Urban fugitive dust emission is an open pollution source that enters the atmosphere because of the dust on the ground being lifted by the wind or human activities. Dust pollution is a major contributor to atmospheric particulate matter, making it a focus for pollution control and environmental surveillance stakeholders. The identification and monitoring of dust sources hold profound practical implications. The use of remote sensing detection method facilitates extensive coverage, high accuracy, and non-invasive monitoring of urban fugitive dust emission sources. This approach enables timely alerts about potential air pollution threats, allowing swift interventions to alleviate adverse consequences. This paper mainly studies the semantic segmentation of fugitive dust sources from remote sensing images, employing advanced deep learning algorithms. In this paper, we selected Wuhai City in China as the experimental area and created Wuhai Dust Sources Dataset. This dataset, established through high-resolution satellite remote sensing data from Gaofen-1 satellite, contains 2,648 images, capturing 707 distinct dust sources. This work evaluates four different deep learning models utilising FCN and U-Net architectures as backbones in conjunction with a variety of feature extraction convolutional neural networks. The experimental results exhibit promising detection outcomes for all four models. Among these, the U-Net combined with VGG feature extraction network has the best performance, achieving an MIoU at 81% and a Mean Precision at 92%.
Petroleum and gas pipelines, comprising petroleum and gas pipes and related components, play an irreplaceable role in petroleum and gas transportation. For global economic growth, petroleum and gas are crucial natural resources. However, the pipelines often cross permafrost regions with challenging working conditions. Additionally, the potential for natural disasters raises concerns about pipeline accidents, posing a threat to pipeline operational safety. In response to the complexity of pipeline supervision and management, we choose to use remote sensing method combining deep learning-based algorithms. In this work, we build a petroleum and gas pipes dataset, which includes 1,388 remote sensing images and the study area is Russian polar regions. We trained FCN and U-Net deep learning models by using our self-built dataset for the detection of petroleum and gas pipes. Models’ performances were evaluated using MIoU (Mean Intersection over Union), mean precision, mean recall to evaluate the accuracy of the model’s prediction results and compared them visually with ground truth. Our results find that deep learning models can effectively learn the characteristics of pipelines and achieve ideal detection results on our dataset. The MIoU of the FCN model achieved 0.885 and the U-Net model achieved 0.894. The results demonstrate that our trained models can be used to accurately identify the petroleum and gas pipelines in remote sensing images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.