# Imagery preprocessing algorithms:

### Radiometric calibration

**Description:**

Radiometric calibration converts digital numbers into at-sensor radiance, measured in W / m² / cp / μm, and reflectance values in relative measurements .

Radiance defines the radiant flux, recieved on a unit of the earth’s surface through a 1 steradian solid angle relative to a unit of wavelength radiance.

Spectral reflectance is the ratio of incident-to-reflected radiant flux measured from an object or area over specified wavelength.

**Settings
**Radiometric_calibration

**Input data
**A raster image in GeoTIFF format and metadata files (RAW data)

**Output data
**A raster image in GeoTIFF format

**Source data:**

Satellite systems Landsat 8 and Sentinel-2

**Applied field**

Post-processing of raw data for further analysis. The calibration results serve as the initial data for calculating derivative image characteristics, such as vegetation indices, temperature, etc.

### Raster calculator

**Description**

This ability to conduct mathematical operations on the values in raster cells is sometimes referred to as map algebra. The raster calculator is a powerful and flexible analytical function. Mathematical functions are performed on a single raster layer and include arithmetic functions: per-pixel addition, multiplication, division, subtraction of rasters.

**Settings
**Raster_calculation

**Input data**

Raster image in GeoTIFF format (JP2)

**Output data**

Raster image in GeoTIFF format

**Source data**

Satellite systems: Landsat 8, Sentinel-2, RapidEye, PlanetScope, WorldView-2, WorldView-3, Google Aerial NRGB

**Applied filed**

GIS analysis: the Raster Calculator feature is designed to create and execute Map Algebra expressions in the instrument, using a simple, calculator-like tool interface.

### Raster filters

**Description**

Image Filtering is used to:

- Remove noise
- Sharpen contrast
- Highlight contours
- Detect edges

The algorithm fullfills the raster filtering, using linear or nonlinear window-based operators, specified by the user:

**Median filtering** – is a nonlinear method used to remove noise from images. It is widely used as it is very effective at removing noise while preserving edges. It is particularly effective at removing ‘salt and pepper’ type noise. The median filter works by moving through the image pixel by pixel, replacing each value with the median value of neighbouring pixels. The pattern of neighbours is called the “window”, which slides, pixel by pixel over the entire image. The median is calculated by first sorting all the pixel values from the window into numerical order, and then replacing the pixel being considered with the middle (median) pixel value.

**Gaussian filtering** is a convolution filter, used to blur images and remove noise and detail.

The Gaussian function is used in numerous research areas:

- It defines a probability distribution for noise or data.
- It is a smoothing operator.
- It is used in mathematics.

Gaussian filtering is more effective at smoothing images. It has its basis in the human visual perception system. It has been found that neurons create a similar filter when processing visual images.

**The Sobel filter** is used for edge detection. It works by calculating the gradient of image intensity at each pixel within the image. It finds the direction of the largest increase from light to dark and the rate of change in that direction. The result shows how abruptly or smoothly the image changes at each pixel, and therefore how likely it is that that pixel represents an edge. It also shows how that edge is likely to be oriented. The result of applying the filter to a pixel in a region of constant intensity is a zero vector. The result of applying it to a pixel on an edge is a vector that points across the edge from darker to brighter values.

**The Laplacian** is a 2-D isotropic measure of the 2nd spatial derivative of an image. The Laplacian of an image highlights regions of rapid intensity change and is therefore often used for edge detection (see zero crossing edge detectors). The Laplacian is often applied to an image that has first been smoothed with something approximating a Gaussian smoothing filter in order to reduce its sensitivity to noise.

**Settings**

Raster_filters

**Input data**

A raster image in GeoTIFF format

**Output data**

A raster image in GeoTIFF format

**Source data**

Satellite systems: Landsat 8, Sentinel-2, PlanetScope, WorldView-2, WorldView-3, Google, Aerial NRGB

**Applied fields**

GIS analysis

### Reprojection

**Description**

Each different projection is a mathematical function that takes coordinate pairs as inputs [(x, y)], and generates new coordinate pairs as output [*f*(x, y)]. Projection of a dataset from one system to another is the process of applying the projection function to each coordinate in the dataset. Reprojection algorithm in EOS Processing allows to change the projection and create a raster in custom (user defined) projection. The larger and more complex a dataset, the longer it will take to perform the projection.

**Input data**

A raster image in GeoTIFF format

**Output**

A raster image in GeoTIFF format

**Source data**

Satellite systems: Landsat 8, Sentinel-2, RapidEye, PlanetScope, WorldView-2, WorldView-3, Google Aerial NRGB

**Applied field**

GIS analysis

### Cropping by AOI

**Description**

Cropping the single-channel or multi-channel image by the vector contour of AOI (area of interest) or by the set of AOI corners coordinates

**Settings**

Clipping_by_AOI

**Input data**

Raster image in GeoTIFF format

**Output data**

Raster image in GeoTIFF format

**Source data**

Satellite systems: Landsat 8, Sentinel-2, RapidEye, PlanetScope, WorldView-2, WorldView-3, Google Aerial NRGB

**Applied field**

GIS analysis

### Cloud Detection

**Description**

Creating a Cloud Mask from raw Sentinel-2 data. Transforming data into binary raster, containing cloud and other objects pixel values. Additional rasters of reflective values are created according to radiometric calibration outcomes.

**Input data**

A raster image in GeoTIFF format

**Output data**

A raster image in GeoTIFF format

A vector layer in GEOJSON format

**Source data**

Satellite system Sentinel-2.

Channels: Coastal aerosol, Water Vapour, SWIR-CIRRUS

**Applied fields**

GIS analysis, preparation of images for further analysis