Wojna, Z;
Maziarz, K;
Jocz, L;
Paluba, R;
Kozikowski, R;
Kokkinos, I;
(2021)
Holistic Multi-View Building Analysis in the Wild with Projection Pooling.
In:
Proceedings of the AAAI Conference on Artificial Intelligence.
(pp. pp. 2870-2878).
Association for the Advancement of Artificial Intelligence: Palo Alto, CA, USA.
Preview |
Text
2008.10041v3.pdf - Accepted Version Download (12MB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Holistic Multi-View Building Analysis in the Wild with Projection Pooling |
| Event: | 35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence |
| Location: | ELECTR NETWORK |
| Dates: | 02 February 2021 - 09 February 2021 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://ojs.aaai.org/index.php/AAAI/article/view/1... |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Scene Analysis & Understanding, Other Applications |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10134219 |
Archive Staff Only
 |
View Item |
