Semi-supervised learning for improved post-disaster damage assessment from satellite imagery

Oludare, Victor; Kezebou, Landry; Panetta, Karen; Agaian, Sos С.

doi:10.1117/12.2586232

Cited by 7 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Completeness measures the proportion of correctly extracted buildings over real buildings, which is also called recall [71,90], and is defined as Formula (7). Correctness measures the proportion of the correctly extracted buildings over the extracted buildings, also called precision [71,90], and is defined as Formula (8).…”

Section: Test Data and Evaluation Metricsmentioning

confidence: 99%

“…Building rooftop extraction plays a significant role in assessing the deployment space of photovoltaic facilities [1], estimating building energy consumption and emissions [2], urban management [3], disaster management [4][5][6][7], population estimation [8], three-dimensional reconstruction [9][10][11][12] and many other applications. However, to date, achieving automatic and accurate building extraction from remotely sensed data remains an unsolved problem in computer vision and remote sensing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Building Extraction from Multimodal Aerial Data Based on Accurate Vegetation Removal and Image Feature Consistency Constraint

et al. 2022

View full text Add to dashboard Cite

Accurate building extraction from remotely sensed data is difficult to perform automatically because of the complex environments and the complex shapes, colours and textures of buildings. Supervised deep-learning-based methods offer a possible solution to solve this problem. However, these methods generally require many high-quality, manually labelled samples to obtain satisfactory test results, and their production is time and labour intensive. For multimodal data with sufficient information, extracting buildings accurately in as unsupervised a manner as possible. Combining remote sensing images and LiDAR point clouds for unsupervised building extraction is not a new idea, but existing methods often experience two problems: (1) the accuracy of vegetation detection is often not high, which leads to limited building extraction accuracy, and (2) they lack a proper mechanism to further refine the building masks. We propose two methods to address these problems, combining aerial images and aerial LiDAR point clouds. First, we improve two recently developed vegetation detection methods to generate accurate initial building masks. We then refine the building masks based on the image feature consistency constraint, which can replace inaccurate LiDAR-derived boundaries with accurate image-based boundaries, remove the remaining vegetation points and recover some missing building points. Our methods do not require manual parameter tuning or manual data labelling, but still exhibit a competitive performance compared to 29 methods: our methods exhibit accuracies higher than or comparable to 19 state-of-the-art methods (including 8 deep-learning-based methods and 11 unsupervised methods, and 9 of them combine remote sensing images and 3D data), and outperform the top 10 methods (4 of them combine remote sensing images and LiDAR data) evaluated using all three test areas of the Vaihingen dataset on the official website of the ISPRS Test Project on Urban Classification and 3D Building Reconstruction in average area quality. These comparative results verify that our unsupervised methods combining multisource data are very effective.

show abstract

Section: Test Data and Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Unsupervised Building Extraction from Multimodal Aerial Data Based on Accurate Vegetation Removal and Image Feature Consistency Constraint

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Perform Segmentation based experiments: SemSegLoss code implementation is easy to follow which allowed applications to use the code implementation of loss functions for their segmentation based experiments. For example, cardiac function assessment in embryonic zebrafish [19], analyzing natural disaster aftermath from satellite images [20], and wildfire detection [21] In all listed use-cases, the results obtained using SemSegLoss GitHub code implementation have provided researchers the ability to do choose the correct loss function to improve the models' performance.…”

Section: Type Loss Functionmentioning

confidence: 99%

SemSegLoss: A python package of loss functions for semantic segmentation

Jadon

2021

Software Impacts

View full text Add to dashboard Cite

“…These methods have been used for several applications, including semantic image segmentation [28], and they are shown to improve predictive accuracy with additional unlabeled data in image classification frameworks [29,30]. In [31], the authors have also shown the superior performance of semi-supervised learning for post-disaster building damage assessment via pre-and post-event satellite imagery.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Learning Method for the Augmentation of an Incomplete Image-Based Inventory of Earthquake-Induced Soil Liquefaction Surface Effects

Asadi,

Baise,

Sanon

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Soil liquefaction often occurs as a secondary hazard during earthquakes and can lead to significant structural and infrastructure damage. Liquefaction is most often documented through field reconnaissance and recorded as point locations. Complete liquefaction inventories across the impacted area are rare but valuable for developing empirical liquefaction prediction models. Remote sensing analysis can be used to rapidly produce the full spatial extent of liquefaction ejecta after an event to inform and supplement field investigations. Visually labeling liquefaction ejecta from remotely sensed imagery is time-consuming and prone to human error and inconsistency. This study uses a partially labeled liquefaction inventory created from visual annotations by experts and proposes a pixel-based approach to detecting unlabeled liquefaction using advanced machine learning and image processing techniques, and to generating an augmented inventory of liquefaction ejecta with high spatial completeness. The proposed methodology is applied to aerial imagery taken from the 2011 Christchurch earthquake and considers the available partial liquefaction labels as high-certainty liquefaction features. This study consists of two specific comparative analyses. (1) To tackle the limited availability of labeled data and their spatial incompleteness, a semi-supervised self-training classification via Linear Discriminant Analysis is presented, and the performance of the semi-supervised learning approach is compared with supervised learning classification. (2) A post-event aerial image with RGB (red-green-blue) channels is used to extract color transformation bands, statistical indices, texture components, and dimensionality reduction outputs, and performances of the classification model with different combinations of selected features from these four groups are compared. Building footprints are also used as the only non-imagery geospatial information to improve classification accuracy by masking out building roofs from the classification process. To prepare the multi-class labeled data, regions of interest (ROIs) were drawn to collect samples of seven land cover and land use classes. The labeled samples of liquefaction were also clustered into two groups (dark and light) using the Fuzzy C-Means clustering algorithm to split the liquefaction pixels into two classes. A comparison of the generated maps with fully and manually labeled liquefaction data showed that the proposed semi-supervised method performs best when selected high-ranked features of the two groups of statistical indices (gradient weight and sum of the band squares) and dimensionality reduction outputs (first and second principal components) are used. It also outperforms supervised learning and can better augment the liquefaction labels across the image in terms of spatial completeness.

show abstract

Semi-supervised learning for improved post-disaster damage assessment from satellite imagery

Cited by 7 publications

References 0 publications

Unsupervised Building Extraction from Multimodal Aerial Data Based on Accurate Vegetation Removal and Image Feature Consistency Constraint

Unsupervised Building Extraction from Multimodal Aerial Data Based on Accurate Vegetation Removal and Image Feature Consistency Constraint

SemSegLoss: A python package of loss functions for semantic segmentation

Semi-Supervised Learning Method for the Augmentation of an Incomplete Image-Based Inventory of Earthquake-Induced Soil Liquefaction Surface Effects

Contact Info

Product

Resources

About