PDLL-YOLO: A Lightweight Framework for Small-Object Detection in UAV Remote Sensing Imagery

Abstract

Small-object-detection is critical for remote sensing using low-altitude uncrewed aerial vehicles (UAVs), where vehicles, pedestrians, bicycles, and motorcycles often occupy only a few pixels and are affected by occlusion, motion blur, illumination variation, and complex backgrounds. These conditions lead to fine-detail degradation, cross-scale semantic inconsistency, and ambiguous responses between adjacent objects. To address these challenges, this article proposes PDLL-YOLO, a lightweight detector tailored to UAV remote sensing imagery. PDLL-YOLO comprises a P2–P3–P4 high-resolution prediction architecture and three core modules: the detail-structure-aware module (DSAM), the local-context enhanced fusion module (LCEF), and the local density hint module (LDH). The P2–P3–P4 architecture introduces high-resolution features into the detection stage to improve sensitivity to small targets. DSAM refines local structural cues, including edges, contours, and texture fragments, to suppress background interference. LCEF performs adaptive cross-scale fusion by jointly modeling local context, global response, and channel importance. LDH enhances crowded-region responses to improve the separability of densely distributed objects. Experiments on VisDrone2019 show that PDLL-YOLO achieves 41.42% mAP$_{50}$ with only 2.24 M parameters, outperforming the reproduced YOLOv12n baseline by 7.8 percentage points under the controlled comparison protocol. Additional evaluations on DroneVehicle, TinyPerson, DIOR, and AI-TOD further demonstrate a favorable accuracy–efficiency tradeoff and cross-scenario applicability for UAV and remote sensing small-object detection.