Skip to main content

Supervised Classification. Remote Sensing

Image classification.

Supervised classification

Unsupervised classification.


Stages:

Raw data

Preprocessing

Signature collection

Signature evaluation

Classification 

.

Information Class and Spectral Class

Information class: It is a class specified by an image analyst. It refers to the information to be extracted.


Spectral class: It a class which includes similar gray-level

vectors in the multispectral space. Spectral classes are groups of pixels that are uniform (or near-similar) with respect to their brightness values.

.

Supervised and Unsupervised

Supervised (Information Class)


Have a set of desired dasses in mind then create the appropriate signatures from the data.


Appropriate

• when one wants to identify relatively few dasses

. when one has selected training sites that can be verified with ground truth data

• when one can identify distinct, homogeneous regions that represent each dass.


Unsupervised (Spectral Class)

Classes to be determined by spectral distinctions that are inherent in the data → define the dasses later.

Appropriate-

when one wants to define many dasses easily, and then identify dasses.

.

Training for Classification


Computer system must be trained to recognize patterns in image data.


Process of defining the criteria by which these patterns are recognized.


Supervised Training is controlled by the analyst.


Select pixels that represent patterns instruct the computer system to identify pixels with similar characteristics.


More accurate but requires high skill.


Unsupervised Training is computer-automated.


Specify number of classes the computer uncovers statistical classes.


Less accurate and less skill required.

.

Supervised Classification

Common decision rules:


Parametric decision rules:

Minimum distance classifier / Centroid classifier.

Maximum likelihood / Bayesian classification.


Nonparametric decision rule:

Parallelepiped classifier.

Feature space classifier.

.

Minimum Distance/Centroid Classifier:

Calculates the spectral distance between the candidate pixel and the mean of each signature.

The candidate pixel is assigned to the class with the closest mean.

Calculates mean of the spectral values for the training set in each band and for each category.

Measures the distance from a pixel of unknown identify to the mean of each category.

Assigns the pixel to the category with the shortest distance.

Assigns a pixel as "unknown" if the pixel is beyond the distances defined by the analyst.

Methods of calculation Minimum Spectral Distance:

Euclidean distance: based on the Pythagorean theorem

Mahalanobis distance:

■ Variance-Covariance matrix are used (normal distribution of DN is assumed)

.

Maximum Likelihood Classifier:

• This classifier quantitatively evaluates both the variance and covariance of the trained spectral response patterns when deciding the fate of an unknown pixel.

■To do this the classifier assumes that the distribution of points for each cover-type are normally distributed.

• Under this assumption, the distribution of a category response can be completely described by the mean vector and the covariance matrix.

■ Given these values, the classifier computes the probability that unknown pixels will belong to a particular category.

Probability function is calculated from the inputs.

Assumes probabilities are equal for all dasses.

Each pixel is then judged as to the dass to which it most probably belong.

.

Parallelepiped Classifier:

Based on Maximum and Minimum values in each signature.

..

Feature Space Classifier:

Based on discrete objects (polygons) in a feature space image.

More accurate than parallelepiped.

Comments

Popular posts from this blog

Disaster Management

1. Disaster Risk Analysis → Disaster Risk Reduction → Disaster Management Cycle Disaster Risk Analysis is the first step in managing disasters. It involves assessing potential hazards, identifying vulnerable populations, and estimating possible impacts. Once risks are identified, Disaster Risk Reduction (DRR) strategies come into play. DRR aims to reduce risk and enhance resilience through planning, infrastructure development, and policy enforcement. The Disaster Management Cycle then ensures a structured approach by dividing actions into pre-disaster, during-disaster, and post-disaster phases . Example Connection: Imagine a coastal city prone to cyclones: Risk Analysis identifies low-lying areas and weak infrastructure. Risk Reduction includes building seawalls, enforcing strict building codes, and training residents for emergency situations. The Disaster Management Cycle ensures ongoing preparedness, immediate response during a cyclone, and long-term recovery afterw...

Linear Arrays Along-Track Scanners or Pushbroom Scanners

Multispectral Imaging Using Linear Arrays (Along-Track Scanners or Pushbroom Scanners) Multispectral Imaging: As previously defined, this involves capturing images using multiple sensors that are sensitive to different wavelengths of electromagnetic radiation. Linear Array of Detectors (A): This refers to a row of discrete detectors arranged in a straight line. Each detector is responsible for measuring the radiation within a specific wavelength band. Focal Plane (B): This is the plane where the image is formed by the lens system. It is the location where the detectors are placed to capture the focused image. Formed by Lens Systems (C): The lens system is responsible for collecting and focusing the incoming radiation onto the focal plane. It acts like a camera lens, creating a sharp image of the scene. Ground Resolution Cell (D): As previously defined, this is the smallest area on the ground that can be resolved by a remote sensing sensor. In the case of linear array scanne...

Discrete Detectors and Scanning mirrors Across the track scanner Whisk broom scanner.

Multispectral Imaging Using Discrete Detectors and Scanning Mirrors (Across-Track Scanner or Whisk Broom Scanner) Multispectral Imaging:  This technique involves capturing images of the Earth's surface using multiple sensors that are sensitive to different wavelengths of electromagnetic radiation.  This allows for the identification of various features and materials based on their spectral signatures. Discrete Detectors:  These are individual sensors that are arranged in a linear or array configuration.  Each detector is responsible for measuring the radiation within a specific wavelength band. Scanning Mirrors:  These are optical components that are used to deflect the incoming radiation onto the discrete detectors.  By moving the mirrors,  the sensor can scan across the scene,  capturing data from different points. Across-Track Scanner or Whisk Broom Scanner:  This refers to the scanning mechanism where the mirror moves perpendicular to the direction of flight.  This allows for t...

Disaster Risk

Disaster Risk 

geostationary and sun-synchronous

Orbital characteristics of Remote sensing satellite geostationary and sun-synchronous  Orbits in Remote Sensing Orbit = the path a satellite follows around the Earth. The orbit determines what part of Earth the satellite can see , how often it revisits , and what applications it is good for . Remote sensing satellites mainly use two standard orbits : Geostationary Orbit (GEO) Sun-Synchronous Orbit (SSO)  Geostationary Satellites (GEO) Characteristics Altitude : ~35,786 km above the equator. Period : 24 hours → same as Earth's rotation. Orbit type : Circular, directly above the equator . Appears "stationary" over one fixed point on Earth. Concepts & Terminologies Geosynchronous = orbit period matches Earth's rotation (24h). Geostationary = special type of geosynchronous orbit directly above equator → looks fixed. Continuous coverage : Can monitor the same area all the time. Applications Weather...