Hybrid Feature Embedding For Automatic Building Outline Extraction
This work addresses a domain-specific issue for applications like change detection and disaster assessment, presenting an incremental improvement over existing methods.
The paper tackled the problem of imprecise building outline extraction from high-resolution aerial images by proposing a hybrid CNN-Transformer model with an active contour model and triple-branch decoder, achieving 91.1% mIoU on Vaihingen and 83.8% on Bing huts datasets.
Building outline extracted from high-resolution aerial images can be used in various application fields such as change detection and disaster assessment. However, traditional CNN model cannot recognize contours very precisely from original images. In this paper, we proposed a CNN and Transformer based model together with active contour model to deal with this problem. We also designed a triple-branch decoder structure to handle different features generated by encoder. Experiment results show that our model outperforms other baseline model on two datasets, achieving 91.1% mIoU on Vaihingen and 83.8% on Bing huts.