This paper presents an improved YOLOv8 algorithm for remote sensing image target detection, addressing the challenges of complex backgrounds, numerous small targets, and varying target scales. The key contributions include: 1. **Additional Detection Layer**: An extra detection layer is added to the backbone network to enhance the extraction of small target features. 2. **C2f-E Module**: A C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) is introduced to improve the network's ability to detect targets of different sizes. 3. **Wise-IoU Loss Function**: The CIoU loss function is replaced with Wise-IoU to improve the model's robustness and generalization. The improved algorithm was evaluated on the DOTA v1.0 dataset, achieving an mAP@0.5 value of 82.7%, which is 1.3% higher than the original YOLOv8. The experimental results demonstrate that the proposed method effectively enhances the detection accuracy of remote sensing images, particularly for small and multi-sized targets. The paper also includes comparisons with other state-of-the-art algorithms, showing superior performance in various target categories and complex scenes.This paper presents an improved YOLOv8 algorithm for remote sensing image target detection, addressing the challenges of complex backgrounds, numerous small targets, and varying target scales. The key contributions include: 1. **Additional Detection Layer**: An extra detection layer is added to the backbone network to enhance the extraction of small target features. 2. **C2f-E Module**: A C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) is introduced to improve the network's ability to detect targets of different sizes. 3. **Wise-IoU Loss Function**: The CIoU loss function is replaced with Wise-IoU to improve the model's robustness and generalization. The improved algorithm was evaluated on the DOTA v1.0 dataset, achieving an mAP@0.5 value of 82.7%, which is 1.3% higher than the original YOLOv8. The experimental results demonstrate that the proposed method effectively enhances the detection accuracy of remote sensing images, particularly for small and multi-sized targets. The paper also includes comparisons with other state-of-the-art algorithms, showing superior performance in various target categories and complex scenes.