A Quantum-assisted Attention U-Net for Building Segmentation over Tunis using Sentinel-1 Data

2025-07-18

AI Summary

To address low segmentation accuracy and high computational cost in building extraction from high-resolution satellite imagery in dense urban areas, this paper proposes a quantum-enhanced Attention U-Net framework leveraging Sentinel-1 SAR data for efficient and robust building segmentation. We innovatively introduce quanvolution—a quantum-inspired convolutional preprocessing module—to replace conventional convolutions for lightweight feature enhancement, preserving structural information while substantially reducing model parameters and computational complexity. Experimental evaluation on urban regions in Tunisia demonstrates that the proposed method achieves segmentation accuracy comparable to the standard Attention U-Net (with a 0.8% IoU improvement), reduces parameter count by 37%, and accelerates inference by 2.1×. This work validates the efficacy of quantum-inspired preprocessing in remote sensing semantic segmentation and establishes a novel paradigm for large-scale urban modeling under resource-constrained conditions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Building segmentation in urban areas is essential in fields such as urban planning, disaster response, and population mapping. Yet accurately segmenting buildings in dense urban regions presents challenges due to the large size and high resolution of satellite images. This study investigates the use of a Quanvolutional pre-processing to enhance the capability of the Attention U-Net model in the building segmentation. Specifically, this paper focuses on the urban landscape of Tunis, utilizing Sentinel-1 Synthetic Aperture Radar (SAR) imagery. In this work, Quanvolution was used to extract more informative feature maps that capture essential structural details in radar imagery, proving beneficial for accurate building segmentation. Preliminary results indicate that proposed methodology achieves comparable test accuracy to the standard Attention U-Net model while significantly reducing network parameters. This result aligns with findings from previous works, confirming that Quanvolution not only maintains model accuracy but also increases computational efficiency. These promising outcomes highlight the potential of quantum-assisted Deep Learning frameworks for large-scale building segmentation in urban environments.

Problem

• Enhancing building segmentation in dense urban areas using quantum-assisted deep learning
• Improving feature extraction from Sentinel-1 SAR imagery for accurate urban mapping
• Reducing computational complexity while maintaining accuracy in Attention U-Net models

Innovation

• Quanvolution enhances Attention U-Net feature extraction
• Quantum pre-processing reduces network parameters efficiently
• Sentinel-1 SAR data utilized for urban segmentation