ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

DeepMAO: Deep Multi-scale Aware Overcomplete Network for Building Segmentation in Satellite Imagery

Sikdar, A and Udupa, S and Gurunath, P and Sundaram, S (2023) DeepMAO: Deep Multi-scale Aware Overcomplete Network for Building Segmentation in Satellite Imagery. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, 17 - 24 June 2023, Vancouver, BC, Canada, pp. 487-496.

[img] PDF
IEEE-CVF_CVPRW2023_2023_487-496_2023.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy
Official URL: https://doi.org/10.1109/CVPRW59228.2023.00055


Building segmentation in large-scale aerial images is challenging, especially for small buildings in dense and cluttered urban environments. Complex building structures with highly varied geometric footprints pose an additional challenge for the building segmentation task in satellite imagery. In this work, we propose to tackle the issue of detecting and segmenting small and complex-shaped buildings in Electro-Optical (EO) and SAR satellite imagery. A novel architecture Deep Multi-scale Aware Overcomplete Network (DeepMAO), is proposed that comprises an overcomplete branch that focuses on fine structural features and an undercomplete (U-Net) branch tasked to focus on coarse, semantic-rich features. Additionally, a novel self-regulating augmentation strategy, "Loss-Mix,"is proposed to increase pixel representation of misclassified pixels. DeepMAO is simple and efficient in accurately identifying small and geometrically complex buildings. Experimental results on SpaceNet 6 dataset, on both EO and SAR modalities, and the INRIA dataset show that DeepMAO achieves state-of-the-art building segmentation performance, including small and complex-shaped buildings with a negligible increase in the parameter count. In addition, the presence of the overcomplete branch in DeepMAO helps in handling the speckle noise present in the SAR image modality. © 2023 IEEE.

Item Type: Conference Paper
Publication: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher: IEEE Computer Society
Additional Information: The copyright for this article belongs to the IEEE Computer Society.
Keywords: Antennas; Buildings; Complex networks; Pixels; Radar imaging; Semantic Segmentation; Semantics; Synthetic aperture radar, Aerial images; Building structure; Complex buildings; Electro-optical; Large-scales; Multi-scales; Novel architecture; Over-complete; Small buildings; Urban environments, Satellite imagery
Department/Centre: Division of Interdisciplinary Sciences > Robert Bosch Centre for Cyber Physical Systems
Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 23 Nov 2023 06:26
Last Modified: 23 Nov 2023 06:26
URI: https://eprints.iisc.ac.in/id/eprint/83211

Actions (login required)

View Item View Item