Object-Based Image Analysis (OBIA) is a sub-discipline of GIScience devoted to partitioning remote sensing (RS) imagery into meaningful image-objects, and assessing their characteristics through spatial, spectral and temporal scale. Fundamentally consisting of image segmentation, attribution, and classification.

OBIA allows for hierarchical relationship framework development that give successive levels of image objects an association.

Work scheme:

  1. develop rule set;

  2. develop applications;

  3. combine, modify and calibrate rule sets;

  4. process data;

  5. execute and monitor analysis;

  6. review and edit results.




Image segmentation is a partitioning of an image into constituent parts using image attributes such as pixel intensity, spectral values, and/or textural properties. Image segmentation produces an image representation in terms of edges and regions of various shapes and interrelationships.

Segmentation algorithms are based on region growing/merging, simulated annealing, boundary detection, probability-based image segmentation, fractal net evolution approach (FNEA), and more.

In region growing/merging, neighboring pixels or small segments that have similar spectral properties are assumed to belong to the same larger segment and are therefore merged.



Multiresolution segmentation



—Once created each image object can be identified and classified based on its attributes which the user can define.

For example:

  1. spatial extent;

  2. —linearity;

  3. —spectral reflectance;

  4. —relationship with Image Object Primitives.

Membership function are used to determine if an object belongs to a class or not. These membership functions are based on fuzzy logic. Where an object can have a probability of belonging to a class – with the probability being in the range 0 to 1 – where 0 is absolutely DOES NOT belong to the class, and 1 is absolutely DOES belong to the class.


The result of classification is a vector or raster layer containing classes classified by user.