Holistic Multi-View Building Analysis in the Wild with Projection Pooling
DOI:
https://doi.org/10.1609/aaai.v35i4.16393Keywords:
Scene Analysis & Understanding, Other ApplicationsAbstract
We address six different classification tasks related to fine-grained building attributes: construction type, number of floors, pitch and geometry of the roof, facade material, and occupancy class. Tackling such a remote building analysis problem became possible only recently due to growing large-scale datasets of urban scenes. To this end, we introduce a new benchmarking dataset, consisting of 49426 images (top-view and street-view) of 9674 buildings. These photos are further assembled, together with the geometric metadata. The dataset showcases various real-world challenges, such as occlusions, blur, partially visible objects, and a broad spectrum of buildings. We propose a new \emph{projection pooling layer}, creating a unified, top-view representation of the top-view and the side views in a high-dimensional space. It allows us to utilize the building and imagery metadata seamlessly. Introducing this layer improves classification accuracy -- compared to highly tuned baseline models -- indicating its suitability for building analysis.Downloads
Published
2021-05-18
How to Cite
Wojna, Z., Maziarz, K., Jocz, Łukasz, Pałuba, R., Kozikowski, R., & Kokkinos, I. (2021). Holistic Multi-View Building Analysis in the Wild with Projection Pooling. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 2870-2878. https://doi.org/10.1609/aaai.v35i4.16393
Issue
Section
AAAI Technical Track on Computer Vision III