Sun Shizun, Han Shuo, Xu Junwei, Zhao Jie, Xu Ziyu, Li Lingjie, Han Zhaoming, Mo Bo
School of Aerospace Engineering, Beijing Institute of Technology, Beijing 100081, China.
North Navigation Control Technology Co., Ltd., Beijing 101102, China.
Sensors (Basel). 2025 Mar 29;25(7):2169. doi: 10.3390/s25072169.
In foggy environments, infrared images suffer from reduced contrast, degraded details, and blurred objects, which impair detection accuracy and real-time performance. To tackle these issues, we propose IDDNet, a lightweight infrared object detection network that integrates multi-scale fusion dehazing. IDDNet includes a multi-scale fusion dehazing (MSFD) module, which uses multi-scale feature fusion to eliminate haze interference while preserving key object details. A dedicated dehazing loss function, DhLoss, further improves the dehazing effect. In addition to MSFD, IDDNet incorporates three main components: (1) bidirectional polarized self-attention, (2) a weighted bidirectional feature pyramid network, and (3) multi-scale object detection layers. This architecture ensures high detection accuracy and computational efficiency. A two-stage training strategy optimizes the model's performance, enhancing its accuracy and robustness in foggy environments. Extensive experiments on public datasets demonstrate that IDDNet achieves 89.4% precision and 83.9% AP, showing its superior accuracy, processing speed, generalization, and robust detection performance.
在有雾环境中，红外图像存在对比度降低、细节退化和物体模糊的问题，这会损害检测精度和实时性能。为了解决这些问题，我们提出了IDDNet，一种集成了多尺度融合去雾的轻量级红外目标检测网络。IDDNet包括一个多尺度融合去雾（MSFD）模块，该模块利用多尺度特征融合来消除雾的干扰，同时保留关键目标细节。一个专门的去雾损失函数DhLoss进一步提高了去雾效果。除了MSFD，IDDNet还包含三个主要组件：（1）双向极化自注意力，（2）加权双向特征金字塔网络，以及（3）多尺度目标检测层。这种架构确保了高检测精度和计算效率。一种两阶段训练策略优化了模型的性能，增强了其在有雾环境中的精度和鲁棒性。在公共数据集上进行的大量实验表明，IDDNet实现了89.4%的精度和83.9%的平均精度（AP），显示出其卓越的精度、处理速度、泛化能力和鲁棒的检测性能。
