HyperBlend is a new type of hyperspectral image simulator based on Blender.

Overview

HyperBlend version 0.1.0

This is the HyperBlend leaf spectra simulator developed in Spectral Laboratory of University of Jyväskylä. You can use and modify this software under MIT licence.

Currently, HyperBlend can only simulate point-spectrometer-like spectral data. It needs actual measured reflectance and transmittance data which it tries to replicate.

Installing

Clone the repository to some location on your machine. Create a python environment by running conda env create -n hb --file hb_env.yml in yor anaconda command prompt when in project root directory. Use your favourite IDE for editing and running the code (developed using PyCharm). Command line build and run is untested, but it should work as well.

You will also need open-source 3D-modeling and rendering software Blender, which you can download and install from (blender.org). At least versions 2.8x and 2.9x should work (developed on version 2.93.5). Change your Blender executable path to constants.py.

Working principle

The measured reflectances and transmittances look like this:

wavelength [nm] reflectance transmittance
400 0.21435 0.26547
401 0.21431 0.26540
... ... ...

We call this the target. Reflectance and transmittance values represent the fraction of reflected and transmitted light so both values are separately bound to closed interval [0,1] and their sum cannot exceed 1.

We use a Blender scene with a rectangular box that represents a leaf. The material of the leaf has four adjustable parameters: absorption particle density, scattering particle density, scattering anisotropy, and mix factor. These control how the light is scattered and absorbed in the leaf material.

For each wavelength in the target, we adjust the leaf material parameters until the modeled reflectance and transmittance match the target values.

Usage

The entry point of the software is __main__.py file. For testing the software without actual data, run

from src import presets

presets.optimize_default_target()

that uses hard-coded test spectrum of a leaf.

The base element of the software is a measurement set identified by set_name, which consists of one or more samples identified by sample_id. To initialize a new set, initialize an Optimization object which will create a directory structure for given set_name under optimization directory.

To use real measured data, you should use

data.toml_handling.write_target(set_name:str, data, sample_id=0)

where data is a list of wavelength, reflectance, transmittance 3-tuples (or lists). This will write the data to disk in human-readable toml-formatted form that the rest of the code can understand.

Now you can start the optimization process. To summarize a simple use case in one snippet:

from src.optimization import Optimization
from data import toml_handlling as TH

data = [[400, 0.21435, 0.26547], [401, 0.21431, 0.26540]]
set_name = 'test_set'

o = Optimization(set_name)
TH.write_target(set_name, data, sample_id=0)
o.run_optimization()

The results are written onto disk in the set's directory as toml files and plotted to .png images.

Project structure, i.e., where to find stuff

Descriptions of the most important files.

  • optimization Optimization results and targets are stored here in set-wise sub-directories.
  • src Top level source code package.
    • __main__.py Entrypoint of the software.
    • constants.py Mainly names of things that should not be changed unless you are sure what you are doing. With the exception of path to Blender executable that you have to change to match your installation.
    • optimization.py Optimization work is done here.
    • plotter.py Responsible for plotting the results.
    • presets.py Default runnable example with hard-coded spectral values.
    • data Package responsible for data structure. Making changes in here will likely result in failure to read old optimization results.
      • file_handling.py Creation and removal of files and directories. Data structure reduction and expansion for more convenient file sharing.
      • file_names.py Knows all filenames in the project. Generator-parser pairs.
      • path_handling.py Knows the most important paths used in the project. Some paths may still need to be generated manually.
      • toml_handling.py Writing and reading of result data files.
    • rendering Package responsible for calling Blender.
    • utils Package containing miscellaneous utility modules.
  • bs_render_single.py Blender render script file.
  • scene_leaf_material.blend Bender scene file that is run by the bs_render_single.py.
You might also like...
Program to export all new icons from the latest Fortnite patch

Assets Exporter This program allows you to generate all new icons of a patch in png! Requierements Python =3.8 (installed on your computer) If you wa

An open source image editor which can manipulate an image in many ways!

Image Editor - An open source image editor which can manipulate an image in many ways! If you need any more modes in repo or I

Image enhancing model for making a blurred image to be somehow clearer than before

This is a very small prject which helps in enhancing the images by taking a Input images. This project has many features like detcting the faces and enhaning the faces itself and also a feature which enhances the whole image

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

img2dataset Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine. Also supports

A pure python implementation of the GIMP XCF image format. Use this to interact with GIMP image formats
A pure python implementation of the GIMP XCF image format. Use this to interact with GIMP image formats

Pure Python implementation of the GIMP image formats (.xcf projects as well as brushes, patterns, etc)

Image Reading, Metadata Conversion, and Image Writing for Microscopy Images in Python

AICSImageIO Image Reading, Metadata Conversion, and Image Writing for Microscopy Images in Pure Python Features Supports reading metadata and imaging

This app finds duplicate to near duplicate images by generating a hash value for each image stored with a specialized data structure called VP-Tree which makes searching an image on a dataset of 100Ks almost instantanious
This app finds duplicate to near duplicate images by generating a hash value for each image stored with a specialized data structure called VP-Tree which makes searching an image on a dataset of 100Ks almost instantanious

Offline Reverse Image Search Overview This app finds duplicate to near duplicate images by generating a hash value for each image stored with a specia

Quickly 'anonymize' all people in an image. This script will put a black bar over all eye-pairs in an image

Face-Detacher Quickly 'anonymize' all people in an image. This script will put a black bar over all eye-pairs in an image This is a small python scrip

Fast Image Retrieval is an open source image retrieval framework

Fast Image Retrieval is an open source image retrieval framework release by Center of Image and Signal Processing Lab (CISiP Lab), Universiti Malaya. This framework implements most of the major binary hashing methods, together with both popular backbone networks and public datasets.

Comments
  • Usage of the program

    Usage of the program

    Hi!

    Thanks for this implementation, I have been looking to run it since a couple of days but I can't get it to be done. Is there any tutorial or instructions for somebody who is new to this type of software (and blender)? I tried running bs_render_single.py from IDE, from Conda Prompt, and from blender itself, but nothing seems to work.

    Also, I tried to run main.py from windows cmd, from my IDE, and from Conda prompt, but it throws errors in references. I tried changing all the references to match what is being called, but I end up with an error that some files (and the directory optimization) does not exist. Tried to run code from the readme, but still can't get to work.

    Would be very helpful if somebody can help me through some basic follow up on how to run this implementation.

    Best regards!

    opened by fieterovich 12
Releases(v0.2.0)
  • v0.2.0(Nov 28, 2022)

    This is the second released version of HyperBlend on our way towards a full canopy scale vegetation simulator. HyperBlend is developed in Spectral Laboratory of University of Jyväskylä by Kimmo Riihiaho (kimmo.a.riihiaho at jyu.fi).

    Version 0.2.0 will break many things in the previous version. Don't expect simulations created in 0.1.0 to work. Also the folder structure and some constants have been reorganized and renamed.

    Main improvements in this version:

    1. Simulation speed 200 times faster (simulation accuracy decreases 2-4 times)
      • You can still use the old simulation method if you need maximum accuracy
    2. Incorporation of the PROSPECT leaf model
      • You can now use PROSPECT parameters such as water thickness and chlorophyll content
      • It is fairly simple to plug in any other leaf model you would like. Just follow how our local prospect module does it, and you should be fine
    Source code(tar.gz)
    Source code(zip)
  • v0.1.0(Nov 11, 2021)

    This is the first release of HyperBlend. This release only demonstrates the usability of Blender in simulating hyperspectral reflectance and transmittance properties of plant leaves. Future releases will add more useful functionalities to the software.

    Created by @11kaks

    Source code(tar.gz)
    Source code(zip)
Owner
SILMAE
Spectral Imaging Laboratory for Multidisciplinary Analysis and Expertise
SILMAE
A proof-of-concept implementation of a parallel-decodable PNG format

mtpng A parallelized PNG encoder in Rust by Brion Vibber [email protected] Backgrou

Brion Vibber 193 Dec 16, 2022
CropImage is a simple toolkit for image cropping, detecting and cropping main body from pictures.

CropImage is a simple toolkit for image cropping, detecting and cropping main body from pictures. Support face and saliency detection.

Haofan Wang 15 Dec 22, 2022
LSB Image Steganography Using Python

Steganography is the science that involves communicating secret data in an appropriate multimedia carrier, e.g., image, audio, and video files

Mahmut Can Gönül 2 Nov 04, 2021
Kimimaro: Skeletonize Densely Labeled Images

Kimimaro: Skeletonize Densely Labeled Images # Produce SWC files from volumetric images. kimimaro forge labels.npy --progress # writes to ./kimimaro_o

92 Dec 17, 2022
Seeks to remove text from an image in a convincing way.

Text-Removal This is a Computer Vision project that seeks to successfully remove text from an image by covering the text areas in a convincing way. He

6 Nov 22, 2022
Python wrappers for external BART computational imaging tools and internal libraries

bartpy Python bindings for BART. Overview This repo contains code to generate an updated Python wrapper for the Berkeley Advance Reconstruction Toolbo

Max Litster 7 May 09, 2022
kikuchipy is an open-source Python library for processing and analysis of electron backscatter diffraction (EBSD) patterns

kikuchipy is an open-source Python library for processing and analysis of electron backscatter diffraction (EBSD) patterns. The library builds on the

pyxem 53 Dec 29, 2022
Image Processing - Make noise images clean

影像處理-影像降躁化(去躁化) (Image Processing - Make Noise Images Clean) 得力於電腦效能的大幅提升以及GPU的平行運算架構,讓我們能夠更快速且有效地訓練AI,並將AI技術應用於不同領域。本篇將帶給大家的是 「將深度學習應用於影像處理中的影像降躁化 」,

2 Aug 04, 2022
This is the official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

Freedom to build what you want FreeCAD is an open-source parametric 3D modeler made primarily to design real-life objects of any size. Parametric modeling allows you to easily modify your design by g

FreeCAD 12.9k Jan 07, 2023
Convert a DOS Punk image to text

DOS Punk Text Inspired by MAX CAPACITY's DOS Punks & the amazing DOS Punk community. DOS Punk Text is a Python 3 script that renders a DOS Punk image

4 Jan 13, 2022
Fuzzware is a project for automated, self-configuring fuzzing of firmware images

Fuzzware Fuzzware is a project for automated, self-configuring fuzzing of firmware images. The idea of this project is to configure the memory ranges

190 Dec 21, 2022
This is an app that allows users to upload photos and display and store the photos in a file until the user deletes them.

Qt Photo App This is an app that allows users to upload photos and display and store the photos in a file until the user deletes them. Setup python3 -

Kathy Yang 5 Jan 22, 2022
Image Processing HighPass Filter With Python

Image_Processing_HighPassFilter High Pass Filter take the high frequency and ignore the low frequency High Pass Filter can be use to sharpening an ima

Felix Pratamasan 1 Dec 27, 2021
Water marker for images.

watermarker linux users: To fix this error,please add truetype font path File "watermark.py", line 58, in module font = ImageFont.truetype("Dro

13 Oct 27, 2022
Generate meme GIFs in which an image you choose can be viewed by the user only after they wait a whole hour.

Generate meme GIFs in which an image you choose can be viewed by the user only after they wait a whole hour.

Feliks Maak 1 Jan 31, 2022
Design custom QR codes with this web app!

My-QR.Art This web app lets users design their own QR codes to any domain. It can be acessed on my-qr.art. You can find some more background info abou

Marien Raat 406 Dec 20, 2022
Deep Illuminator is a data augmentation tool designed for image relighting.

Deep Illuminator Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently genera

George Chogovadze 52 Nov 29, 2022
Glyph-graph - A simple, yet versatile, package for graphing equations on a 2-dimensional text canvas

Glyth Graph Revision for 0.01 A simple, yet versatile, package for graphing equations on a 2-dimensional text canvas List of contents: Brief Introduct

Ivan 2 Oct 21, 2022
starfish is a Python library for processing images of image-based spatial transcriptomics.

starfish: scalable pipelines for image-based transcriptomics starfish is a Python library for processing images of image-based spatial transcriptomics

199 Dec 08, 2022
Scramb.py is a region based JPEG Image Scrambler and Descrambler written in Python

Scramb.py Scramb.py is a region based JPEG Image Scrambler and Descrambler written in Python. Main features Scramb.py can scramble images regions. So

47 Dec 25, 2022