Automatic Recognition of Playful Physical Activity Opportunities of the Urban Environment

Tuure Saloheimo, Maximus Kaos, Pia Fricker, Perttu Hämäläinen

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

We investigate deep neural networks in recognizing playful physical activity opportunities of the urban environment. Using transfer learning with a pre-trained Faster R-CNN network, we are able to train a parkour training spot detector with only a few thousand street level photographs. We utilize a simple and efficient annotation scheme that only required a few days of annotation work by parkour hobbyists, and should be easily applicable in other contexts, e.g. skateboarding. The technology is tested through parkour spot exploration and visualization experiments. To inform and motivate the technology development, we also conducted an interview study about what makes an interesting parkour spot and how parkour hobbyists find spots. Our work should be valuable for researchers and practitioners of fields like urban design and exercise video games, e.g., by providing data for a location-based game akin to Pokémon Go, but with parkour-themed gameplay and challenges.

OriginalsprogEngelsk
TitelAcademic Mindtrek 2021 - Proceedings of the 24th International Academic Mindtrek Conference
ForlagAssociation for Computing Machinery
Publikationsdato1. jun. 2021
Sider49-59
ISBN (Elektronisk)9781450385145
DOI
StatusUdgivet - 1. jun. 2021
Begivenhed24th International Academic Mindtrek Conference, Mindtrek 2021 - Virtual, Online, Finland
Varighed: 1. jun. 20213. jun. 2021

Konference

Konference24th International Academic Mindtrek Conference, Mindtrek 2021
Land/OmrådeFinland
ByVirtual, Online
Periode01/06/202103/06/2021

Bibliografisk note

Publisher Copyright:
© 2021 ACM.

Fingeraftryk

Dyk ned i forskningsemnerne om 'Automatic Recognition of Playful Physical Activity Opportunities of the Urban Environment'. Sammen danner de et unikt fingeraftryk.

Citationsformater