Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network
The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited and furthermore, available data do not present a fair representation of different scenarios and rare...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/2/471 |
id |
doaj-60c0fc2183d2433ebd826863bcbcbb80 |
---|---|
record_format |
Article |
spelling |
doaj-60c0fc2183d2433ebd826863bcbcbb802021-01-07T00:00:49ZengMDPI AGApplied Sciences2076-34172021-01-011147147110.3390/app11020471Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial NetworkJames Spooner0Vasile Palade1Madeline Cheah2Stratis Kanarachos3Alireza Daneshkhah4Centre for Connected and Automated Automotive Research (CCAAR), Institute for Future Transport and Cities, Coventry University, Coventry CV1 5FB, UKResearch Centre for Data Science, Coventry University, Coventry CV1 5FB, UKHorizon Scanning, HORIBA MIRA Ltd., Watling Street, Nuneaton CV10 0TU, UKFaculty of Engineering and Computing, Coventry University, Coventry CV1 5FB, UKResearch Centre for Data Science, Coventry University, Coventry CV1 5FB, UKThe safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited and furthermore, available data do not present a fair representation of different scenarios and rare events. Before deploying autonomous vehicles publicly, their abilities must reach a safety threshold, not least with regards to vulnerable road users, such as pedestrians. In this paper, we present a novel Generative Adversarial Networks named the Ped-Cross GAN. Ped-Cross GAN is able to generate crossing sequences of pedestrians in the form of human pose sequences. The Ped-Cross GAN is trained with the Pedestrian Scenario dataset. The novel Pedestrian Scenario dataset, derived from existing datasets, enables training on richer pedestrian scenarios. We demonstrate an example of its use through training and testing the Ped-Cross GAN. The results show that the Ped-Cross GAN is able to generate new crossing scenarios that are of the same distribution from those contained in the Pedestrian Scenario dataset. Having a method with these capabilities is important for the future of transport, as it will allow for the adequate testing of Connected and Autonomous Vehicles on how they correctly perceive the intention of pedestrians crossing the street, ultimately leading to fewer pedestrian casualties on our roads.https://www.mdpi.com/2076-3417/11/2/471CAVautomotiveautonomouspedestriandatasethuman pose |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
James Spooner Vasile Palade Madeline Cheah Stratis Kanarachos Alireza Daneshkhah |
spellingShingle |
James Spooner Vasile Palade Madeline Cheah Stratis Kanarachos Alireza Daneshkhah Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network Applied Sciences CAV automotive autonomous pedestrian dataset human pose |
author_facet |
James Spooner Vasile Palade Madeline Cheah Stratis Kanarachos Alireza Daneshkhah |
author_sort |
James Spooner |
title |
Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network |
title_short |
Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network |
title_full |
Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network |
title_fullStr |
Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network |
title_full_unstemmed |
Generation of Pedestrian Crossing Scenarios Using Ped-Cross Generative Adversarial Network |
title_sort |
generation of pedestrian crossing scenarios using ped-cross generative adversarial network |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-01-01 |
description |
The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited and furthermore, available data do not present a fair representation of different scenarios and rare events. Before deploying autonomous vehicles publicly, their abilities must reach a safety threshold, not least with regards to vulnerable road users, such as pedestrians. In this paper, we present a novel Generative Adversarial Networks named the Ped-Cross GAN. Ped-Cross GAN is able to generate crossing sequences of pedestrians in the form of human pose sequences. The Ped-Cross GAN is trained with the Pedestrian Scenario dataset. The novel Pedestrian Scenario dataset, derived from existing datasets, enables training on richer pedestrian scenarios. We demonstrate an example of its use through training and testing the Ped-Cross GAN. The results show that the Ped-Cross GAN is able to generate new crossing scenarios that are of the same distribution from those contained in the Pedestrian Scenario dataset. Having a method with these capabilities is important for the future of transport, as it will allow for the adequate testing of Connected and Autonomous Vehicles on how they correctly perceive the intention of pedestrians crossing the street, ultimately leading to fewer pedestrian casualties on our roads. |
topic |
CAV automotive autonomous pedestrian dataset human pose |
url |
https://www.mdpi.com/2076-3417/11/2/471 |
work_keys_str_mv |
AT jamesspooner generationofpedestriancrossingscenariosusingpedcrossgenerativeadversarialnetwork AT vasilepalade generationofpedestriancrossingscenariosusingpedcrossgenerativeadversarialnetwork AT madelinecheah generationofpedestriancrossingscenariosusingpedcrossgenerativeadversarialnetwork AT stratiskanarachos generationofpedestriancrossingscenariosusingpedcrossgenerativeadversarialnetwork AT alirezadaneshkhah generationofpedestriancrossingscenariosusingpedcrossgenerativeadversarialnetwork |
_version_ |
1724347106745909248 |