A simple tool to process multispectral images from the Micasense RedEdge-P
Coming next:
- Pan sharpening algorithm
- Agisoft automated workflow
- Image annotation
SkySpectral is a simple tool for visualizing and processing multispectral imagery. It enables the alignment and combination of various sub-images (bands) to extract relevant data.
#Multispectral #Open-CV #Building diagnosis #ImageProcessing
The project is still in pre-release, so do not hesitate to send your recommendations or the bugs you encountered!
Processing multispectral image, from a folder
The functionalities include:
- Import Micasense output folder
- Visualize bands with standard matplotlib color palettes
- Align channels (R,G,B,NIR,Red-Edge) to Pan-chromatic with an intuitive interface (especially critical for close-shots, as in building façades analyses)
- Visualize composed shot (RGB image re-composed from individual channels, CIR - Color Infrared, etc.)
- Create custom indices based on arithmetic operations on bands
- Access typical vegetation indices such as NDVI
- Prepare the files for Agisoft Metashape (organize images in folders)
- ...
Creating custom indices
- Clone the repository:
git clone https://github.com/s-du/SkySpectral
- Navigate to the app directory:
cd SkySpectral
- Install the required dependencies:
pip install -r requirements.txt
- Run the app:
python main.py
Contributions to the app are welcome! If you find any bugs, have suggestions for new features, or would like to contribute enhancements, please follow these steps:
- Fork the repository.
- Create a new branch for your feature or bug fix.
- Make the necessary changes and commit them.
- Push your changes to your fork.
- Submit a pull request describing your changes.