Journal
IET INTELLIGENT TRANSPORT SYSTEMS
Volume 11, Issue 5, Pages 282-289Publisher
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-its.2016.0066
Keywords
road safety; collision avoidance; computer vision; entropy; gait analysis; time series; pedestrians; behavioural sciences computing; traffic engineering computing; video signal processing; traffic conflicts; traffic safety diagnosis; proactive automated approach; road safety; collision avoidance; walking behaviour; speed profile; automatic pedestrian evasive action detection; computer-vision framework; permutation entropy; dynamic characteristics; time-series; normal free walking behaviour; video data; Shanghai; China; nonconforming road user behaviour; PE-based indicator; transportation infrastructure monitoring; pedestrian crossing behaviour; safety programmes
Funding
- NPRP award from the Qatar Research Fund (a member of Qatar Foundation) [NPRP 4-1170-2-456]
Ask authors/readers for more resources
The use of traffic conflicts is gaining acceptance as a proactive approach to studying road safety. A traffic conflict involves a chain of events in which at least one of the involved road-users performs some sort of evasive actions to avoid a potential collision. Pedestrian evasive actions are normally manifested by changes in the walking behaviour which is expressed through variations in their speed profile. This paper investigates the automatic detection of pedestrian evasive actions in a computer-vision framework. The study proposes a new measure for detecting pedestrians undertaking evasive actions based on permutation entropy (PE). PE is a robust approach for discovering dynamic characteristics of a time-series. In the current context, it reveals the degree of abnormality in the walking pattern by identifying the deviations from the normal free walking. The methodology is applied and validated using video data from an intersection in Shanghai, China. Results show that the PE-based indicator has a high potential to identify and measure the severity of conflicts that involve pedestrian evasive actions compared to traditional time-proximity measures (e.g. time-to-collision and post-encroachment-time). This research finds many applications in the modern transportation infrastructure monitoring, studying pedestrian crossing behaviour and developing safety programs for vulnerable road-users.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available