Vulnerable road user safety is of paramount importance as transport moves towards fully autonomous driving. The research question posed by this research is of how can we train a computer to be able to see and perceive a pedestrian’s movement. This work presents a dual network architecture, trained in tandem, which is capable of classifying the behaviour of a pedestrian from a single image with no prior context. The results show that the most successful network was able to achieve a correct classification accuracy of 94.3% when classifying images based on their behaviour. This shows the use of a novel data fusion method for pedestrian images and human poses. Having a network with these capabilities is important for the future of transport, as it will allow vehicles to correctly perceive the intention of pedestrians crossing the street, and will ultimately lead to fewer pedestrian casualties on our roads.
Classification of a Pedestrian’s Behaviour Using Dual Deep Neural Networks
Advs in Intelligent Syst., Computing
Science and Information Conference ; 2020 ; London, United Kingdom July 16, 2020 - July 17, 2020
2020-07-04
17 pages
Article/Chapter (Book)
Electronic Resource
English
The paradox of pedestrian's risk aversion
Elsevier | 2020
|Pedestrian's needs matter: Examining Manila's walking environment
Online Contents | 2016
|Pedestrian's needs matter: Examining Manila's walking environment
Elsevier | 2015
|Influence of built environment on pedestrian's crossing decision
Elsevier | 2014
|Evaluating Pedestrian's Choice of Some Specific Facilities in Dhaka
British Library Conference Proceedings | 2006
|