Enrolment options
In this module, we will move a step further and learn how to make more sense of the landscape by dividing it into separate classes based on surface characteristics. This process is known as image classification. It involves conversion of raster data into finite set of classes that represent surface types in the imagery. It may be used to identify vegetation types, anthropogenic structures, mineral resources, etc. or transient changes in any of these features. Additionally, classified raster image can be converted to vector features (e.g., polygons) in order to compare with other data sets or to calculate spatial attributes (e.g., area, perimeter, etc). Image classification is a very active field of study broadly related to the field of pattern recognition. In this unit, we will discuss about different image classification methods, signature evaluation and the guidelines for selecting a classification method.
In this module, you will studied about the elements and keys of image interpretation, techniques of ground truth data collection and characteristics of digital remote sensing images. Proper knowledge of all these concepts is required to extract precise and accurate information present in remotely sensed images. The module, comprising four units, introduces you to various aspects of digital image processing and interpretation such as image correction, enhancement, transformation, classification and accuracy assessment.
Unit 1 deals with errors present in the images such as radiometric and geometric errors and their corrections. Necessary corrections are required in order to correct the raw data transmitted from satellites to ground stations. In this unit, you will learn how images are corrected before they become suitable for practical applications.
Unit 2 introduces you to image enhancement and transformation techniques which greatly increase the visibility of features contained in the images. You will learn about the image enhancement and transformation techniques such as contrast stretching, image filtering, image fusion and vegetation indices.
Unit 3 deals with various aspects of image classification. You will study about the transformation of an image into a thematic map based on spectral response of image features. We will be discussing various methods of image classification such as supervised and unsupervised in this unit.
Unit 4 discusses fundamental concepts, needs and methods of accuracy assessment. You will study more about the sources of errors, sampling size, error matrix and also importance of assessing quality of map products generated from remote sensing data.
Objectives
After studying this block, you should be able to:
- Discuss major distortions of remotely sensed data and process of their corrections;
- Explain techniques employed for enhancement and transformation of remotely sensed data;
- Describe image classification methods and choose an appropriate image classification technique for a specify study; and
- Outline methods of accuracy assessment and identify the role of error matrix and sampling size in accuracy assessment.