Han Yuqi, Wang Chengcheng, Luo Hui, Wang Huihua, Chen Zaiqing, Xia Yuelong, Yun Lijun
School of Information, Yunnan Normal University, Kunming, 650500, Yunnan, China.
Department of Education of Yunnan Province, Engineering Research Center of Computer Vision and Intelligent Control Technology, Kunming, 650500, Yunnan, China.
Sci Rep. 2025 Jul 2;15(1):22627. doi: 10.1038/s41598-025-07021-6.
Small object detection in UAV aerial images is challenging due to low contrast, complex backgrounds, and limited computational resources. Traditional methods struggle with high miss detection rates and poor localization accuracy caused by information loss, weak cross-layer feature interaction, and rigid detection heads. To address these issues, we propose LRDS-YOLO, a lightweight and efficient model tailored for UAV applications. The model incorporates a Light Adaptive-weight Downsampling (LAD) module to retain fine-grained small object features and reduce information loss. A Re-Calibration Feature Pyramid Network (Re-Calibration FPN) enhances multi-scale feature fusion using bidirectional interactions and resolution-aware hybrid attention. The SegNext Attention mechanism improves target focus while suppressing background noise, and the dynamic detection head (DyHead) optimizes multi-dimensional feature weighting for robust detection. Experiments show that LRDS-YOLO achieves 43.6% mAP50 on VisDrone2019, 11.4% higher than the baseline, with only 4.17M parameters and 24.1 GFLOPs, striking a balance between accuracy and efficiency. On the HIT-UAV infrared dataset, it reaches 84.5% mAP50, demonstrating strong generalization. With its lightweight design and high precision, LRDS-YOLO offers an effective real-time solution for UAV-based small object detection.
由于对比度低、背景复杂以及计算资源有限，无人机航拍图像中的小目标检测具有挑战性。传统方法因信息丢失、跨层特征交互薄弱和检测头僵化，导致漏检率高和定位精度差。为解决这些问题，我们提出了LRDS-YOLO，这是一种专为无人机应用量身定制的轻量级高效模型。该模型集成了轻量级自适应加权下采样（LAD）模块，以保留细粒度小目标特征并减少信息丢失。重新校准特征金字塔网络（Re-Calibration FPN）利用双向交互和分辨率感知混合注意力增强多尺度特征融合。SegNext注意力机制在抑制背景噪声的同时提高目标聚焦度，动态检测头（DyHead）优化多维特征加权以实现稳健检测。实验表明，LRDS-YOLO在VisDrone2019上实现了43.6%的mAP50，比基线高11.4%，参数仅417万个，计算量24.1 GFLOP，在准确性和效率之间取得了平衡。在HIT-UAV红外数据集上，它达到了84.5%的mAP50，展现出强大的泛化能力。凭借其轻量级设计和高精度，LRDS-YOLO为基于无人机的小目标检测提供了一种有效的实时解决方案。
