2021
DOI: 10.1016/j.apenergy.2021.117085
|View full text |Cite
|
Sign up to set email alerts
|

Lunar features detection for energy discovery via deep learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 13 publications
(11 citation statements)
references
References 23 publications
0
11
0
Order By: Relevance
“…This section experiments with different networks, including UNet [26], ResUnet [35], GLNet [24], HRNet [23], and GL-HRNet. There were 30,000 training images, 3000 verification images, and 3000 test images.…”
Section: Analysis Of the Lunar Impact Crater Detection Resultsmentioning
confidence: 99%
See 3 more Smart Citations
“…This section experiments with different networks, including UNet [26], ResUnet [35], GLNet [24], HRNet [23], and GL-HRNet. There were 30,000 training images, 3000 verification images, and 3000 test images.…”
Section: Analysis Of the Lunar Impact Crater Detection Resultsmentioning
confidence: 99%
“…In this paper, four kinds of different data sets were used for experiments: lunar digital elevation data SLDEM [29], Mars HRSC MOLA Blend DEM Global 200 m v2, Surface crack [30], and an assembled dataset [23]. The SLDEM data have a resolution of 59 m and span ±60 • latitude (maximum longitude range).…”
Section: Datasetmentioning
confidence: 99%
See 2 more Smart Citations
“…Recently, deep learning has demonstrated high prediction accuracy in computer vision tasks [25] as well as in computational biology [26,27,28]. A simple neural network can obtain very complex underlying features, which is especially suitable for large-scale data sets and sparse dimension cases.…”
Section: Introductionmentioning
confidence: 99%