---
title: "Cubert Camera Data Workflow"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Cubert Camera Data Workflow}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

<!-- badges: start -->
[![R-CMD-check](https://github.com/CTTIR/hyperspectR/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/CTTIR/hyperspectR/actions/workflows/R-CMD-check.yaml)
[![pkgdown](https://github.com/CTTIR/hyperspectR/actions/workflows/pkgdown.yaml/badge.svg)](https://cttir.github.io/hyperspectR/)
[![CRAN status](https://www.r-pkg.org/badges/version/hyperspectR)](https://CRAN.R-project.org/package=hyperspectR)
[![Codecov test coverage](https://codecov.io/gh/CTTIR/hyperspectR/branch/main/graph/badge.svg)](https://app.codecov.io/gh/CTTIR/hyperspectR?branch=main)
[![CRAN downloads](https://cranlogs.r-pkg.org/badges/hyperspectR)](https://cran.r-project.org/package=hyperspectR)
[![CRAN downloads total](https://cranlogs.r-pkg.org/badges/grand-total/hyperspectR)](https://cran.r-project.org/package=hyperspectR)
[![License: MIT](https://img.shields.io/badge/license-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
<!-- badges: end -->

```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width = 7,
  fig.height = 5
)
```

```{r setup}
library(hyperspectR)
```

## Overview

This vignette demonstrates the package's ENVI and calibration interfaces using
synthetic data. Device support tests use fixtures and SDK mocks; real camera
sessions remain an external validation requirement. Read wavelength, FWHM,
processing mode and acquisition settings from each recording. Do not infer them
from a model name or this demonstration's defaults.

## Step 1: Reading ENVI Data

After exporting from CUVIS Export to ENVI format:

```{r eval=FALSE}
# Read the ENVI header + binary pair
cube <- hs_read_envi("path/to/measurement.hdr")

# Or use the auto-detect reader
cube <- hs_read_cube("path/to/measurement.hdr")
```

For this vignette we use synthetic data:

```{r}
cube <- hs_simulate_cube(rows = 30, cols = 30, seed = 42)
print(cube)
```

## Step 2: Calibration

Apply dark current subtraction and white reference normalization:

```{r}
# Simulate dark and white references
dark_data <- array(0.02, dim(cube$data))
white_data <- array(0.95, dim(cube$data))
dark <- hsi_cube(dark_data, cube$wavelengths)
white <- hsi_cube(white_data, cube$wavelengths)

# Demonstrate the calibration arithmetic (these references are synthetic)
calibrated <- hs_calibrate(cube, dark, white)
range(calibrated$data)
```

## Step 3: Preprocessing

Apply spectral smoothing to reduce noise:

```{r}
smoothed <- hs_smooth(calibrated, window = 5, poly = 2)
hs_plot_spectra(smoothed, pixels = "mean", show_sd = TRUE)
```

## Step 4: Computing Indices

```{r fig.width=10, fig.height=4}
hs_plot_clinical(smoothed, indices = c("sto2", "npi", "thi"))
```

## Step 5: Saving Results

```{r eval=FALSE}
# Save processed cube
hs_write_envi(smoothed, "path/to/processed_cube")

# Export index map as PNG
sto2 <- hs_sto2(smoothed)
hs_export_png(sto2, "path/to/sto2_map.png")
```