Multiband spectro-radiometric satellite image analysis with K-means cluster algorithm

Overview

Multi-band Spectro Radiomertric Image Analysis with K-means Cluster Algorithm

Overview

Multi-band Spectro Radiomertric images are images comprising of several channels / bands which hold information on band energy in each pixel.
The most common multi band channels are the RGB (Red Green Blue) channels of the visible light spectrum.

The images used are LANDSAT 8 satellite images and each image consist of three bands, namely: Thermal Infrared, Red and Near infrared bands corresponding to band 10, band 4 and band 5 of LANDSAT 8 satellite imagery with wavelengths of 10.895µm, 0.655µm and 0.865µm respectively.

Each pixel in each bands of each image are used to compute three features namely: NDVI (Normalized Differential Vegetative Index), PV (Portion of Vegetation) and LST (Land Surface Temperature).

The K-means cluster algorithm is initialized and the "number of clusters" hyper-parameter is set to 60. The algorithm is then trained on the extracted features and forms 60 different clusters represented by each of the 60 centroids.

These centroids are stored in the "ouput" folder and will be futher studied to learn what NDVI, PV and LST combinations a geograhical location might need to have for the occurence and spread of wild fire to be highly probable.



Features

NDVI (Normalized Differential Vegetative Index):

The Normalized Differential Vegetative Index is a metric for checking the presence and health of a vegetation in a given region.
It is basically how much RED light energy from the visible light spectrum is absorbed by the plant and how much NIR (near-infrared rays) it emmits.
Healthy vegetation absorbs red-light energy to fuel photosynthesis and create chlorophyll, and a plant with more chlorophyll will reflect more near-infrared energy than an unhealthy plant.
The NDVI ranges from -1 to 1, -1 corresponds to a very unhealthy plant and 1 corresponds to a very healthy plant.

The mathematical expression for NDVI is:
NDVI = (NIR - RED) / (NIR + RED)


PV (Portion of Vegetation):

Portion of Vegetation is the ratio of the vertical projection area of vegetation on the ground to the total vegetation area

The mathematical expression for PV is:
PV = (NDVI - NDVImin) / (NDVImin + NDVImax)
NDVImin is the minimum NDVI value a pixel holds in a single image
NDVImin is the maximum NDVI value a pixel holds in a single image


LST (Land Surface Temperature):

Land Surface Temperature is the radiative temperature / intensity of the land surface

The mathematical expression for LST is:
LST = BT / ( 1 + ( ( kn * BT / p ) * np.log(E) ) )

BT is brighness Temperature in celcius and is mathematically expressed as:
BT = (K2 / np.log( ( K1 / TOA ) + 1 )) - 273.15
where K1 and K2 are landsat 8 constants 774.8853 and 1321.0789 respectively

TOA (Top of Atmosphere) Reflectance is a unitless measurement which provides the ratio of radiation reflected to the incident solar radiation on a given surface.
It is mathematically expressed as:
TOA = ML * TIR + Al
where ML and Al are landsat 8 constants 3.42E-4 and 0.1 respectively.

p is mathematically expressed as:
p = hc/A
where h, c and a are plank's constant, speed of light and boltzmann constant respectively

E is emissivity of the land surface and is mathematically expressed as:
( Ev * PV * Rv ) + ( Es * ( 1 - PV ) * Rs ) + C
where:
Ev (Vegitation Emissivity) of location = 0.986
Es (Soil Emissivity) of location = 0.973
C (topography factor) of location = 0.0001
Rv =(0.92762 + (0.07033PV))
Rs=(0.99782 + (0.05362
PV))



Dependencies

  • Rasterio
  • Numpy
  • Pandas
  • Sklearn
  • Pickle


Setup

clone the repository and download the 'requirement.txt' files, then open terminal in the working directory and type 'pip install -r requirements.txt' to install all the requirements for this project.
Owner
Chibueze Henry
A machine learning enthusiast and developer as well as a full-stack web developer
Chibueze Henry
Deep Dual Consecutive Network for Human Pose Estimation (CVPR2021)

Beanie - is an asynchronous ODM for MongoDB, based on Motor and Pydantic. It uses an abstraction over Pydantic models and Motor collections to work wi

295 Dec 29, 2022
Demonstrates how to divide a DL model into multiple IR model files (division) and introduce a simplest way to implement a custom layer works with OpenVINO IR models.

Demonstration of OpenVINO techniques - Model-division and a simplest-way to support custom layers Description: Model Optimizer in Intel(r) OpenVINO(tm

Yasunori Shimura 12 Nov 09, 2022
Automatically creates genre collections for your Plex media

Plex Auto Genres Plex Auto Genres is a simple script that will add genre collection tags to your media making it much easier to search for genre speci

Shane Israel 63 Dec 31, 2022
Efficient 6-DoF Grasp Generation in Cluttered Scenes

Contact-GraspNet Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes Martin Sundermeyer, Arsalan Mousavian, Rudolph Triebel, Dieter

NVIDIA Research Projects 148 Dec 28, 2022
Code for "Retrieving Black-box Optimal Images from External Databases" (WSDM 2022)

Retrieving Black-box Optimal Images from External Databases (WSDM 2022) We propose how a user retreives an optimal image from external databases of we

joisino 5 Apr 13, 2022
Codebase for "ProtoAttend: Attention-Based Prototypical Learning."

Codebase for "ProtoAttend: Attention-Based Prototypical Learning." Authors: Sercan O. Arik and Tomas Pfister Paper: Sercan O. Arik and Tomas Pfister,

47 2 May 17, 2022
PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML)

pytorch-maml This is a PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML): https://arxiv

Kate Rakelly 516 Jan 05, 2023
Multi-task yolov5 with detection and segmentation based on yolov5

YOLOv5DS Multi-task yolov5 with detection and segmentation based on yolov5(branch v6.0) decoupled head anchor free segmentation head README中文 Ablation

150 Dec 30, 2022
Pytorch implementation of DeepMind's differentiable neural computer paper.

DNC pytorch This is a Pytorch implementation of DeepMind's Differentiable Neural Computer (DNC) architecture introduced in their recent Nature paper:

Yuanpu Xie 91 Nov 21, 2022
PyTorch Implementation of Small Lesion Segmentation in Brain MRIs with Subpixel Embedding (ORAL, MICCAIW 2021)

Small Lesion Segmentation in Brain MRIs with Subpixel Embedding PyTorch implementation of Small Lesion Segmentation in Brain MRIs with Subpixel Embedd

22 Oct 21, 2022
Multi-View Radar Semantic Segmentation

Multi-View Radar Semantic Segmentation Paper Multi-View Radar Semantic Segmentation, ICCV 2021. Arthur Ouaknine, Alasdair Newson, Patrick Pérez, Flore

valeo.ai 37 Oct 25, 2022
Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (CVPR 2021)

ASGNet The code is for the paper "Adaptive Prototype Learning and Allocation for Few-Shot Segmentation" (accepted to CVPR 2021) [arxiv] Overview data/

Gen Li 91 Dec 23, 2022
ReGAN: Sequence GAN using RE[INFORCE|LAX|BAR] based PG estimators

Sequence Generation with GANs trained by Gradient Estimation Requirements: PyTorch v0.3 Python 3.6 CUDA 9.1 (For GPU) Origin The idea is from paper Se

40 Nov 03, 2022
This project is based on our SIGGRAPH 2021 paper, ROSEFusion: Random Optimization for Online DenSE Reconstruction under Fast Camera Motion .

ROSEFusion 🌹 This project is based on our SIGGRAPH 2021 paper, ROSEFusion: Random Optimization for Online DenSE Reconstruction under Fast Camera Moti

219 Dec 27, 2022
Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

Diffusion Probabilistic Models for 3D Point Cloud Generation [Paper] [Code] The official code repository for our CVPR 2021 paper "Diffusion Probabilis

Shitong Luo 323 Jan 05, 2023
[ICCV 2021] Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification

Counterfactual Attention Learning Created by Yongming Rao*, Guangyi Chen*, Jiwen Lu, Jie Zhou This repository contains PyTorch implementation for ICCV

Yongming Rao 90 Dec 31, 2022
Cross Quality LFW: A database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Cross-Quality Labeled Faces in the Wild (XQLFW) Here, we release the database, evaluation protocol and code for the following paper: Cross Quality LFW

Martin Knoche 10 Dec 12, 2022
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions This is the official repository of PRIME, the data agumentation method introduced i

Apostolos Modas 34 Oct 30, 2022
Tzer: TVM Implementation of "Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation (OOPSLA'22)“.

Artifact • Reproduce Bugs • Quick Start • Installation • Extend Tzer Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation This is the s

12 Dec 29, 2022
SHIFT15M: multiobjective large-scale fashion dataset with distributional shifts

[arXiv] The main motivation of the SHIFT15M project is to provide a dataset that contains natural dataset shifts collected from a web service IQON, wh

ZOZO, Inc. 138 Nov 24, 2022