不可见气体检测：一种 RGB-热红外交叉注意力网络与新基准
Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark
AI总结：
针对热红外气体泄漏检测纹理不足和数据稀缺问题，提出 RGB 辅助双流交叉注意力网络 RT-CAN，并构建含约 1.3K 标注图像的 Gas-DB 基准，性能达到 SOTA。
摘要：
各种化学气体在工业过程中的广泛使用，使得有必要采取有效措施防止其在运输和储存期间发生泄漏，因为这些气体具有高毒性。基于热红外的计算机视觉检测技术为识别气体泄漏区域提供了一种直接方法。然而，由于热红外图像纹理较少且缺乏开源数据集，高质量算法的开发一直具有挑战性。本文提出 RGB-Thermal Cross Attention Network（RT-CAN），该网络采用 RGB 辅助的双流网络架构，以整合来自 RGB 图像的纹理信息和来自热红外图像的气体区域信息。此外，为促进不可见气体检测研究，我们引入 Gas-DB，这是一个大规模开源气体检测数据库，包含约 1.3K 张具有良好标注的 RGB-热红外图像，涵盖八种不同采集场景。实验结果表明，我们的方法成功利用了两种模态的优势，在 RGB-热红外方法中达到 state-of-the-art（SOTA）性能，并在准确率、Intersection of Union（IoU）和 F2 指标上分别超过单流 SOTA 模型 4.86%、5.65% 和 4.88%。代码和数据可在 https://github.com/logic112358/RT-CAN 获取。
英文摘要：
The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity. Thermal infrared-based computer vision detection techniques provide a straightforward approach to identify gas leakage areas. However, the development of high-quality algorithms has been challenging due to the low texture in thermal images and the lack of open-source datasets. In this paper, we present the RGB-Thermal Cross Attention Network (RT-CAN), which employs an RGB-assisted two-stream network architecture to integrate texture information from RGB images and gas area information from thermal images. Additionally, to facilitate the research of invisible gas detection, we introduce Gas-DB, an extensive open-source gas detection database including about 1.3K well-annotated RGB-thermal images with eight variant collection scenes. Experimental results demonstrate that our method successfully leverages the advantages of both modalities, achieving state-of-the-art (SOTA) performance among RGB-thermal methods, surpassing single-stream SOTA models in terms of accuracy, Intersection of Union (IoU), and F2 metrics by 4.86%, 5.65%, and 4.88%, respectively. The code and data can be found at https://github.com/logic112358/RT-CAN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
