Deep learning identification models have shown promise for identifying gas plumes in Longwave IR hyperspectral images of urban scenes, particularly when a large library of gases are being considered. Because many gases have similar spectral signatures, it is important to properly estimate the signal from a detected plume. Typically, a scene's global mean spectrum and covariance matrix are estimated to whiten the plume's signal, which removes the background's signature from the gas signature. However, urban scenes can have many different background materials that are spatially and spectrally heterogeneous. This can lead to poor identification performance when the global background estimate is not representative of a given local background material. We use image segmentation, along with an iterative background estimation algorithm, to create local estimates for the various background materials that reside underneath a gas plume. Our method outperforms global background estimation on a set of simulated and real gas plumes. This method shows promise in increasing deep learning identification confidence, while being simple and easy to tune when considering diverse plumes.

翻译：深度学习识别模型在城市场景长波红外高光谱图像的气体羽流辨识中展现出潜力，尤其在考虑大规模气体数据库时。由于多数气体具有相似的光谱特征，准确估计探测羽流的信号至关重要。通常，通过估计场景的全局均值光谱与协方差矩阵对羽流信号进行白化处理，以消除背景信号对气体特征的影响。然而，城市场景常包含空间与光谱异质性显著的多类背景材料，当全局背景估计无法代表特定局部背景材质时，会导致识别性能下降。本文采用图像分割技术结合迭代背景估计算法，为气体羽流下方的不同背景材质生成局部估计。在模拟及真实气体羽流数据集上的实验表明，该方法优于全局背景估计，能够提升深度学习模型的识别置信度，同时针对多种羽流场景具有简洁易调参的优势。