Automatic Early Smoke Segmentation based on Conditional Generative Adversarial Networks

Jia, Yang; Du, Hanrong; Wang, Haijuan; Yu, Runyang; Fan, Lianghui; Xu, Guizhi; Zhang, Qixing

doi:10.1016/j.ijleo.2019.05.085

Cited by 19 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And many of them (Yuan et al 2019a(Yuan et al ,b, 2021 have only been quantitatively evaluated on synthetic datasets. Despite some methods (Jia et al 2019;Wang et al 2014) claiming to address early smoke, they still rely on images of regular smoke. Therefore, the existing smoke segmentation methods are not capable of effectively addressing the issue of early smoke.…”

Section: Related Workmentioning

confidence: 99%

FoSp: Focus and Separation Network for Early Smoke Segmentation

Yao,

Zhao,

Peng

et al. 2024

AAAI

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

FoSp: Focus and Separation Network for Early Smoke Segmentation

Yao,

Zhao,

Peng

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…The nascent smoke is hard to be discovered both because of its light color, bad contrast with the background, and the distance [49]. Besides, since there is no benchmark (as different groups own different private data sets and can not build up each other), the instance number of existing early smoke data sets is limited [42] [50] [51], this fact makes the research even more difficult.…”

Section: A) Early Smoke Detectionmentioning

confidence: 99%

AI-Enhanced Gas Flares Remote Sensing and Visual Inspection: Trends and Challenges

Radi,

Li,

Boumaraf

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The real-time analysis of gas flares is one of the most challenging problems in the operation of various combustion-involving industries, such as oil and gas refineries. Despite the crucial role of gas flares in securing safe plant operation and lowering environmental pollution, they are among the least monitored components of petrochemical plants due to their harsh working environments. Remote sensing techniques are emerging as potential alternatives for conventional sampling-based techniques in visual inspection and performance analysis. This paper presents an in-depth review of significant achievements in Gas flares monitoring over past two decades and highlights ongoing challenges in Artificial Intelligence (AI)enhanced remote inspection. By reading the content, both industry professionals and academic researchers can gain a comprehensive knowledge of improvements from the integration of AI and remote sensing, understanding the trend of Gas flares monitoring. The paper commences with an analysis of RGB camerabased methods, focusing on how their combination with cutting-edge machine learning and deep learning algorithms can significantly improve the detection, segmentation, and measurement of gas flare systems. It then explores the use of hyper-spectral imaging techniques, including infrared cameras and space-borne satellite sensors, underscoring their potential in remote monitoring and performance analysis. Additionally, the effectiveness of multi-view inspection methods is assessed, highlighting how these approaches enhance the monitoring capabilities. Finally, the paper identifies key research areas that require further attention. It also presents a clearer direction for future progress, emphasizing the importance of continuous research to foster advancements and facilitate broader commercial adoption.

show abstract

“…For fire detection in spacious buildings with high ceilings, such as warehouses, factories, airports, and atrium buildings; forests; and grasslands, it will be difficult to install traditional fire detectors to detect fire events [1,2]. Video-based fire detection has become a prospective solution for fire protection in spacious buildings, forests, and grasslands [3][4][5] due to its advantages, such as being untouchable, not limited to the height of installation, fast response, and large view scope.…”

Section: Introductionmentioning

confidence: 99%

Fully Synthetic Videos and the Random-Background-Pasting Method for Flame Segmentation

et al. 2023

Self Cite

View full text Add to dashboard Cite

Video-based flame detection (VFD) aims to recognize fire events by using image features. Flame segmentation is an essential task in VFD, providing suspected regions for feature analysis and object recognition. However, the lack of positive flame samples makes it difficult to train deep-learning-based VFD models effectively. In this paper, we propose the assumption that we can train a segmentation model with virtual flame images and design experiments to prove it. We collected many virtual flame videos to extend existing flame datasets, which provide adequate flame samples for deep-learning-based VFD methods. We also apply a random-background-pasting method to distribute the flame images among different scenarios. The proposed method trains a flame segmentation model with zero real flame images. Moreover, we perform segmentation testing using real flame images, which the model has never used, to see if the model trained using ‘fake’ images can segment real objects. We trained four segmentation models based on FCN, U-Net, Deeplabv3, and Mask-RCNN using synthetic flame video frames and obtained the highest mPA of 0.783 and mIoU of 0.515. The experimental results on the FIRE-SMOKE-DATASET and the Fire-Detection-Image-Dataset demonstrate that the ‘fake’ flame samples generated by the proposed random-background-pasting method can obviously improve the performance of existing state-of-the-art flame segmentation methods using cross-dataset evaluation settings.

show abstract

Automatic Early Smoke Segmentation based on Conditional Generative Adversarial Networks

Cited by 19 publications

References 10 publications

FoSp: Focus and Separation Network for Early Smoke Segmentation

FoSp: Focus and Separation Network for Early Smoke Segmentation

AI-Enhanced Gas Flares Remote Sensing and Visual Inspection: Trends and Challenges

Fully Synthetic Videos and the Random-Background-Pasting Method for Flame Segmentation

Contact Info

Product

Resources

About