计算机科学
最小边界框
人工智能
推论
背景(考古学)
计算机视觉
跳跃式监视
目标检测
失败
过程(计算)
一般化
矩形
功能(生物学)
边缘设备
深度学习
领域(数学)
GSM演进的增强数据速率
全球地图
对象(语法)
空间语境意识
比例(比率)
灵敏度(控制系统)
实时计算
航空影像
作者
Yan Gao,Min Zhang,Cheng Yang Tian,Runce Zhang,Zhejun Jin,Zhongsen Sun,Tian Liu,Yu Zheng
标识
DOI:10.1088/1361-6501/ae96cd
摘要
Abstract This paper addresses the challenge of small object detection in complex backgrounds under limited computational resources in unmanned aerial vehicle (UAV) aerial imagery. Based on the lightweight YOLOv11s framework, we proposes a lightweight model LMS-YOLO designed for UAV small object detection. With a view to alleviate the loss of subtle features caused by deep downsampling, we propose a local–global decoupled attention module, which splits the original global attention into local window attention and global context modules to process local details and global information respectively. Meanwhile, in order to expand the receptive field to cope with drastic scale changes, this paper proposes a multi-scale sparse dilated attention module, which can expand the receptive field without adding extra parameters through parallel processing of different dilation rates, and better capture the context around small objects. To enhance gradient sensitivity in bounding box regression and reduce missed detections of small targets, this paper proposes a loss function sensitive to small-scale objects (SS-ShapeIoU). The proposed loss function addresses low-resolution regression by penalizing edge offsets and adapting area weights. Consequently, bounding box accuracy improves significantly. Compared to the baseline YOLOv11s, LMS-YOLO improves mAP 50 by 4.37% on VisDrone-DET2019, and the precision and recall are increased by 5.60% and 2.16% respectively. Additionally, our model reduces parameters by 1.91% and FLOPs by 0.83%, while sustaining an inference speed of 32.8 FPS. Evaluations on the UAVDT dataset further validate the cross-dataset adaptability of our model. Despite varying illumination and weather conditions, its mAP 50 still improves by 2.49% over the baseline. In summary, LMS-YOLO achieves a good balance between accuracy and efficiency, offering strong practical viability for resource-constrained UAV edge devices.
科研通智能强力驱动
Strongly Powered by AbleSci AI