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.
Accurate road extraction from remote sensing images is crucial for autonomous driving, urban planning, and route planning. However, existing methods struggle to address the challenges of scale variation, occlusion, and blurred boundaries. To tackle these challenges, this paper proposes a heterogeneous dual-decoder network (HDDNet), which aims to simultaneously solve the multiple problems in remote sensing road extraction by designing two decoders with complementary functions. Specifically, the main decoder incorporates the Dynamic Snake Grouping Dilation (DSGD) module, which combines road morphological features with a grouped multi-scale receptive field to enhance the capture of narrow and multi-scale road features. The auxiliary decoder integrates the Multi-directional Connectivity and Boundary Enhancement (MCBE) module, which jointly optimizes road connectivity and boundary refinement by leveraging directional consistency between the road body and edges. Finally, the Dual Attention Feature Fusion (DAFF) module is introduced to interactively learn and fuse the output features of the main decoder and the auxiliary decoder in both spatial and channel dimensions, which improves the accuracy and robustness of feature representations. We conducted systematic experiments on three representative public datasets: DeepGlobe, Ottawa, and CHN6-CUG. The results demonstrate that the proposed method significantly outperforms current mainstream approaches in the road extraction task, achieving Intersection over Union (IoU) scores of 71.36%, 91.85%, and 67.27%, respectively, which strongly validates the performance and robustness of HDDNet across diverse road scenarios.
10 October 2024 in Pattern Analysis and Applications