Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/GeoBigData/tatortot

Prototype for a simple image annotation tool
https://github.com/GeoBigData/tatortot

Last synced: about 1 month ago
JSON representation

Prototype for a simple image annotation tool

Host: GitHub
URL: https://github.com/GeoBigData/tatortot
Owner: GeoBigData
License: mit
Archived: true
Created: 2019-10-16T18:18:56.000Z (over 4 years ago)
Default Branch: master
Last Pushed: 2019-11-06T20:33:45.000Z (over 4 years ago)
Last Synced: 2024-02-07T12:45:15.807Z (5 months ago)
Language: Python
Size: 33.2 KB
Stars: 0
Watchers: 3
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- Changelog: HISTORY.rst
- Contributing: CONTRIBUTING.rst
- License: LICENSE

Lists

awesome-earthobservation-code - tatortot - Prototype for a simple image annotation tool `Python` (`Python` processing of optical imagery (non deep learning) / Processing imagery - post processing)

README

# Tatortot
Prototype tool for annotating images.

This package includes one CLI tool:

**tator:**
```
Usage: tator [OPTIONS] SRC DEST

Options:
-C, --overlay_color TEXT Color to use for overlay. Valid options are: 'b
lue','orange','green','red','purple','brown','p
ink','gray','olive','cyan'.Defualt: 'cyan'.
-A, --overlay_alpha FLOAT Transparency to use for overlay provided as
alpha value (0-1).Default: 0.3.
-w, --img_width INTEGER Width of src images in pixels. Default is 256
-h, --img_height INTEGER Height of src images in pixels. Default is 256
-W, --viewer_width INTEGER Width of viewer in pixels. Default is 325
-H, --viewer_height INTEGER Height of viewer in pixels. Default is 800
-f, --filetype TEXT File format for src images (as file extension).
Default is '.jpeg'
--help Show this message and exit.

Note: SRC and DEST should both be local directories. SRC should contain images to annotate, DEST will store results.
```

This utility provides a simple interface for performing image annotation, and specifically defining binary semantic segmentation.

------------
## TODOS:
- [x] r/w from rasterio instead of skimage
- [ ] refactor to make code simpler, add docs
- [ ] add box selector feature?
- [ ] r/w from S3 directories as well as local dirs

------------
## Installation

### Development
#### Requirements:
- General requirements listed above
- Anaconda or Miniconda

#### To set up your local development environment:
This will install the s1_preprocessor package from the local repo in editable mode.
Any changes to Python files within the local repo should immediately take effect in this environment.

1. Clone the repo
`git clone https://github.com/GeoBigData/tatortot.git`

2. Move into the local repo
`cd tatortot`

3. Create conda virtual environment
`conda env create -f environment.yml`

4. Activate the environment
`conda activate tatortot`

5. Install Python package
`pip install -r requirements_dev.txt`

### Common Issues:
- TBD