Semantic Segmentation and Analysis on Sensitive Parameters of Forest Fire Smoke Using Smoke-Unet and Landsat-8 Imagery

Wang, Zewei; Yang, Pengfei; Liang, Haotian; Zheng, Change; Yin, Jun; Tian, Yongchao; Cui, Wei

doi:10.3390/rs14010045

Cited by 48 publications

(42 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is one of our fundamental research questions in this paper to address the need for using VIs as hand-crafted features, instead of end-to-end training. In [109], it has already been shown that adding the input of extra-bands causes an inference to the network parameter learning and this, in turn, causes a degradation of the network performance. We believe that even if the input of all band data can increase the global information, those extra bands may be insufficient to identify detailed small tree objects in the scene [110].…”

Section: B Resultsmentioning

confidence: 99%

Deep Semantic Segmentation of Trees Using Multispectral Images

Ülkü

Akagündüz

Ghamisi

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Forests can be efficiently monitored by automatic semantic segmentation of trees using satellite and/or aerial images. Still, several challenges can make the problem difficult, including the varying spectral signature of different trees, lack of sufficient labelled data, and geometrical occlusions. In this paper, we address the tree segmentation problem using multispectral imagery. While we carry out large-scale experiments on several deep learning architectures using various spectral input combinations, we also attempt to explore whether hand-crafted spectral vegetation indices can improve the performance of deep learning models in the segmentation of trees. Our experiments include benchmarking a variety of multispectral remote sensing image sets, deep semantic segmentation architectures, and various spectral bands as inputs, including a number of hand-crafted spectral vegetation indices. From our large-scale experiments, we draw several useful conclusions. One particularly important conclusion is that, with no additional computation burden, combining different categories of multispectral vegetation indices, such as NVDI, ARVI, and SAVI, within a single three-channel input, and using the state-of-the-art semantic segmentation architectures, tree segmentation accuracy can be improved under certain conditions, compared to using high-resolution visible and/or nearinfrared input.

show abstract

Section: B Resultsmentioning

confidence: 99%

Deep Semantic Segmentation of Trees Using Multispectral Images

Ülkü

Akagündüz

Ghamisi

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Data obtained from different platforms can provide diverse and complementary information [46]- [47]. The smoke datasets for optical satellite images mostly come from lowresolution multi-spectral images such as MODIS [48], Himawari-8 [49], LandSat-8 [50], and GOES-16 [51]. The lack of large-scale, open-source, high-resolution labeled datasets for segmentation restricts the development of smoke segmentation network models for high-resolution optical satellite imagery.…”

Section: B Deep-learning-based Smoke Segmentation Methodsmentioning

confidence: 99%

AOSVSSNet: Attention-Guided Optical Satellite Video Smoke Segmentation Network

Wang

Hong

Han

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Smoke is more observable than open fires. Optical satellite video has the advantages of a wide monitoring range, fast response speed, and good economy in large-scale surface smoke monitoring tasks. It can be used in wide-area forest wildfire monitoring, battlefield dynamic monitoring, disaster relief decision-making. The smoke segmentation method based on traditional handcrafted features is easily limited by the scene and data. This paper introduces the deep learning method to the optical satellite video smoke target segmentation. However, due to the lack of real smoke images and the blurred edges of smoke, there are currently few labeled datasets for smoke segmentation in high-resolution optical satellite imagery scenes, which cannot provide sufficient training data for deep learning models. The smoke image from the satellite perspective also has the characteristics of multi-scale features and ground object background interference. To solve the above problems, we construct a set of high-resolution optical satellite imagery smoke synthesis datasets based on the optical imaging process of smoke targets, which saves the cost of manual labeling. In addition, we design an attention-guided optical satellite video smoke segmentation network model (AOSVSSNet), which can effectively suppress the ground object background's false alarm and extract the smoke's multi-scale features. Synthetic data faces the transferability problem in real-world applications, so the physical constraints of the smoke imaging process are introduced into the loss function to improve the generalization of the model in real smoke data. The comprehensive evaluation results show that the method outperforms representative semantic segmentation networks.

show abstract

“…As a result of experiments, they achieved 82.2% IoU value and 90% accuracy for building segmentation. Wang et al [12] worked on removing the difficulties in early forest fire detection through satellite images. They stated that early forest fires could be mis-detected as clouds.…”

Section: Literature Reviewmentioning

confidence: 99%

Forest and Water Bodies Segmentation Through Satellite Images Using U-Net

Filatov¹,

Yar²

2022

Preprint

View full text Add to dashboard Cite

Global environment monitoring is a task that needs attention due to changing climate. This includes monitoring the rate of deforestation and areas affected by flooding. Satellite imaging has helped a lot in effectively monitoring the earth, and deep learning techniques have helped automate this monitoring process. This paper proposes a solution for observing the area covered by the forest and water. To achieve this task UNet model has been proposed, which is an image segmentation model. Our model achieved a validation accuracy of 82.55% and 82.92% for segmentation of areas covered by forest and water, respectively.

show abstract

Semantic Segmentation and Analysis on Sensitive Parameters of Forest Fire Smoke Using Smoke-Unet and Landsat-8 Imagery

Cited by 48 publications

References 43 publications

Deep Semantic Segmentation of Trees Using Multispectral Images

Deep Semantic Segmentation of Trees Using Multispectral Images

AOSVSSNet: Attention-Guided Optical Satellite Video Smoke Segmentation Network

Forest and Water Bodies Segmentation Through Satellite Images Using U-Net

Contact Info

Product

Resources

About