This paper proposes a lightweight aerial photography target detection algorithm MFW-RTDETR for UAV embedded devices, aiming to solve the computing power bottleneck problem when large-scale detection models are deployed on edge devices. By integrating MobileNetV4ConvSmall as the backbone network (introducing the UIB module and depthwise separable convolution), combining the Varifocal Loss (VFL) classification loss with the Focaler-WIoUv3 (FWIoUv3) bounding box regression loss, and adopting the Layer-Adaptive Magnitude Pruning (LAMP) strategy, the model achieves a 66% reduction in parameter scale (from 19.97M to 6.70M) and a 42.3% reduction in computational complexity (FLOPs) on the VisDrone2019 dataset, while maintaining a detection accuracy of mAP@0.5 at 52.08%. Experimental results show that the algorithm has significant real-time advantages and robustness in complex aerial photography scenarios such as foggy days and nights.