyan, Md Moinul Hoque

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

Abstract

Bangladesh faces a severe challenge with a high frequency of road accidents, often caused by distracted drivers. Driver distraction is a significant contributor to road accidents and accounts for a large number of road crashes and injuries. Many researchers have experimented with various deep learning approaches in simulated environments to automatically address this situation worldwide. Unlike other studies, we use real-world images from Bangladesh, creating a dataset that fits the local context. We evaluated five deep learning models using transfer learning to detect driver distraction on this new dataset. Performance comparisons are provided by using five recent deep learning models: MobileNetV2, DenseNet201, ResNet50, InceptionResNetV2, and InceptionV3. The experiment shows that without using data augmentation, InceptionV3 achieved an accuracy of 75%. On the other hand, with data augmentation, both MobileNetV2 and DenseNet201 showed an accuracy of 72%.

Original languageEnglish
Title of host publication2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems (iCACCESS 2024)
Subtitle of host publicationInnovation for Sustainability
EditorsAbul Barkat Mollah Sayeed Ud Doulah
Place of PublicationBangladesh
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9798350350289
DOIs
Publication statusPublished - 2024
EventInternational Conference on Advances in Computing, Communication, Electrical, and Smart Systems 2024 - University of Liberal Arts, Dhaka, Bangladesh
Duration: 8 Mar 20249 Mar 2024
https://access.ulab.edu.bd/

Conference

ConferenceInternational Conference on Advances in Computing, Communication, Electrical, and Smart Systems 2024
Abbreviated titleiCACCESS 2024
Country/TerritoryBangladesh
CityDhaka
Period8/03/249/03/24
Internet address

Keywords

  • data pre-processing
  • Driver distraction detection
  • Inception-ResnetV2
  • InceptionV3
  • MobileNetV2
  • Resnet50
  • Transfer Learning

Cite this