Search

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.

Please cite this article as: Fricker, P. (2019). Virtual Reality for Immersive Data Interaction. Landscape Architecture Frontiers, 7(2), 153-159. https://doi:10.15302/J-LAF-20190216 In a time shaped by technological developments dissolving the boundaries between the real and the virtual world, we are challenged to newly define the potentials of virtual and mixed reality in the field of landscape architecture. Critical analyses of the primary application areas of these technologies show that the current focus mostly lies on the optimization of 3D visualization and navigation in virtual space. Within professional practice, mixed reality tools are increasingly being used to test and communicate design decisions, for marketing purposes, and more often, within the smart building industry as well. Thus far, the incorporation of immersive environments in landscape architecture is lacking research on human-centered data interaction and the perception of space. At Aalto University, Finland, the team of Pia Fricker, Professor of Practice for Computational Methodologies in Landscape Architecture and Urbanism, researches new immersive co-design methodologies to introduce new meaningful trajectories for participatory processes. Mixed reality applications are thus extended beyond common and conventional uses to help create multidisciplinary immersive interactive spaces using data informed processes. The research and teaching results showcased in the article address international discourse on the larger theme of “Digital Humanism — Big Data and Human- Centered Design.”