用语言增强零样本方法，精准检测半透明气体泄漏。
LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset
- 融合背景减除与零样本检测，通过语言提示定位泄漏
- 在合成数据集上达到69%的交并比，显著优于基线
- 开源数据集和代码，适合气体检测与视觉语言研究者
气体泄漏带来重大安全隐患，传统人工检测效率低。现有机器学习方法受限于高质量公开数据集的缺乏。本文提出合成数据集SimGas，包含多样背景、干扰物体、多位置泄漏及精确分割标注。设计零样本方法，结合背景减除、零样本目标检测、过滤与分割，利用语言提示提升检测能力。实验表明，该方法在仅使用背景减除或零样本检测的基础上，交并比（IoU）达69%，显著提升。进一步分析了不同提示配置与阈值设置对性能的影响。在真实数据集GasVid上进行定性测试，结果良好。相关数据集、代码与完整结果已开源至https://github.com/weathon/Lang-Gas。
原文摘要 · Abstract (English)
Gas leakage poses a significant hazard that requires prevention. Traditionally, human inspection has been used for detection, a slow and labour-intensive process. Recent research has applied machine learning techniques to this problem, yet there remains a shortage of high-quality, publicly available datasets. This paper introduces a synthetic dataset, SimGas, featuring diverse backgrounds, interfering foreground objects, diverse leak locations, and precise segmentation ground truth. We propose a zero-shot method that combines background subtraction, zero-shot object detection, filtering, and segmentation to leverage this dataset. Experimental results indicate that our approach significantly outperforms baseline methods based solely on background subtraction and zero-shot object detection with segmentation, reaching an IoU of 69%. We also present an analysis of various prompt configurations and threshold settings to provide deeper insights into the performance of our method. Finally, we qualitatively (because of the lack of ground truth) tested our performance on GasVid and reached decent results on the real-world dataset. The dataset, code, and full qualitative results are available at https://github.com/weathon/Lang-Gas.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。