FoSp: Focus and Separation Network for Early Smoke Segmentation
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 6621-6629
Abstract
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 smoke segmentation datasets: SYN70K (mIoU: 83.00%), SMOKE5K (F_beta: 81.6%) and SmokeSeg (F_beta: 72.05%). The code can be found at https://github.com/LujianYao/FoSp.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- SmokeSeger: A Transformer-CNN Coupled Model for Urban Scene Smoke SegmentationIEEE Transactions on Industrial Informatics, 2023
- Cubic-cross convolutional attention and count prior embedding for smoke segmentationPattern Recognition, 2022
- STCNet: spatiotemporal cross network for industrial smoke detectionMultimedia Tools and Applications, 2022
- A survey and performance evaluation of deep learning methods for small object detectionExpert Systems with Applications, 2021
- A Gated Recurrent Network With Dual Classification Assistance for Smoke Semantic SegmentationIEEE Transactions on Image Processing, 2021
- A Wave-Shaped Deep Neural Network for Smoke Density EstimationIEEE Transactions on Image Processing, 2019
- Automatic Early Smoke Segmentation based on Conditional Generative Adversarial NetworksOptik, 2019
- Deep smoke segmentationNeurocomputing, 2019
- Early fire detection using convolutional neural networks during surveillance for effective disaster managementNeurocomputing, 2018
- Learning-Based Smoke Detection for Unmanned Aerial Vehicles Applied to Forest Fire SurveillanceJournal of Intelligent & Robotic Systems, 2018