2020
DOI: 10.1016/j.geomorph.2020.107045
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning-based approach for landform classification from integrated data sources of digital elevation model and imagery

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

3
71
1
1

Year Published

2020
2020
2023
2023

Publication Types

Select...
6

Relationship

2
4

Authors

Journals

citations
Cited by 119 publications
(76 citation statements)
references
References 58 publications
3
71
1
1
Order By: Relevance
“…Du et al ., 2019; Li et al ., 2020), optical imagery (e.g. Li et al ., 2020), vegetation indices (Mulder et al ., 2011), synthetic aperture radar (SAR) (Mulder et al ., 2011), or airborne radiometrics (e.g. Metelka et al ., 2018).…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Du et al ., 2019; Li et al ., 2020), optical imagery (e.g. Li et al ., 2020), vegetation indices (Mulder et al ., 2011), synthetic aperture radar (SAR) (Mulder et al ., 2011), or airborne radiometrics (e.g. Metelka et al ., 2018).…”
Section: Discussionmentioning
confidence: 99%
“…Zhang et al ., 2018) and landform classification (e.g. Li et al ., 2020). Previous successful applications which bear notable similarities to dune pattern mapping are the segmentation of blood vessels in retina images (e.g.…”
Section: Introductionmentioning
confidence: 99%
“…The deep‐learning method was used to learn class‐dependent discriminative features based on imagery and extract the check dam areas. Compared with traditional classification methods, this approach can automatically extract high‐level and representative features due to its multilayer network structure (Chen et al, 2019) and thus improve the classification accuracy (Li et al, 2020; Nogueira et al, 2017). This section is divided into two steps: preparation of the training data and construction of a deep convolutional neural network (DCNN).…”
Section: Methodsmentioning
confidence: 99%
“…We calculated the overall accuracy (OA) and kappa coefficient of the results based on a confusion matrix. These indices are commonly used to validate the accuracy of certain types of object polygons in matching ground truth data (Li et al, 2020; Lv et al, 2018). The rows and columns of the confusion matrix represent the predicted label and the ground truth, respectively.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation