TL;DR
A context-gated dynamic perception framework that treats small-object feature degradation as a coupled problem of representation, fusion, and prediction and indicates a practical accuracy-efficiency trade-off for dense aerial small-object perception.
HD-YOLO improves small-object detection with a compact parameter footprint, while direct hardware benchmarks remain necessary to establish deployment efficiency.
The proposed framework features a redesigned cross-scale feature fusion module, CCFM-S2, which utilizes the SPD-Conv operator for information preserving downsampling and explicitly integrates high-resolution shallow features (S2 layer), thereby infusing indispensable spatial details into the feature hierarchy for small targets.
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.
Small-object detection in unmanned aerial vehicle (UAV) imagery remains challenging because target objects often occupy only a few pixels, exhibit weak feature responses, and are easily obscured by complex backgrounds. These aspects significantly limit the effectiveness of end-to-end detection systems. To overcome these limitations and enhance the detection accuracy in challenging UAV settings, this paper proposes MPC-DETR, a Multi-scale Patch Context Transformer that is based on RT-DETR. To begin with, a Local-Global Attention Fusion Module (LGAF) is proposed to capture fine-grained local features and long-range semantic relations of small objects. LGAF enhances feature representation through a lightweight multi-branch synergistic attention mechanism while introducing limited computational overhead. Second, a Dilated Context-Aware Feature Interaction Module (DCFI) is proposed to enhance the discriminative capability of high-level features in cluttered backgrounds and densely populated small-object scenes. DCFI allows more efficient feature aggregation and contextual comprehension through multi-scale contextual modeling and scale-adaptive feature interaction. Third, a Patch-Guided Multi-scale Feature Fusion Module (PGMFF) is developed to create a patch-guided contextual fusion approach that combines shallow, high-resolution features with deeper semantic information. This process improves the maintenance and representation of fine object information and minimizes information loss in feature propagation. The experimental results on the VisDrone2019 dataset show that MPC-DETR has an mAP50 and mAP50–95 of 52.5% and 33.3%, respectively, which are 4.6 and 4.0 percentage points higher than the baseline model. Further analyses of the UAVDT and HIT-UAV datasets also support the high generalization potential of the suggested method to various UAV-based small-object detection problems. In general, the findings suggest that MPC-DETR provides precise, strong, and efficient small-object detection in complicated UAV images.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
