The current study examines the possibility of automatically detecting distracted pedestrians on crosswalks using their gait parameters. The methodology utilises recent findings in health science concerning the relationship between walking gait behaviour and cognitive abilities. Walking speed and gait variability are shown to be affected by the complexity of tasks (e.g. texting) that are performed during walking. Experiments are performed on a video data set from Surrey, British Columbia. The analysis relies on automated video‐based data collection using computer vision. A sensitivity analysis is carried out to assess the quality of the selected features in improving the accuracy of the classification. Classification results show that the proposed approach is promising with around 80% correct detection rate. This research can benefit applications in several transportation related fields such as pedestrian facility planning, pedestrian simulation models as well as road safety programmes and legislative studies.


    Access

    Download


    Export, share and cite



    Title :

    Exploring walking gait features for the automated recognition of distracted pedestrians


    Contributors:

    Published in:

    Publication date :

    2016-03-01


    Size :

    8 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Distracted walking: Cell phones increase injury risk for college pedestrians

    Stavrinos, Despina / Byington, Katherine W. / Schwebel, David C. | Elsevier | 2011



    Self-Reported Behaviors and Habits of Distracted College Pedestrians While Walking

    White, Mary / White, Jamario / Siuhi, Saidi et al. | Transportation Research Record | 2017