Revisiting Aerial Scene Classification on the AID Benchmark
This work addresses the challenge of robust scene classification for aerial images, which is important for urban planning and environmental preservation, but it is incremental as it builds on existing deep learning approaches.
The paper tackles aerial scene classification by reviewing machine learning methods and proposing Aerial-Y-Net, a spatial attention-enhanced CNN with multi-scale feature fusion, achieving 91.72% accuracy on the AID dataset.
Aerial images play a vital role in urban planning and environmental preservation, as they consist of various structures, representing different types of buildings, forests, mountains, and unoccupied lands. Due to its heterogeneous nature, developing robust models for scene classification remains a challenge. In this study, we conduct a literature review of various machine learning methods for aerial image classification. Our survey covers a range of approaches from handcrafted features (e.g., SIFT, LBP) to traditional CNNs (e.g., VGG, GoogLeNet), and advanced deep hybrid networks. In this connection, we have also designed Aerial-Y-Net, a spatial attention-enhanced CNN with multi-scale feature fusion mechanism, which acts as an attention-based model and helps us to better understand the complexities of aerial images. Evaluated on the AID dataset, our model achieves 91.72% accuracy, outperforming several baseline architectures.