Dense Object Detection Method for Remote Sensing Images Based on Improved YOLOv10

Due to the problems of low detection accuracy and high missed detection rate caused by small and dense objects in remote sensing images, we propose an improved lightweight YOLOv10 model aimed at improving detection performance. Specifically, the standard convolution is replaced with RFAConv in the backbone network to better capture fine-grained object details. Additionally, we incorporate a coordinate attention module to refine the spatial localization and object recognition capabilities of the model. Furthermore, the CARAFE up-sampling operator is adopted in place of standard nearest-neighbor interpolation, expanding the model's receptive field. Experimental results demonstrate that the improved model significantly outperforms the original YOLOv10 on the UCAS-AOD dataset, achieving a mAP50 of 97.2% and a mAP95 of 63.2%. This approach offers an efficient and lightweight solution for object detection in remote sensing images.