With special consideration for complex scenes and densely distributed small objects, this frequently leads to serious false and missed detections for unmanned aerial vehicle (UAV) images in small object detection scenarios. Consequently, we propose a UAV image small object detection algorithm, termed SMA-YOLO. Firstly, a parameter-free simple slicing convolution (SSC) module is integrated in the backbone network to slice the feature maps and enhance the features so as to effectively retain the features of small objects. Subsequently, to enhance the information exchange between upper and lower layers, we design a special multi-cross-scale feature pyramid network (M-FPN). The C2f-Hierarchical-Phantom Convolution (C2f-HPC) module in the network effectively reduces information loss by fine-grained multi-scale feature fusion. Ultimately, adaptive spatial feature fusion detection Head (ASFFDHead) introduces an additional P2 detection head to enhance the resolution of feature maps to better locate small objects. Moreover, the ASFF mechanism is employed to optimize the detection process by filtering out information conflicts during multi-scale feature fusion, thereby significantly optimizing small object detection capability. Using YOLOv8n as the baseline, SMA-YOLO is evaluated on the VisDrone2019 dataset, achieving a 7.4% improvement in mAP@0.5 and a 13.3% reduction in model parameters, and we also verified its generalization ability on VAUDT and RSOD datasets, which demonstrates the effectiveness of our approach.
10 July 2025 in IEEE Geoscience and Remote Sensing Letters
In recent years, remarkable progress has been achieved in lightweight Remote Sensing Image Super-Resolution (RSISR) techniques. However, these methods, in order to maintain lightweight property and efficient computation, are often affected by inadequate feature extraction and limited receptive fields, which restrict the precise reconstruction of structurally complex remote sensing images (RSI). To address this issue, we propose a Multi-Scale Frequency-Enhanced Mamba (MFEM), which employs a unique multi-scale convolutional structure to enhance feature extraction and utilizes a frequency-enhanced Mamba to capture long-range dependencies with linear complexity. Specifically, we design a Multi-Scale Blueprint Residual Block (MBRB) with three specifications, which allows the network to efficiently extract multi-scale features of RSIs while maintaining lightweight property by using different specifications of MBRB at varying network depths. Furthermore, we develop a Frequency Mamba Enhancement Block (FMEB), which enhances Mamba from within through frequency analysis to globally model multi-level features while improving local information loss. Extensive experiments demonstrate that our method achieves better super-resolution performance while maintaining lightweight property.