DCSDNet: A Dual-Stream Cooperative Sensing Detection Network for Infrared Small Targets

Infrared images usually lack significant texture and morphological features, while there is a large amount of noise and clutter in the background. These characteristics make it difficult for general-purpose target detection algorithms to adequately extract key features of small targets in infrared images, resulting in incomplete feature information. In addition, the direct feature fusion of traditional neck networks suffers from feature misalignment, and the features of small targets are easily diluted or masked, further exacerbating the problem of feature loss. To solve the above problems, this paper proposes a Dual-Stream Cooperative Sensing Detection Network (DCSDNet) specifically designed for infrared small target detection. First, to improve the feature extraction capability of the model, this paper proposes the Dense Grouped Feature Learning (DGFL) Module, which provides a richer feature representation base for the infrared small target detection task through multi-level feature processing. Meanwhile, to reduce the problems of information loss and fusion imbalance, the Refined Feature Fusion Bottleneck (RFFB) Module is designed to achieve a finer feature fusion, which improves the feature extraction accuracy and fusion effect. In addition, this paper critically re-examines the necessity of feature pyramids through experimental validation and heatmap visualization. We deliberately discard the conventional pyramid structure prevalent in multi-object detection systems, and propose a Feature Harmonization Backbone (FHB). This innovation not only reduces feature dilution and misalignment risks but also strengthens the model's feature extraction capacity. Ultimately, combining these improvements forms the DCSDNet target detection algorithm, which focuses on improving the detection of small infrared targets. The DCSDNet method proposed in this paper achieves a mAP0.5 of 65.4%, 95.4% and 83.4% on the VEDAI-Infrared, NUAA-SIRST and IRSTD-1K datasets, respectively. These data indicate that the algorithm achieves deep feature extraction of small targets in infrared images and shows superior performance in IR small target detection.