Image classification methods Photo interpretation is a method by which the user

Image classification methods photo interpretation is

This preview shows page 163 - 164 out of 355 pages.

Image classification methods Photo-interpretation is a method by which the user visu- ally inspects an image and identifies habitats. Multi- spectral classification is a computer-based method by which a number of wavebands are input to a statistical clustering algorithm which organises individual pixels into distinctive groups (classes) which are assumed to represent specific habitat types. Each method will be dis- cussed in turn. Photo-interpretation (visual interpretation) Visual interpretation is the process whereby an image is studied and habitats identified by eye. The image may be a photographic print or colour hard copy of a satellite image bought from a data supplier or digital data viewed on a computer monitor. Digital imagery is advantageous in that it may be processed (e.g. contrast stretched) to empha- sise the habitats of interest. For example, land can be masked out of an image and the full dynamic range of the display device applied only to the aquatic habitats. Image interpretation should be carried out using either a range of individual wavebands or an optimally-combined colour composite. For the latter case it will be necessary to choose the most appropriate wavebands for the habitats in ques- tion, e.g. Landsat Thematic Mapper bands 3, 2, and 1 as an RGB colour composite for submerged habitats. Habitats are identified visually by an analyst based on experience, then delineated and labelled manually. Deci- sions on the boundaries between different habitats are made with reference to local knowledge, common sense, field data, aerial photographs or maps and a sound under- standing of remote sensing theory. In essence the analyst edits and classifies the image in context (see Box 10.1). These decisions are reached without any computational effort or statistical processing. Delineation of boundaries is achieved using a tracing overlay and pencil or a mouse- driven cursor on a computer screen. Whether using a pencil or mouse-driven cursor, photo- interpretation requires a skilled and experienced operator to make sound decisions. Figure 10.1 (Plate 9) illustrates the challenge that visual interpretation presents: it is a Landsat TM image (bands 1, 2 and 3) of a 12 x 10 km area of uniform depth with patch reefs to the west, and areas of dense algae to the east. Some of the boundaries between habitats are clear, because the contrast with adjacent habi- tats is high, and should be relatively straight- forward to delineate (e.g. boundaries around A and B). Area C is a seagrass bed – its eastern boundary (white line) is clear but to the west the seagrass grades into sand. There is no clear boundary and the analyst must decide where the boundary lies (red line). Ideally, supplementary data will be available to guide this decision but typically this is not the case and the analyst is obliged to rely on common sense and local knowledge. Similarly it would be difficult to draw a boundary around areas D and E although their colour and texture would seem to indicate different habitats. The south-eastern boundary of F is

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture