Object detection in unmanned aerial vehicle (UAV)-based visual sensing is important for aerial monitoring and intelligent perception. However, it remains difficult because camera-captured aerial images often contain small targets, cluttered backgrounds, occlusion, and limited edge-computing resources. We propose LFC-YOLO, a lightweight feature-complementary detector for small objects in UAV imagery. The main component of LFC-YOLO is the Tiny Object-Specific Detection Architecture (TSD-Arch), which removes redundant computation from deep layers and builds a shallow high-resolution feature pyramid to preserve localization cues for small targets. To reduce the extra cost introduced by high-resolution feature fusion, lightweight GSConv is integrated into the reconstructed neck. In addition, we embed a Feature Complementary Mapping (FCM) block into the C2f backbone structure and form a C2f-based Feature Complementary Mapping (C2f-FCM) module. This module combines semantic and spatial information and reduces interference from complex backgrounds. Experiments on VisDrone2019 show that LFC-YOLO improves the mean average precision at an intersection-over-union threshold of 0.5 (${\mathrm{mAP}}_{50}$) by 4.0 percentage points over YOLOv8s while reducing the number of model parameters by 73.9%. Additional evaluation on UAVDT shows that the proposed design remains effective across different UAV scenarios.