Visual image interpretation

Introduction

The most intuitive way of extracting information from remote sensing images is by visual image interpretation, which is based on our ability to relate colours and patterns in an image to real world features.

Examples

Visual image interpretation is used to produce geospatial data in all of ITC’s fields of interest: urban mapping, soil mapping, geomorphological mapping, forest mapping, natural vegetation mapping, cadastral mapping, land use mapping, and many others. Actual image interpretation is application specific, although it does follow a standard approach.

How to

We can interpret images displayed on a computer monitor or printed images, but how to convey our findings to somebody else? In everyday life we often do this verbally, but for thousands of years we have also been doing it by mapping. We used to overlay a transparency on a photograph and trace over the outline of areas that we recognized as having characteristics we were interested in. By doing so for all features of interest in a scene, we obtained a map.

The digital variant of this approach is to digitize—either on-screen, or using a digitizer tablet if we only have a hardcopy image—points, lines and areas and label these geometric entities to convey thematic attributes. This way we obtain a map of, for example, all vineyards in a certain area and the roads and tracks leading to them. Instead of interpreting and digitizing from a single image, we can also use a stereo-image pair. The interpretation process is the same, although we do need special devices for stereoscopic display and viewing, as well as equipment that allows us to measure properly in a stereogram.

Visual image interpretation is not as easy as it may seem at first glace; it requires training. Yet our eye–brain system is quite capable of doing the job. Visual interpretation is, in fact, an extremely complex process, as was discovered when we tried to let computers do image interpretation. Research on image understanding has helped us to conceptualize human vision and interpretation, and progress in this area continues to be made.

Prior knowledge

Outgoing relations

Incoming relations

Learning paths