Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau

Liu, Yang; Yao, Xin; Gu, Zhenkui; Zhou, Zhenkai; Liu, Xinghong; Chen, Xingming; Wei, Shangfei

doi:10.3390/rs14143362

Cited by 29 publications

(15 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the core prerequisite for employing AI models is a reliable dataset to be used for training. Recent studies have only focused on mapping landslides with AI but at scales that are small or regional while also claiming that the proposed models can cater towards rapid mapping of landslides at any given time, location and scale (Liu et al, 2022;Meena et al, 2022a;Nava, Monserrat, et al, 2022;Soares et al, 2022a;Tang et al, 2022;. However, seldom has been the case where truly an approach has been taken to map landslides outside the regions where the models are initially trained on, and also towards actually applying the proposed models in capturing and mapping event-based landslides that has recently occurred.…”

Section: Introductionmentioning

confidence: 99%

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

Meena

Nava²,

Bhuyan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. Multiple landslide events occur often across the world which has the potential to cause significant harm to both human life and property. Although a substantial amount of research has been conducted to address mapping of landslides using Earth Observation (EO) data, several gaps and uncertainties remain when developing models to be operational at the global scale. To address this issue, we present the HR-GLDD, a high resolution (HR) dataset for landslide mapping composed of landslide instances from ten different physiographical regions globally: South and South-East Asia, East Asia, South America, and Central America. The dataset contains five rainfall triggered and five earthquake-triggered multiple landslide events that occurred in varying geomorphological and topographical regions. HR-GLDD is one of the first datasets for landslide detection generated by high-resolution satellite imagery which can be useful for applications in artificial intelligence for landslide segmentation and detection studies. Five state-of-the-art deep learning models were used to test the transferability and robustness of the HR-GLDD. Moreover, two recent landslide events were used for testing the performance and usability of the dataset to comment on the detection of newly occurring significant landslide events. The deep learning models showed similar results for testing the HR-GLDD in individual test sites thereby indicating the robustness of the dataset for such purposes. The HR-GLDD can be accessed open access and it has the potential to calibrate and develop models to produce reliable inventories using high-resolution satellite imagery after the occurrence of new significant landslide events. The HR-GLDD will be updated regularly by integrating data from new landslide events.

show abstract

Section: Introductionmentioning

confidence: 99%

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

Meena

Nava²,

Bhuyan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These representations can then be expanded to the input dimensions, retaining only selected characteristics of the original image. In the field of InSAR processing, CNNs have previously been used to filter wrapped interferograms [44]- [46], to unwrap interferograms [47]- [49], and to detect deformation related to ground subsidence [50], [51], volcanic activity [52], [53], mining [47], [54], landslides [55], and earthquakes [56]. Chen et al [57] implemented a multi-layer perceptron neural network to remove elevation-dependent atmospheric noise from interferograms.…”

Section: B Atmospheric Noise Correction With Machine Learningmentioning

confidence: 99%

Removing Atmospheric Noise from InSAR Interferograms in Mountainous Regions with a Convolutional Neural Network

Brencher¹,

Henderson²,

Shean³

2023

Preprint

View full text Add to dashboard Cite

<p>Atmospheric errors in interferometric synthetic aperture radar (InSAR)-derived estimates of surface deformation often obscure real displacement signals, especially in mountainous regions. As climate change disproportionately impacts the mountain cryosphere, developing a technique for atmospheric correction that performs well in high-relief terrain is increasingly important. Here, we developed and implemented a statistical machine learning-based atmospheric correction that relies on the differing spatial and topographic characteristics of periglacial features and atmospheric noise. Our correction is applied at the native spatial and temporal resolution of the InSAR data (40 m, 12 days), does not require external atmospheric data, and can correct both stratified and turbulent atmospheric noise. Using Sentinel-1 data from 2015-2022, we trained a convolutional neural network (CNN) on atmospheric noise from 136 short-baseline interferograms and displacement signals from time-series inversion of 337 interferograms. The CNN correction was then tested on a densely connected network of 202 Sentinel-1 interferograms which were inverted to create a displacement time series. We used the Rocky Mountains in Colorado as our training, validation, and testing areas. When applied to our validation data, our correction offers a 690% improvement in performance over a global meteorological reanalysis-based correction and a 209% improvement over a high-pass filter correction. We found that our correction reveals previously hidden time-dependent kinematic behavior of three representative rock glaciers in our testing dataset. Our flexible, robust approach can be used to correct arbitrary InSAR data to analyze subtle surface deformation signals for a range of science and engineering applications. </p>

show abstract

“…One part is used by Backbone to extract features, and the other part is used by Head to classify, box regression and mask prediction for each ROI.So two architectures are proposed to generate corresponding masks, namely, the left and right are faster R-CNN/ResNet and R-CNN/FPN respectively, as shown in Fig. 2 [36]:…”

Section: Mask R-cnnmentioning

confidence: 99%

Art Portrait Design Based on Mobile Internet in Digital Media

Zhang¹

2023

J Multimed Inf Syst

View full text Add to dashboard Cite

With the improvement of people's living standards and art appreciation, more and more people are engaged in the design and collection of art portrait. At the same time, the development of new generation information technology, such as digital media and mobile internet, has also made art portrait design techniques more diverse and more rich artistic styles. However, facing a huge number of art portrait, the current management work is mainly carried out manually by professionals, with high people and financial costs. Therefore, it is of great significance to study the effective and correct design and management of art portrait and apply digital mobile technology to provide users with more accurate art portrait. For the demand of art portrait design, this paper takes print, oil painting, ink painting and watercolor painting as the research object, and proposes a deep learning model Mask R-CNN. Based on the multi-disciplinary fields such as deep neural network, digital media and art, this paper analyzes and studies an art portrait design system based on mobile internet. In the paper, the in-depth learning model Mask R-CNN is applied in the system. By comparing the accuracy of the training of Mask R-CNN and U-Net models, this paper analyzes the effectiveness of the two models in extracting art portrait features. In addition, Mask R-CNN model is applied to the art portrait design system based on mobile internet. The final experimental results show that the art portrait design system using Mask R-CNN model has higher prediction and detection accuracy and has better practicability for art portrait design and art communication.

show abstract

Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau

Cited by 29 publications

References 66 publications

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

Removing Atmospheric Noise from InSAR Interferograms in Mountainous Regions with a Convolutional Neural Network

Art Portrait Design Based on Mobile Internet in Digital Media

Contact Info

Product

Resources

About