This paper presents an improved YOLOv8 algorithm for remote sensing image target detection. The algorithm addresses the challenges of complex backgrounds, numerous small targets, and varying target sizes in remote sensing images. The key improvements include adding an extra detection layer for small targets, introducing a C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) to enhance detection of different-sized targets, and replacing the CIoU loss function with Wise-IoU to improve model robustness. The improved algorithm achieves an mAP@0.5 of 82.7% on the DOTA v1.0 dataset, which is 1.3% higher than the original YOLOv8. The algorithm demonstrates improved detection accuracy for remote sensing targets. The experiments show that the improved algorithm outperforms other detection algorithms such as SSD, YOLOv5, YOLOv7, and YOLOX. The results indicate that the improved algorithm enhances the model's ability to extract feature details of remote sensing targets, leading to better overall detection accuracy. The algorithm's performance is validated through ablation studies and comparison tests with other algorithms. The improved algorithm is more effective in detecting targets in remote sensing images with different characteristics.This paper presents an improved YOLOv8 algorithm for remote sensing image target detection. The algorithm addresses the challenges of complex backgrounds, numerous small targets, and varying target sizes in remote sensing images. The key improvements include adding an extra detection layer for small targets, introducing a C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) to enhance detection of different-sized targets, and replacing the CIoU loss function with Wise-IoU to improve model robustness. The improved algorithm achieves an mAP@0.5 of 82.7% on the DOTA v1.0 dataset, which is 1.3% higher than the original YOLOv8. The algorithm demonstrates improved detection accuracy for remote sensing targets. The experiments show that the improved algorithm outperforms other detection algorithms such as SSD, YOLOv5, YOLOv7, and YOLOX. The results indicate that the improved algorithm enhances the model's ability to extract feature details of remote sensing targets, leading to better overall detection accuracy. The algorithm's performance is validated through ablation studies and comparison tests with other algorithms. The improved algorithm is more effective in detecting targets in remote sensing images with different characteristics.