Enhanced Detection of Tiny Objects in Aerial Images

2025-09-21

AI Summary

To address the poor detection performance of low-resolution, small-scale objects in complex backgrounds within aerial imagery, this paper proposes MoonNet—a lightweight, YOLOv8-based framework. Methodologically, MoonNet introduces (1) high-resolution input coupled with small-object-oriented data augmentation; (2) a hybrid orthogonal neural module integrating SE and CBAM attention mechanisms into the backbone, alongside expanded channel capacity to enhance representation of fine-grained features; and (3) an end-to-end trainable architecture. Experimental results demonstrate that MoonNet achieves state-of-the-art performance across multiple aerial small-object benchmarks, significantly outperforming the baseline YOLOv8. The implementation is publicly available, and extensive ablation studies confirm its strong compatibility and generalization capability—validated through integration into downstream models such as YOLC.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Large Vision Models
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

While one-stage detectors like YOLOv8 offer fast training speed, they often under-perform on detecting small objects as a trade-off. This becomes even more critical when detecting tiny objects in aerial imagery due to low-resolution targets and cluttered backgrounds. To address this, we introduce three enhancement strategies -- input image resolution adjustment, data augmentation, and attention mechanisms -- that can be easily implemented on YOLOv8. We demonstrate that image size enlargement and the proper use of augmentation can lead to enhancement. Additionally, we designed a Mixture of Orthogonal Neural-modules Network (MoonNet) pipeline which consists of attention-augmented CNNs. Two well-known attention modules, the Squeeze-and-Excitation Block (SE Block) and the Convolutional Block Attention Module (CBAM), were integrated into the backbone of YOLOv8 with an increased number of channels, and the MoonNet backbone obtained improved detection accuracy compared to the original YOLOv8. MoonNet further proved its adaptability and potential by achieving state-of-the-art performance on a tiny-object benchmark when integrated with the YOLC model. Our codes are available at: https://github.com/Kihyun11/MoonNet

Problem

• Improving detection of tiny objects in aerial images
• Addressing YOLOv8 limitations with small object detection
• Enhancing performance against low-resolution targets and cluttered backgrounds

Innovation

• Enlarged input image resolution for better detection
• Enhanced data augmentation strategies to improve performance
• Integrated attention mechanisms like SE Block and CBAM