Recognition and Mapping of Landslide Using a Fully Convolutional DenseNet and Influencing Factors

Xiao, Gao; Chen, Tao; Niu, Ruiqing

doi:10.1109/jstars.2021.3101203

Cited by 51 publications

(22 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications of the fully convolutional network (FCN) [36] and U-Net [37] for landslide detection have been demonstrated by [38] and built upon by many studies using different variants of these models. For instance, the U-Net and ResU-Net models have been compared by Gao et al [39] and Ghorbanzadeh et al [5] for mapping landslides using Landsat-8 OLI and Sentinel-2 images, respectively. The latter study has performed 48 different scenarios to evaluate the generalization and transferability of these models for landslide detection in case studies in three different areas of Eastern Iburi, Shuzheng Valley, and Western Taitung County.…”

Section: Prior Workmentioning

confidence: 99%

“…To the best of our knowledge, most of the implemented and developed DL models have been evaluated in a local geographical region, typically covering a small area divided into training and testing areas using different ratios [5]. Therefore, the direct applicability of these models to a novel unexplored geographical region, mainly in emergency cases, is usually unclear [4], [39]. Also, DL models are adequately trained when an extensive training dataset with annotated landslides is used to learn effective models with several different parameters.…”

Section: Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

Ghorbanzadeh,

Xu,

Ghamis

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: Prior Workmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

Ghorbanzadeh,

Xu,

Ghamis

et al. 2022

Preprint

View full text Add to dashboard Cite

“…Thanks to the pixel-level object annotation capability, semantic segmentation has been widely used for various object detection applications. A study [16] used FC-DenseNet for landslide detection for the photos taken by satellites in the aftermath of earthquakes. However, their target objects are limited to the landslide regions and the satellite images can not be used for automobile navigation.…”

Section: B Semantic Segmentation-based Object Detectionmentioning

confidence: 99%

Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones

Zelek

Jeon

2022

IEEE Access

View full text Add to dashboard Cite

The role of unmanned vehicles for searching and localizing the victims in disaster impacted areas such as earthquake-struck zones is getting more important. Self-navigation on an earthquake zone has a unique challenge of detecting irregularly shaped obstacles such as road cracks, debris on the streets, and water puddles. In this paper, we characterize a number of state-of-the-art Fully Convolutional Network (FCN) models on mobile embedded platforms for self-navigation at these sites containing extremely irregular obstacles. We evaluate the models in terms of accuracy, performance, and energy efficiency. We present a few optimizations for our designed vision system. Lastly, we discuss the trade-offs of these models for a couple of mobile platforms that can each perform self-navigation. To enable vehicles to safely navigate earthquake-struck zones, we compile a new annotated image database of various earthquake impacted regions that is different than traditional road damage databases. We train our database with a number of state-of-the-art semantic segmentation models in order to identify obstacles unique to earthquake-struck zones. Based on the statistics and tradeoffs, an optimal FCN model is selected and applied to the mobile vehicular platforms. To our best knowledge, this is the first study that identifies unique challenges and discusses the accuracy, performance, and energy impact of edge-based self-navigation mobile vehicles for earthquake-struck zones. Our proposed database and trained models are publicly available.INDEX TERMS Convolutional Neural Networks, Edge Computing, Self Driving, Semantic Segmentation I. INTRODUCTIONWith global-wide monitoring and technology evolution, the riskiness of natural disaster is getting lower. However, there are still deadly incidents such as earthquakes. Earthquakes are a geologic inevitability of some countries and states. To reduce the effects from earthquakes, we should think about the ways to quickly search earthquake-struck zones and safely rescue more lives. For this purpose, unmanned autonomous vehicles will be effective, which navigate impacted sites while localizing the people and reporting the damages without risking the lives of others, such as firefighters and other rescue workers. In the natural disaster impacted sites, edge-based small automobiles would be more cost effective and feasible solutions because these small cars can navigate underneath collapsed buildings, unstable bridges, and narrow walkways that are difficult to be driven in by a full-sized vehicle, and also hidden from the viewing angles of aerial solutions such as drones. Though the self-navigation research and industry has been quickly evolving, most of the solutions focus on detecting fairly regular-shaped objects such as hu-mans, buildings, and streets from a full-sized vehicle's perspective. However, these solutions cannot be directly applied to earthquake-struck zones because of the unique obstacles such as debris, cracks, and puddles on the streets, which the mobile edge vehicle perceive...

show abstract

“…Compared with ResNet, each layer in ResNet is only connected to the previous layer, while DenseNet is reflected in that each layer is directly connected to all previous layers, and each layer can obtain the gradient from the loss function. This operation can optimize the information flow and gradient of the whole network, which is easy to train and performs better on small datasets [79]. The structure of DenseNet can achieve better feature reuse and reduce the number of parameters.…”

Section: F Densely Connected Convolution Network (Densenet)mentioning

confidence: 99%

Landslide Detection Mapping Employing CNN, ResNet, and DenseNet in the Three Gorges Reservoir, China

Liu¹,

Chen²,

Niu³

2021

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

Self Cite

View full text Add to dashboard Cite

Landslide detection mapping (LDM) is the basis of the field of landslide disaster prevention; however, it has faced certain difficulties. The Three Gorges Reservoir area of the Yangtze River has been one of the most intensively evaluated areas for landslide prevention in the world, due to the high frequency of landslide disasters here. In this study, we constructed an accurate LDM model based on convolutional neural networks (CNNs), residual neural networks (ResNets), and dense convolutional neural networks (DenseNets) that considers 'ZY-3' high spatial resolution (HSR) data and conditioning factors (CFs). In this work, nineteen factors based on remote sensing (RS) images, topographical and geological data associated with historical landslide locations were randomly divided into training (70% of total) and testing (30%) datasets. The experimental results show that the accuracy (ACC) of these three LDM models is above 0.95, indicating that the deep neural networks (DNNs) aimed at landslide detection performed well. Furthermore, DenseNet with RS images and CFs can accurately detect landslides. Specifically, DenseNet with RS images and CFs outperforms the other five models by considering the accuracy evaluation indexes, which exhibited Kappa coefficient improvements of 0.01-0.04 and ACC improvements of 0.02%-0.3%. Among all the factors, elevation factor has a high importance of 0.727, which is the most important factors found in this landslide model construction experiment.

show abstract

Recognition and Mapping of Landslide Using a Fully Convolutional DenseNet and Influencing Factors

Cited by 51 publications

References 54 publications

Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones

Landslide Detection Mapping Employing CNN, ResNet, and DenseNet in the Three Gorges Reservoir, China

Contact Info

Product

Resources

About