Skip to main content

Supervised Classification

Image Classification in Remote Sensing

Image classification in remote sensing involves categorizing pixels in an image into thematic classes to produce a map. This process is essential for land use and land cover mapping, environmental studies, and resource management. The two primary methods for classification are Supervised and Unsupervised Classification. Here's a breakdown of these methods and the key stages of image classification.

1. Types of Classification

Supervised Classification

In supervised classification, the analyst manually defines classes of interest (known as information classes), such as "water," "urban," or "vegetation," and identifies training areas—sections of the image that are representative of these classes. Using these training areas, the algorithm learns the spectral characteristics of each class and applies them to classify the entire image.

  • When to Use Supervised Classification:   - You have prior knowledge about the classes.   - You can verify the training areas with ground truth data.   - You can identify distinct, homogeneous regions for each class.

Unsupervised Classification

Unsupervised classification, on the other hand, uses the spectral properties of the image data to automatically group pixels with similar spectral characteristics into spectral classes. These classes are later labeled by the analyst based on the spectral patterns and ground-truth information.

  • When to Use Unsupervised Classification:   - You have limited prior knowledge about the image's content.   - You need a large number of classes or wish to explore the data's spectral characteristics.   - It's beneficial for quickly exploring unknown regions.

2. Key Stages of Image Classification

Image classification follows a systematic series of stages to produce accurate thematic maps.

  1. Raw Data Collection: Initial, unprocessed image data is collected.
  2. Preprocessing: Prepares the data for analysis by correcting atmospheric effects, removing noise, and aligning geometry. This stage is essential to ensure data accuracy.
  3. Signature Collection: In supervised classification, the analyst collects samples, called signatures, representing each class. These signatures capture the typical spectral characteristics for each category.
  4. Signature Evaluation: The quality and distinctiveness of signatures are evaluated to ensure that they are statistically separate and represent the classes accurately.
  5. Classification: Using the collected signatures, the classification algorithm assigns each pixel to a specific class, producing the classified map.

3. Information Class vs. Spectral Class

  • Information Class: An information class represents real-world categories, such as water bodies, urban areas, or vegetation, specified by the analyst for extraction from the image.
  • Spectral Class: A spectral class is determined by the clustering of pixels with similar spectral (color or brightness) values. These classes are automatically identified based on statistical similarities in pixel values across multiple spectral bands.

4. Supervised vs. Unsupervised Training

To classify an image, a system needs to be trained to recognize patterns.

  • Supervised Training:   - Controlled by the analyst, who selects representative pixels and instructs the system on what each class should look like.   - Often more accurate but requires skill and understanding of the region.
  • Unsupervised Training:   - The computer automatically groups pixels based on spectral properties, with the analyst specifying the desired number of classes.   - This approach requires less skill but may be less accurate.

5. Classification Decision Rules in Supervised Classification

In supervised classification, different decision rules guide the process of assigning pixels to classes. Here are some common ones:

Parametric Decision Rules

These rules assume that pixel values follow a normal distribution, which allows the system to use statistical measures for classification.

  • Minimum Distance Classifier:   - Calculates the distance between a candidate pixel and the mean of each class signature.   - Assigns the pixel to the class with the shortest distance (e.g., Euclidean or Mahalanobis distance).
  • Maximum Likelihood Classifier:   - Considers both variance and covariance within class signatures.   - Assumes a normal distribution and assigns pixels to the class with the highest probability of belonging.

Nonparametric Decision Rules

These rules do not assume a specific distribution.

  • Parallelepiped Classifier:   - Uses minimum and maximum values for each class and assigns pixels within these limits to the corresponding class.

  • Feature Space Classifier:   - Analyzes classes based on polygons within a feature space, which is often more accurate than the parallelepiped method.

Summary Table

AspectSupervised ClassificationUnsupervised Classification
DefinitionUses predefined classes and training areas.Uses statistical groupings based on spectral properties.
ClassesInformation Classes: Known classes defined by the analyst.Spectral Classes: Classes identified by the system.
Training ProcessAnalyst selects and verifies classes.System automatically groups pixels; analyst labels classes.
Best Use CaseWhen classes are known, distinct, and verifiable with ground truth.When classes are unknown or when exploratory analysis is needed.
Accuracy and Skill RequirementHigh accuracy; requires skill and knowledge.Generally lower accuracy; requires less skill.
Decision RulesMinimum Distance, Maximum Likelihood, Parallelepiped, Feature Space.Classes grouped by spectral similarity.

https://geogisgeo.blogspot.com/2023/01/minimum-distance-gaussian-maximum.html



PG and Research Department of Geography,
Government College Chittur, Palakkad
https://g.page/vineeshvc

Comments

Post a Comment

Popular posts from this blog

Regional Geography, Systematic Geography, Idiographic, Nomothetic, Inductive and Deductive Approaches

T wo major ways of studying Geography : the Regional Approach and the Systematic Approach . It also explains the related ideas of idiographic vs. nomothetic and inductive vs. deductive reasoning , especially in the context of the Hartshorne–Schaefer debate . 1. Regional Geography: “All About One” Regional Geography studies one particular region in detail . A region is an area that has some degree of homogeneity (sameness) within its boundary but is also unique or different from other regions . For example, if we study Palakkad District , we may study: Relief and drainage Climate Soil Vegetation Agriculture Population Occupation Economy Culture Political characteristics The purpose is to understand the complete geographical personality of Palakkad and the relationships among its different features. Key concepts Region: A geographical area with identifiable characteristics and boundaries. Homogeneity: Si...
Post a Comment
Read more

Kuhn’s Paradigms

The given content explains Thomas S. Kuhn’s model of scientific development , its application to geography, and criticisms by Karl Popper, Paul Feyerabend, Michel Foucault , and others. 1. Basic Idea Kuhn argued that science does not develop continuously in a straight line . Instead, scientific development occurs through: Preparadigm → Paradigm → Normal Science → Crisis → Scientific Revolution → New Paradigm A new paradigm may replace an older one, producing a major change in the way scientists understand and study a subject. Concepts and Terminologies Concept / Term Simple Meaning Paradigm A commonly accepted framework/model that guides scientific research Exemplar A successful concrete problem-solution used as a model for future research Disciplinary Matrix Shared beliefs, values, concepts, methods and techniques of a scientific community Preparadig...
Post a Comment
Read more

Multispectral and Hyperspectral Imaging Systems

The main idea is how a remote-sensing sensor collects information about an area . A sensor does not simply take an ordinary photograph. It measures the electromagnetic energy reflected or emitted by objects in different wavelength bands . Depending on how many bands are measured and how the sensor collects them, different imaging systems are used. 1. Multispectral vs. Hyperspectral Multispectral imaging (MSI) records information in a limited number of relatively broad, separate spectral bands , such as blue, green, red, near-infrared and shortwave infrared. Hyperspectral imaging (HSI) records information in many narrow and usually contiguous spectral bands . Therefore, it provides a much more detailed spectral signature of each pixel. The resulting dataset is commonly called a hyperspectral data cube (hypercube) because it contains: X-axis → spatial information Y-axis → spatial information Z-axis → wavelength/spectral information Thus, hype...
Post a Comment
Read more

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...
Post a Comment
Read more

Satalite

Landsat → Land resources SPOT → High-resolution mapping IRS → Indian natural-resource mapping ASTER → Geology + thermal + DEM QuickBird → Very high spatial resolution MODIS → Daily global monitoring GOES → Weather monitoring AVHRR → Weather + vegetation + ocean AVIRIS → Hyperspectral imaging Highest spectral resolution: AVIRIS (224 narrow bands) Highest spatial resolution in this list: QuickBird (~0.61 m PAN) Highest temporal frequency: GOES (minutes) Best broad global monitoring: MODIS Indian sensors: IRS-LISS III and LISS IV Hyperspectral: AVIRIS Thermal + multispectral + DEM: ASTER abbreviations MSS – Multispectral Scanner System TM – Thematic Mapper ETM+ – Enhanced Thematic Mapper Plus GOES – Geostationary Operational Environmental Satellite AVHRR – Advanced Very High Resolution Radiometer HRV – High Resolution Visible HRVIR – High Resolution Visible and Infrared HRG – High Resolution Geometric ...
Post a Comment
Read more