高级检索

    谷小婧, 林昊琪, 丁德武, 顾幸生. 基于红外气体成像及实例分割的气体泄漏检测方法[J]. 华东理工大学学报(自然科学版), 2023, 49(1): 76-86. DOI: 10.14135/j.cnki.1006-3080.20210719001
    引用本文: 谷小婧, 林昊琪, 丁德武, 顾幸生. 基于红外气体成像及实例分割的气体泄漏检测方法[J]. 华东理工大学学报(自然科学版), 2023, 49(1): 76-86. DOI: 10.14135/j.cnki.1006-3080.20210719001
    GU Xiaojing, LIN Haoqi, DING Dewu, GU Xingsheng. An Infrared Gas Imaging and Instance Segmentation Based Gas Leakage Detection Method[J]. Journal of East China University of Science and Technology, 2023, 49(1): 76-86. DOI: 10.14135/j.cnki.1006-3080.20210719001
    Citation: GU Xiaojing, LIN Haoqi, DING Dewu, GU Xingsheng. An Infrared Gas Imaging and Instance Segmentation Based Gas Leakage Detection Method[J]. Journal of East China University of Science and Technology, 2023, 49(1): 76-86. DOI: 10.14135/j.cnki.1006-3080.20210719001

    基于红外气体成像及实例分割的气体泄漏检测方法

    An Infrared Gas Imaging and Instance Segmentation Based Gas Leakage Detection Method

    • 摘要: 针对红外气体成像实现自动化的泄漏检测,提出了一种基于深度网络的气羽实例分割方法,可以同时实现泄漏检测、气羽分割以及多泄露源的区分。不同于现有的实例分割方法,针对泄漏气羽各向异性的空间特征,采用二维高斯模型下的概率函数作为嵌入空间的相似性度量,提出了一种新的聚类损失函数。该损失函数通过聚拢实例内的像素点,同时学习一个斜椭圆形的带宽来最大化每个气羽实例分割掩膜。为了获得更多的红外气体成像数据以及避免人工标注气羽轮廓的困难,提出了一种使用合成红外气体成像数据集来训练模型的方法。实验结果表明,经过合成数据的训练,本文方法可以成功地在真实的红外视频上进行自动泄漏检测。与其他先进的实例分割方法相比,本文方法在保持高精度的同时具有更快的处理速度,适用于实时泄漏检测场景。

       

      Abstract: To realize automatic leakage detection for infrared gas imaging, we propose an instance segmentation method for gas plumes, which can simultaneously offer leakage detection, plume segmentation, and multi-source detection. To model the anisotropy of plumes in embedding space, different from the existing instance segmentation methods, we employ a new clustering loss function based on the similarity of the probability of two-dimensional Gaussians. The loss function pulls the pixels of the instance together and jointly maximizes the segmentation mask of each plume by learning a bandwidth that is with a slanted elliptical shape. Moreover, to obtain more infrared gas imaging data and avoid the difficulty of manually labeling plume contours, we generate a large synthetic infrared gas imaging data set and train our model on synthetic data. Experimental results show that our method can successfully perform automatic leakage detection on real infrared videos after training on synthetic data. Compared with the state-of-the-art methods, our method can perform plume instance segmentation at a higher speed while maintaining a high accuracy, which is suitable for real-time detection.

       

    /

    返回文章
    返回