Reconstructing unseen spaces in collapsed structures for search and rescue via deep learning based radargram inversion
Reconstructing unseen spaces in collapsed structures for search and rescue via deep learning based radargram inversion
复制标题
DOI：
10.1016/j.autcon.2022.104380
复制
发表时间：
2022-08
影响因子：
10.3
通讯作者：
Da Hu;Junjie Chen;Shuai Li
中科院分区：
文献类型：
--
作者：
Da Hu;Junjie Chen;Shuai Li
提出了一种新的基于深度学习的探地雷达(GPR)雷达图像处理方法，用于重建坍塌建筑物被遮挡的内部空间，并提取诸如可存活的空隙等重要信息来辅助搜救行动。该方法创新性地利用了产生式对抗性网络(GAN)来扩充合成的探地雷达训练数据，并利用端到端的深度学习模型将探地雷达雷达图反转为横截面的介电常数图，该图可以进一步解释以重建倒塌结构的内部场景。首先，为了解决缺乏具有正确标签的训练数据的问题，从模拟倒塌结构的场景中生成合成雷达雷达图。GAN被应用于增强用于训练的合成雷达雷达图的真实性，提供了一种新的机制来准备和增强难以从真实灾难现场收集的数据。其次，不需要检测和分割雷达雷达图中的非直观特征，而是使用扩展的雷达雷达图训练一种新的编解码器结构，以直接重建对应于倒塌结构横截面的介电常数图。视觉图灵测试表明，GaN显著提高了合成探地雷达雷达图的真实感。所提出的探地雷达反演方法在从合成雷达图推断材料介电常数时，R2值为0.93，平均绝对误差(MAE)为0.73，结构相似指数(SSIM)为0.95。将预测的介电常数图进一步用于识别空隙，在像素水平上的F1得分为64.34%，准确率为63.06%，召回率为71.84%。在扩展的雷达图上，该网络预测介电常数图的R2值为0.76，MAE为1.49，SSIM为0.89。对增强后的雷达图进行空洞检测，在像素级的F1评分为45.20%，准确率为45.35%，召回率为53.99%。在两个多层建筑物倒塌的模拟中，实验验证了利用所提出的反演网络从雷达图重建介电常数图的可行性。
This paper developed a novel deep learning-based approach to processing ground-penetrating radar (GPR) radargrams to reconstruct the occluded interior spaces of collapsed structures and extract essential information such as survivable void spaces to assist search-and-rescue operations. The proposed method innovatively exploits a generative adversarial network (GAN) to augment synthetic GPR training data and an end-to-end deep learning model to invert a GPR radargram to a permittivity map of the cross-section that can be further interpreted to reconstruct the interior scenarios of collapsed structures. First, to address the lack of training data with correct labels, synthetic GPR radargrams were generated from simulated scenarios of collapsed structures. The GAN was applied to augment the realism of synthetic GPR radargrams for training, providing a new mechanism for preparing and augmenting data that is difficult to collect from a real disaster site. Second, instead of detecting and segmenting nonintuitive features in GPR radargrams, a new encoder-decoder structure was trained using the augmented GPR radargrams to directly reconstruct permittivity maps corresponding to the cross-sections of collapsed structures. The visual Turing test indicated that the GAN substantially improved the realism of synthetic GPR radargrams. The proposed GPR inversion method achieved anR2value of 0.93, a Mean Absolute Error (MAE) of 0.73, and a Structural Similarity Index Measure (SSIM) of 0.95 in inferring the material permittivity from synthetic radargrams. The predicted permittivity map was further used to identify void spaces, achieving an F1 score of 64.34%, a precision of 63.06%, and a recall of 71.84% at the pixel level. On the augmented radargrams, the network achieved anR2value of 0.76, an MAE of 1.49, and an SSIM of 0.89 in predicting the permittivity map. The void detection on augmented radargrams achieved an F1 score of 45.20%, a precision of 45.35%, and a recall of 53.99% at the pixel level. The feasibility of using the proposed inversion network to reconstruct permittivity maps from radargrams is also experimentally tested and demonstrated in simulations of two multistory building collapses.