landuselandcovermultilabelclassification
https://github.com/0jaspreetsingh/landuselandcovermultilabelclassification
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: ieee.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: 0jaspreetsingh
- Language: Python
- Default Branch: main
- Size: 1.08 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
LandUseLandCoverMultiLabelClassification
This repository contains the code for INTER-REGION TRANSFER LEARNING FOR LAND USE LAND COVER CLASSIFICATION published in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.
Citation
If you find our work helpful, please consider citing our paper:
bibtex
@Article{isprs-annals-X-1-W1-2023-881-2023,
AUTHOR = {Siddamsetty, J. and Stricker, M. and Charfuelan, M. and Nuske, M. and Dengel, A.},
TITLE = {INTER-REGION TRANSFER LEARNING FOR LAND USE LAND COVER CLASSIFICATION},
JOURNAL = {ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
VOLUME = {X-1/W1-2023},
YEAR = {2023},
PAGES = {881--888},
URL = {https://isprs-annals.copernicus.org/articles/X-1-W1-2023/881/2023/},
DOI = {10.5194/isprs-annals-X-1-W1-2023-881-2023}
}
Motivation
Regular observation of the earth to tackle some of the following problems:
1. Understanding land use dynamics
2. Resource management
3. Urban planning
4. Environmental monitoring
5. Disaster risk reduction
Dataset Description
12 Bands
Bands and pixel resolution in meters:
60 Meter (20 x 20 pixels) - B01: Coastal aerosol | B09: Water vapor
10 Meter (120 x 120 pixels) - B02: Blue | B03: Green | B04: Red | B08: NIR
20 Meter (60 x 60 pixels) - B05: Vegetation red edge | B06: Vegetation red edge | B07: Vegetation red edge | B8A: Narrow NIR | B11: SWIR | B12: SWIR
https://bigearth.net/static/documents/Description_BigEarthNet-S2.pdf
https://www.tensorflow.org/datasets/catalog/bigearthnet
Few examples
Preprocessing using Datadings
Accessing tiny files in separate directories is slow.
Accessing data over the network attached storage slows this further.
Converting Train, Test and Val splits to datadings files for faster training.
Link: https://datadings.readthedocs.io/en/latest/index.html
3 Experiments
- Resizing all Bands to 120X120
- Intermediate Fusion
- Late Fusion
Classification Results
Deep Multi-Attention Driven Approach paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9096309
Owner
- Name: Jaspreet Singh
- Login: 0jaspreetsingh
- Kind: user
- Location: Germany
- Website: https://www.linkedin.com/in/0jaspreet/
- Repositories: 4
- Profile: https://github.com/0jaspreetsingh
Citation (CITATION.cff)
@Article{isprs-annals-X-1-W1-2023-881-2023,
AUTHOR = {Siddamsetty, J. and Stricker, M. and Charfuelan, M. and Nuske, M. and Dengel, A.},
TITLE = {INTER-REGION TRANSFER LEARNING FOR LAND USE LAND COVER CLASSIFICATION},
JOURNAL = {ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
VOLUME = {X-1/W1-2023},
YEAR = {2023},
PAGES = {881--888},
URL = {https://isprs-annals.copernicus.org/articles/X-1-W1-2023/881/2023/},
DOI = {10.5194/isprs-annals-X-1-W1-2023-881-2023}
}