Driving efficiency in aerial scene classification: Insights from data augmentation, image processing, and multiscale Convolutional Neural Network models

Mohammad Rashedur Rahman

Abstract:

Aerial scene classification using satellite and drone imagery is vital for applications like environmental moni￾toring and urban planning, but the high computational demands of Convolutional Neural Networks (CNNs) limit
their real-time use on resource-constrained platforms. Additionally, these models often lack global context
awareness, relying mainly on small 3 × 3 kernels that capture fine details but miss broader spatial relationships.
While large models can learn complex patterns, lightweight models struggle without adequate data and pre￾processing. To address these challenges, we propose a lightweight CNN classifier optimized for fast, real-time
aerial scene classification. Inspired by the Inception network, our architecture integrates multi-scale convolu￾tional filters (1 × 1, 3 × 3, 5 × 5, and 7 × 7) to capture both local and global context. To reduce computational
overhead, we incorporate Depthwise Separable Convolutions (DSC). To overcome the limitations of a compact
model, we apply 5-fold semantic-preserving data augmentation and Contrast Limited Adaptive Histogram
Equalization (CLAHE) to enhance feature visibility. While most state-of-the-art models require at least a million
parameters, our lightweight CNN achieves an impressive 97.62 % accuracy on the UC (University of California)
Merced Land Use Dataset using only 56,293 parameters. Furthermore, we use Gradient-Weighted Class Acti￾vation Mapping (Grad-CAM) to assess augmentation, CLAHE, and our architecture’s influence on feature
attention. This study demonstrates that effective preprocessing with CLAHE and extensive augmentation can
narrow the gap between lightweight CNNs and complex models. These results support the use of efficient models
for real-time, resource-constrained aerial scene classification, promoting sustainable and accessible Artificial
Intelligence (AI) in remote sensing applications.