To address the challenges of small target detection and significant scale variations in unmanned aerial vehicle (UAV) aerial imagery, which often lead to missed and false detections, we propose Multi-scale Feature Fusion YOLO (MFF-YOLO), an enhanced algorithm based on YOLOv8s. Our approach introduces a Multi-scale Feature Fusion Strategy (MFFS), comprising the Multiple Features C2f (MFC) module and the Scale Sequence Feature Fusion (SSFF) module, to improve feature integration across different network levels. This enables more effective capture of fine-grained details and sequential multi-scale features. Furthermore, we incorporate Inner-CIoU, an improved loss function that uses auxiliary bounding boxes to enhance the regression quality of small object boxes. To ensure practicality for UAV deployment, we apply the Layer-adaptive Magnitude-based pruning (LAMP) method to significantly reduce model size and computational cost. Experiments on the VisDrone2019 dataset show that MFF-YOLO achieves a 5.7% increase in mean average precision (mAP) over the baseline, while reducing parameters by 8.5 million and computation by 17.5%. The results demonstrate that our method effectively improves detection performance in UAV aerial scenarios.