Building footprints are among the most predominant features in urban areas, and provide valuable information for urban planning, solar energy suitability analysis, etc. We aim to automatically and rapidly identify building footprints by leveraging deep learning techniques and the increased availability of remote sensing datasets at high spatial resolution. The task is computationally challenging due to the use of large training datasets and large number of parameters. In related work, You-Only-Look-Once (YOLO) is a state-of-the-art deep learning framework for object detection. However, YOLO is limited in its capacity to identify small objects that appear in groups, which is the case for building footprints. We propose a LOcally-COnstrained (LOCO) You-Only-Look-Once framework to detect small and densely-distributed building footprints. LOCO is a variant of YOLO. Its layer architecture is determined by the spatial characteristics of building footprints and it uses a constrained regression modeling to improve the robustness of building size predictions. We also present an invariant augmentation based voting scheme to further improve the precision in the prediction phase. Experiments show that LOCO can greatly improve the solution quality of building detection compared to related work.
|Original language||English (US)|
|Number of pages||25|
|Journal||International Journal of Geographical Information Science|
|State||Published - Apr 2 2020|
Bibliographical noteFunding Information:
This work was supported by the Advanced Research Projects Agency - Energy, U.S. Department of Energy [DE-AR0000795]; U.S. Department of Defense [HM0210-13-1-0005, HM1582-08-1-0017]; U.S. National Science Foundation [1737633, 0940818, 1029711,1541876, IIS-1218168, IIS-1320580]; U.S. Department of Agriculture [2017-51181-27222]; U.S. National Institute of Health [KL2 TR002492, TL1 TR002493, UL1 TR002494]; OVPR Infrastructure Investment Initiative, University of Minnesota; Minnesota Supercomputing Institute (MSI), University of Minnesota. We would like to thank the reviewers and the members of the spatial computing research group at the University of Minnesota for their helpful comments on improving the quality of the paper. We also thank Kim Koffolt for improving the readability of this article.
- Building detection
- deep learning
- locally constrained
- remote sensing