Abstract
FlameFinder is a deep metric learning (DML) framework designed to accurately detect flames, even when obscured by smoke, using thermal images from firefighter drones during wildfire monitoring. Traditional RGB cameras struggle in such conditions, but thermal cameras can capture smoke-obscured flame features. However, they lack absolute thermal reference points, leading to false this http URL address this issue, FlameFinder utilizes paired thermal-RGB images for training. By learning latent flame features from smoke-free samples, the model becomes less biased towards relative thermal gradients. In testing, it identifies flames in smoky patches by analyzing their equivalent thermal-domain distribution. This method improves performance using both supervised and distance-based clustering metrics.The framework incorporates a flame segmentation method and a DML-aided detection framework. This includes utilizing center loss (CL), triplet center loss (TCL), and triplet cosine center loss (TCCL) to identify optimal cluster representatives for classification. However, the dominance of center loss over the other losses leads to the model missing features sensitive to them. To address this limitation, an attention mechanism is proposed. This mechanism allows for non-uniform feature contribution, amplifying the critical role of cosine and triplet loss in the DML framework. Additionally, it improves interpretability, class discrimination, and decreases intra-class variance. As a result, the proposed model surpasses the baseline by 4.4% in the FLAME2 dataset and 7% in the FLAME3 dataset for unobscured flame detection accuracy. Moreover, it demonstrates enhanced class separation in obscured scenarios compared to VGG19, ResNet18, and three backbone models tailored for flame detection.
Abstract (translated)
FlameFinder是一种深度 metric learning（DML）框架，旨在准确检测火焰，即使被烟雾遮挡，使用消防无人机在野火监测期间的热图像。传统 RGB 相机在这种条件下表现不佳，但热成像相机可以捕捉到烟雾遮蔽的火焰特征。然而，它们缺乏绝对热参考点，导致对 this http URL 地址的错误检测，FlameFinder利用成对的热-RGB图像进行训练。通过从无烟样本中学习潜在火焰特征，该模型对相对热梯度的偏见减少。在测试中，它通过分析它们的等效热域分布来检测野火中的火焰。这种方法通过使用监督和距离基于聚类的度量指标来提高性能。该框架包括火焰分割方法和 DML 辅助检测框架。这包括利用中心损失（CL）、三元组中心损失（TCL）和三元组余弦中心损失（TCCL）确定分类的最佳聚类代表。然而，中心损失对其他损失的主导地位导致模型错过对其敏感的特征。为解决这个问题，提出了一个关注机制。该机制允许非均匀特征贡献，突显在 DML 框架中余弦和三元组损失的关键作用。此外，它提高了可解释性、分类准确性和降低内部方差。因此，与基线相比，在 FLAME2 数据集上，所提出的模型提高了 4.4% 的检测准确性，而在 FLAME3 数据集上，它提高了 7% 的检测准确性。此外，在烟雾遮蔽的场景中，与 VGG19、ResNet18 和专为检测火焰的三个骨干模型相比，它展示了更高的类分离能力。
URL
https://arxiv.org/abs/2404.06653
