https://github.com/aurioldegbelo/smartlandmaps
Code for boundary extraction and vectorization used during the SmartLandMaps project
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
✓DOI references
Found 2 DOI reference(s) in README -
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.2%) to scientific vocabulary
Repository
Code for boundary extraction and vectorization used during the SmartLandMaps project
Basic Info
- Host: GitHub
- Owner: aurioldegbelo
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Size: 38.9 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
SmartLandMaps Digitization Software
This repository shows the code for boundary extraction and vectorization used during the SmartLandMaps project.
:wrench: Scripts
The scripts can be found in the /scripts folder.
- boundaryextractorblur202302 is useful to extract boundaries from the original image (raster-to-raster)
- vectorizergrass2023_02 is useful to generate polygons from the boundaries extracted (raster-to-vector)
- OCRcolab2023_02 helps to extract the stickers from the original image
- analyser202302 is useful for analyzing the results and gives feedback on the number of parcels or stickers that need editing
- joiner202303 merges ODK data with polygons by sticker ID
You can run the different modules independently. The SmartLandMaps_Notebook is a Colab Notebook that brings all the pieces together. Note that running the Notebook requires you to upload the dataset to be digitized to the Cloud (e.g. Google Drive) if you intend to run the software in Colab directly. Finally, we trained a unet-model and fine-tuned a segformer model for boundary extraction at the patch level. Both models can be found here and here respectively.
👩🏭👨🏭 Contributors
- Auriol Degbelo (Ideas & Implementation)
- Kaspar Kundert (Ideas & Testing)
- Claudia Linder (Ideas & Testing)
- Gergely Vassányi (Ideas & Implementation)
:clipboard: Documentation
- The SmartLandMaps approach and the key intuitions of the software modules: Lindner, C., Degbelo, A., Vassányi, G., Kundert, K. and Schwering, A. (2023) ‘The SmartLandMaps approach for participatory land rights mapping’, Land, 12(11). Available at: https://doi.org/10.3390/land12112043.
- FIG publications including:
- General introduction to the pillars of the SmartLandMaps approach
- Pilot study in Benin in 2022
- Pilot study in Chad and Sierra Leone in 2023
❔ Questions
You are most welcome to open an issue if you have a question. You can also get in touch with Auriol Degbelo.
Owner
- Name: Auriol Degbelo
- Login: aurioldegbelo
- Kind: user
- Website: https://sites.google.com/site/aurioldegbelo/
- Repositories: 2
- Profile: https://github.com/aurioldegbelo