Performance Analysis of Various EfficientNet Based U-Net++ Architecture for Automatic Building Extraction from High Resolution Satellite Images

TL;DR

This paper proposes an enhanced U-Net++ architecture with various EfficientNet backbones for high-accuracy building extraction from high-resolution satellite images, demonstrating significant performance improvements over existing methods.

Contribution

The study introduces a novel EfficientNet-based U-Net++ model with deep supervision and redesigned skip connections, improving building segmentation accuracy in remote sensing imagery.

Findings

EfficientNet-B4 based U-Net++ achieved 92.23% mean accuracy.

The proposed model outperforms previous state-of-the-art approaches.

High precision and IoU scores demonstrate effective building extraction.

Abstract

Building extraction is an essential component of study in the science of remote sensing, and applications for building extraction heavily rely on semantic segmentation of high-resolution remote sensing imagery. Semantic information extraction gap constraints in the present deep learning based approaches, however can result in inadequate segmentation outcomes. To address this issue and extract buildings with high accuracy, various efficientNet backbone based U-Net++ has been proposed in this study. The designed network, based on U-Net, can improve the sensitivity of the model by deep supervision, voluminous redesigned skip-connections and hence reducing the influence of irrelevant feature areas in the background. Various effecientNet backbone based encoders have been employed when training the network to enhance the capacity of the model to extract more relevant feature. According on the experimental findings, the suggested model significantly outperforms previous cutting-edge approaches. Among the 5 efficientNet variation Unet++ based on efficientb4 achieved the best result by scoring mean accuracy of 92.23%, mean iou of 88.32%, and mean precision of 93.2% on publicly available Massachusetts building dataset and thus showing the promises of the model for automatic building extraction from high resolution satellite images.