Hu Jinlong, Zhang Tian, Zhao Ming
Institute of Seismology, China Earthquake Administration, Wuhan 430071, China.
Northwest Land and Resource Research Center, Shaanxi Normal University, Xi'an 710119, China.
Sensors (Basel). 2025 Jul 16;25(14):4442. doi: 10.3390/s25144442.
Infrared small-target detection remains a critical challenge in military reconnaissance, environmental monitoring, forest-fire prevention, and search-and-rescue operations, owing to the targets' extremely small size, sparse texture, low signal-to-noise ratio, and complex background interference. Traditional convolutional neural networks (CNNs) struggle to detect such weak, low-contrast objects due to their limited receptive fields and insufficient feature extraction capabilities. To overcome these limitations, we propose a Multi-Scale Edge-Aware Convolution (MEAC) module that enhances feature representation for small infrared targets without increasing parameter count or computational cost. Specifically, MEAC fuses (1) original local features, (2) multi-scale context captured via dilated convolutions, and (3) high-contrast edge cues derived from differential Gaussian filters. After fusing these branches, channel and spatial attention mechanisms are applied to adaptively emphasize critical regions, further improving feature discrimination. The MEAC module is fully compatible with standard convolutional layers and can be seamlessly embedded into various network architectures. Extensive experiments on three public infrared small-target datasets (SIRSTD-UAVB, IRSTDv1, and IRSTD-1K) demonstrate that networks augmented with MEAC significantly outperform baseline models using standard convolutions. When compared to eleven mainstream convolution modules (ACmix, AKConv, DRConv, DSConv, LSKConv, MixConv, PConv, ODConv, GConv, and Involution), our method consistently achieves the highest detection accuracy and robustness. Experiments conducted across multiple versions, including YOLOv10, YOLOv11, and YOLOv12, as well as various network levels, demonstrate that the MEAC module achieves stable improvements in performance metrics while slightly increasing computational and parameter complexity. These results validate the MEAC module's significant advantages in enhancing the detection of small and weak objects and suppressing interference from complex backgrounds. These results validate MEAC's effectiveness in enhancing weak small-target detection and suppressing complex background noise, highlighting its strong generalization ability and practical application potential.
由于目标尺寸极小、纹理稀疏、信噪比低以及背景干扰复杂，红外小目标检测在军事侦察、环境监测、森林防火和搜索救援行动中仍然是一项严峻挑战。传统卷积神经网络（CNN）由于其有限的感受野和不足的特征提取能力，难以检测此类微弱、低对比度的物体。为克服这些限制，我们提出了一种多尺度边缘感知卷积（MEAC）模块，该模块在不增加参数数量或计算成本的情况下，增强了对小红外目标的特征表示。具体而言，MEAC融合了：（1）原始局部特征；（2）通过空洞卷积捕获的多尺度上下文；（3）从高斯差分滤波器导出的高对比度边缘线索。融合这些分支后，应用通道和空间注意力机制来自适应地强调关键区域，进一步提高特征辨别能力。MEAC模块与标准卷积层完全兼容，并且可以无缝嵌入到各种网络架构中。在三个公共红外小目标数据集（SIRSTD-UAVB、IRSTDv1和IRSTD-1K）上进行的大量实验表明，采用MEAC增强的网络显著优于使用标准卷积的基线模型。与十一个主流卷积模块（ACmix、AKConv、DRConv、DSConv、LSKConv、MixConv、PConv、ODConv、GConv和Involution）相比，我们的方法始终实现最高的检测准确率和鲁棒性。在包括YOLOv10、YOLOv11和YOLOv12在内的多个版本以及各种网络层级上进行的实验表明，MEAC模块在性能指标上实现了稳定提升，同时略微增加了计算和参数复杂度。这些结果验证了MEAC模块在增强小而弱的物体检测以及抑制复杂背景干扰方面的显著优势。这些结果验证了MEAC在增强微弱小目标检测和抑制复杂背景噪声方面的有效性，突出了其强大的泛化能力和实际应用潜力。
