融合多尺度边缘增强提取的YOLOv8遥感图像目标检测算法

打开文本图片集

中图分类号：TP391.4；TP75 文献标志码：A 文章编号： 1000-5013（2026）01-0050-11

Abstract：In order to enhance the feature extraction capability and detection accuracy of YOLOv8 algorithm for targets of diverse scales in remote sensing tasks，a multi-scale edge enhancement extraction YOLOv8 algorithm is proposed. Shallow robust efficient multi-scale downsampling and deep robust eficient multi-scale downsampling modules are introduced to enhance the ability to preserve low and deep level feature details，respectively. In addition，an eficient edge enhanced upsampling module is introduced to improve the network's detection capability under multi-scale and complex background conditions.Furthermore，a partial self-attention mechanism module is integrated to enhance global information modeling capabilities and efectively suppress background noise. Experimental results show that，compared to the original YOLOv8 algorithm，the proposed algorithm achieves superior performance on the DIOR dataset，with an accuracy improvement of 0.7% ，arecall improvement of 2.4% ，an average accuracy mean value improvement of 2.0% for the intersection-overunion of O.5O，and an average accuracy mean value improvement of 2.8% for the intersection-over-union of 0.50 to 0.95.

Keywords：remote sensing image；YOLOv8 algorithm；edge enhancement；multi-scale feature extraction

随着遥感技术的快速发展，遥感图像的应用已经广泛渗透到环境监测[1]、城市规划[2]、农业监测[3]及军事侦察[4]等多个领域。（剩余14987字）