Skip to main content

Accuracy Assessment


Accuracy assessment is the process of checking how correct your classified satellite image is.

👉 After supervised classification, the satellite image is divided into classes like:

  • Water

  • Forest

  • Agriculture

  • Built-up land

  • Barren land

But classification is done using computer algorithms, so some areas may be wrongly classified.

👉 Accuracy assessment helps to answer this question:

✔ "How much of my classified map is correct compared to real ground conditions?"

 Goal

The main goal is to:

  • Measure reliability of classified maps

  • Identify classification errors

  • Improve classification results

  • Provide scientific validity to research

👉 Without accuracy assessment, a classified map is not considered scientifically reliable.

Reference Data (Ground Truth Data)

Reference data is real-world information used to check classification accuracy.

It can be collected from:

✔ Field survey using GPS
✔ High-resolution satellite images (Google Earth etc.)
✔ Existing maps or survey reports

🧭 Example

Suppose your classified map shows:

  • A location classified as forest

But ground survey shows:

  • The same location is actually agriculture land

👉 This is a classification error.

📊 Error Matrix (Confusion Matrix)

What is Error Matrix?

Error matrix is a table used to compare classified results with actual ground data.

It is the most important tool in accuracy assessment.

🧾 Example of Error Matrix

Reference DataForestAgricultureWaterTotal
Forest405045
Agriculture630238
Water031417
Total463816100

👉 Diagonal values show correct classification
👉 Other values show classification errors

📚 Important Terminologies

1️⃣ Overall Accuracy

It shows how many pixels are correctly classified in total.


✔ Example

Correct pixels = 40 + 30 + 14 = 84
Total pixels = 100

👉 Overall Accuracy = 84%

2️⃣ Producer's Accuracy

✔ Meaning

Shows how well real-world features are correctly classified.

👉 It measures error of omission.

❓ What is Omission Error?

When a real feature is missed in classification.

Example:

  • Real forest area classified as agriculture.


3️⃣ User's Accuracy

✔ Meaning

Shows the probability that a classified pixel actually represents that class on ground.

👉 It measures error of commission.

❓ What is Commission Error?

When a pixel is wrongly included in a class.

Example:

  • Agriculture land classified as forest.

 Steps in Accuracy Assessment

Step 1 – Sampling Design

Selecting sample points to check accuracy.

Methods include:

✔ Random sampling
✔ Stratified sampling
✔ Systematic sampling

Step 2 – Comparison

Compare:

  • Classified image results

  • Ground truth data

Step 3 – Accuracy Calculation

Create error matrix and calculate:

  • Overall Accuracy

  • Producer's Accuracy

  • User's Accuracy

  • Kappa coefficient


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

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

Thermal Infrared Remote Sensing

1. Principles Thermal Infrared Remote Sensing is based on the detection of naturally emitted electromagnetic radiation from objects, rather than reflected solar energy. According to Planck's Radiation Law , all objects with a temperature above absolute zero (0 K) emit electromagnetic radiation. For Earth surface features, the peak emission lies in the Thermal Infrared (TIR) region of 3–14 μm of the electromagnetic spectrum. The amount of radiation emitted is primarily a function of surface temperature and emissivity . Sensors measure the radiant energy flux density (W/m²) , which is later converted to surface temperature using Stefan-Boltzmann's Law . 2. Radiation Properties in TIR Emissivity (ε): Ratio of radiation emitted by a surface to that emitted by a perfect blackbody at the same temperature. Natural surfaces like water (ε ≈ 0.98) have high emissivity, while bare soils and metals have lower values. Blackbody: An idealized object th...
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