Road extraction from satellite and aerial image using SE-Unet

Sofla, Reza Akbari Dotappeh; Alipour-Fard, T.; Arefi, Hossein

doi:10.1117/1.jrs.15.014512

Cited by 17 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, there are several applications of the U-Net architecture in UAV image analyses: delineation and classification of tree species [26], identification of plant communities [27] and prediction of cover fraction of plant species [28]. One application of a U-Net architecture, which is similar to the application addressed in this paper, is the extraction of roads from aerial images using a U-Net extended by residual units in the encoding part of the network [29]or U-Net extended by SE-blocks highlighting only useful channels [30].…”

Section: Related Researchmentioning

confidence: 99%

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

et al. 2021

View full text Add to dashboard Cite

The increasing number of severe storm events is threatening European forests. Besides the primary damages directly caused by storms, there are secondary damages such as bark beetle outbreaks and tertiary damages due to negative effects on the market. These subsequent damages can be minimized if a detailed overview of the affected area and the amount of damaged wood can be obtained quickly and included in the planning of clearance measures. The present work utilizes UAV-orthophotos and an adaptation of the U-Net architecture for the semantic segmentation and localization of windthrown stems. The network was pre-trained with generic datasets, randomly combining stems and background samples in a copy–paste augmentation, and afterwards trained with a specific dataset of a particular windthrow. The models pre-trained with generic datasets containing 10, 50 and 100 augmentations per annotated windthrown stems achieved F1-scores of 73.9% (S1Mod10), 74.3% (S1Mod50) and 75.6% (S1Mod100), outperforming the baseline model (F1-score 72.6%), which was not pre-trained. These results emphasize the applicability of the method to correctly identify windthrown trees and suggest the collection of training samples from other tree species and windthrow areas to improve the ability to generalize. Further enhancements of the network architecture are considered to improve the classification performance and to minimize the calculative costs.

show abstract

Section: Related Researchmentioning

confidence: 99%

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The organizing of mountain roadways needs construction projects such as cutting or digging slopes that will change and weaken the primary geological structure [32]. The road distance is a primary factor to be considered in planning landslide zone projections.…”

Section: Roadmentioning

confidence: 99%

Landslide Vulnerability Assessment in Devikulam Taluk, Idukki District, Kerala Using Gis and Machine Learning Algorithms

Gururajan¹,

Jawaharlal²

2021

Preprint

View full text Add to dashboard Cite

Landslide is a chronic problem that causes severe geographical hazard due to development activities and exploitation of the hilly region and it occurs due to heavy and prolongs rain flow in the mountainous area. Initially, a total of 726 locations were identified at devikulam taluk, Idukki district (India). These landslide potential points utilised to construct a spatial database. Then, the geo spatial database is then split randomly into 70% for training the models and 30% for the model validation. This work considers Seven landslide triggering factors for landslide susceptibility mapping. The susceptibility maps were verified using various evaluation metrics. The metrics are sensitivity, specificity, accuracy, precision, Recall, Matthews correlation efficient (MCE), Area Under the Curve (AUC), Kappa statistics, Mean Absolute Error (MAE), Mean Square Error (MSE).The proposed work with 5 advanced machine learning approaches assess the landslide vulnerability.It includes Logistic Regression (LR), K Nearest Neighbor (KNN), Decision tree classifier, Linear Discriminant Analysis (LDA) and Gaussian Naïve Bayes modelling and comparing their performance for the spatial forecast of landslide possibilities in the Devikulam taluk. In experimental results, Decision tree classifier performs the most reliable performance with an overall accuracy rate of 99.21%.

show abstract

“…For PV detection with segmentation methods, accurate segmentation of multi-spectral satellite remote sensing images using end-to-end deep learning methods remains a challenge. The classical semantic segmentation model U-Net 12 has proven to be advantageous in multi-spectral satellite image segmentation and has been widely used in applications, such as road segmentation, 13 burned area mapping, 14 , 15 and cloud masking 16 . In this study, we propose the E-UNET network structure enhanced from the classical U-Net 12 structure to detect PV facilities from Sentinel-2 11 multi-spectral remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

Automatic detection of photovoltaic facilities from Sentinel-2 observations by the enhanced U-Net method

Dui

Huang

Jin

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

With the enactment of supportive government policies and the increasing maturity of solar photovoltaic (PV) technologies, solar PV energy has become the most cost-effective new energy resource worldwide. Geospatial information on existing solar PV power systems is necessary to manage and optimize the deployment of new PV facilities. In this study, we propose a new deep-learning network, named the enhanced U-Net (E-UNET), to detect PV facilities from Sentinel-2 multi-spectral remote sensing data. Our E-UNET features an enhanced encoderdecoder structure that can efficiently extract spectral and spatial features simultaneously by combining a multi-spectral three-dimensional convolution path and a multi-scale pooling block. We compare the performance of the E-UNET with other semantic segmentation deep-learning networks and a pixel-based random forest classifier. The experimental results show that the E-UNET performs better than the other methods. It achieves an overall accuracy, Matthews correlation coefficient, F1, kappa coefficient, and recall of 0.989, 0.862, 0.869, 0.934, and 0.875, respectively. The experimental results also indicate that the E-UNET accurately detects PV facilities from various complex environments with high accuracy in terms of PV integrity and details.

show abstract

Road extraction from satellite and aerial image using SE-Unet

Cited by 17 publications

References 0 publications

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

Landslide Vulnerability Assessment in Devikulam Taluk, Idukki District, Kerala Using Gis and Machine Learning Algorithms

Automatic detection of photovoltaic facilities from Sentinel-2 observations by the enhanced U-Net method

Contact Info

Product

Resources

About