Early smoke segmentation (ESS) enables the accurate identification of smoke sources, facilitating the prompt extinguishing of fires and preventing large-scale gas leaks. But ESS poses greater challenges than conventional object and regular smoke segmentation due to its small scale and transparent appearance, which can result in high miss detection rate and low precision. To address these issues, a Focus and Separation Network (FoSp) is proposed. We first introduce a Focus module employing bidirectional cascade which guides low-resolution and high-resolution features towards mid-resolution to locate and determine the scope of smoke, reducing the miss detection rate. Next, we propose a Separation module that separates smoke images into a pure smoke foreground and a smoke-free background, enhancing the contrast between smoke and background fundamentally, improving segmentation precision. Finally, a Domain Fusion module is developed to integrate the distinctive features of the two modules which can balance recall and precision to achieve high F_beta. Futhermore, to promote the development of ESS, we introduce a high-quality real-world dataset called SmokeSeg, which contains more small and transparent smoke than the existing datasets. Experimental results show that our model achieves the best performance on three available datasets: SYN70K (mIoU: 83.00%), SMOKE5K (F_beta: 81.6%) and SmokeSeg (F_beta: 72.05%). Especially, our FoSp outperforms SegFormer by 7.71% (F_beta) for early smoke segmentation on SmokeSeg.

翻译：早期烟雾分割（ESS）能够准确识别烟雾源，有助于及时扑灭火灾并防止大规模气体泄漏。然而，由于早期烟雾尺度小且呈透明外观，ESS比传统物体分割和常规烟雾分割面临更大挑战，易导致高漏检率和低精度。为解决这些问题，本文提出聚焦与分离网络（FoSp）。首先，我们引入采用双向级联的聚焦模块，引导低分辨率与高分辨率特征向中等分辨率对齐，以定位并确定烟雾范围，从而降低漏检率。其次，提出分离模块，将烟雾图像分解为纯烟前景和无烟背景，从根本上增强烟与背景的对比度，提升分割精度。最后，开发域融合模块整合两个模块的独特特征，平衡召回率与精度，以实现高F_beta值。此外，为促进ESS发展，我们发布了名为SmokeSeg的高质量真实世界数据集，该数据集所含小尺度透明烟雾量超过现有数据集。实验结果表明，我们的模型在三个可用数据集上均取得最佳性能：SYN70K（mIoU: 83.00%）、SMOKE5K（F_beta: 81.6%）和SmokeSeg（F_beta: 72.05%）。尤其在SmokeSeg早期烟雾分割任务中，我们的FoSp相比SegFormer在F_beta指标上提升7.71%。