Abstract
Detecting infrared gas leaks is critical for environmental monitoring and industrial safety, yet remains difficult because plumes are faint, small, semitransparent, and have weak, diffuse boundaries. We present physics-edge hybrid gas dynamic routing network (PEG-DRNet). First, we introduce the Gas Block, a diffusion-convection unit modeling gas transport: a local branch captures short-range variations, while a large-kernel branch captures long-range propagation. An edge-gated learnable fusion module balances local detail and global context, strengthening weak-contrast plume and contour cues. Second, we propose the adaptive gradient and phase edge operator (AGPEO), computing reliable edge priors from multi-directional gradients and phase-consistent responses. These are transformed by a multi-scale edge perception module (MSEPM) into hierarchical edge features that reinforce boundaries. Finally, the content-adaptive sparse routing path aggregation network (CASR-PAN), with adaptive information modulation modules for fusion and self, selectively propagates informative features across scales based on edge and content cues, improving cross-scale discriminability while reducing redundancy. Experiments on the IIG dataset show that PEG-DRNet achieves an overall AP of 29.8\%, an AP$_{50}$ of 84.3\%, and a small-object AP of 25.3\%, surpassing the RT-DETR-R18 baseline by 3.0\%, 6.5\%, and 5.3\%, respectively, while requiring only 43.7 Gflops and 14.9 M parameters. The proposed PEG-DRNet achieves superior overall performance with the best balance of accuracy and computational efficiency, outperforming existing CNN and Transformer detectors in AP and AP$_{50}$ on the IIG and LangGas dataset.
Abstract (translated)
检测红外气体泄漏对于环境监测和工业安全至关重要，但由于气体羽流微弱、小且半透明，并具有模糊的边界，因此这一任务仍然颇具挑战性。我们提出了物理-边缘混合气动动态路由网络（PEG-DRNet）。首先，引入了Gas Block模块，这是一个模拟气体传输的扩散与对流单元：局部分支捕捉短程变化，而大核分支则捕捉长程传播。一个边缘门控可学习融合模块平衡了局部细节和全局背景，增强了对比度较弱的羽流和轮廓线索。其次，我们提出了自适应梯度相位边缘算子（AGPEO），从多方向梯度与相位一致响应中计算可靠的边缘先验信息。这些通过多尺度边缘感知模块（MSEPM）转换为分层的边缘特征，强化了边界。最后，内容自适应稀疏路由路径聚合网络（CASR-PAN）通过自调制融合和自我调节模块选择性地在各个尺度上传递有意义的信息，基于边缘和内容提示，提高了跨尺度区分能力并减少了冗余。 实验显示，在IIG数据集上，PEG-DRNet实现了29.8%的整体AP、84.3%的AP$_{50}$以及25.3%的小物体AP，分别比RT-DETR-R18基线提升了3.0%、6.5%和5.3%，同时只需消耗43.7 Gflops和14.9 M参数。所提出的PEG-DRNet在准确性和计算效率之间达到了最佳平衡，在IIG和LangGas数据集上，无论是AP还是AP$_{50}$都优于现有的CNN和Transformer检测器。 总结来说，PEG-DRNet通过结合物理模型与边缘特征学习的方法，成功地提高了红外气体泄漏监测的准确性，并且在计算资源消耗方面表现出了较高的效率。
URL
https://arxiv.org/abs/2512.23234
