Feature extraction in satellite imagery is fundamental to the goal of gathering timely, large-area geospatial information relevant to GIScience research and beyond. There are two approaches in remote sensing to feature extraction. One approach involves identifying phenomena in imagery to be reduced into map form (typically features such as categories or land surface elements). A second approach is to enhance and extract specific bands of imagery and transform them in order to provide a reduced set of inputs or predictors to a model (e.g., a vegetation index). This section focuses only on the former. Extraction of features is performed using a conceptualization of the study site known as a scene model, and the combination of ground reference information and appropriately chosen satellite data. Features can be represented in maps as discrete pixels, polygons or fuzzy membership surfaces, and machine learning algorithms have emerged as the most reliable and effective approaches to feature extraction in the last decade. There are five key steps to performing effective feature extraction: (1) developing a scene model to determine the appropriate scales of information required for a project; (2) ground reference data collection to support the calibration and validation process; (3) selection of appropriate satellite image data, and this can include ancillary data such as digital elevation models; (4) application of a feature extraction algorithm that can best distinguish the feature(s) of interest from background features and produce a map product that is logically consistent; and (5) assessment of map accuracy using validation data to determine the quality of the product for various uses.
Geographic Information Systems (GIS) are fueled by geospatial data. This comprehensive article reviews the evolution of procedures and technologies used to create the data that fostered the explosion of GIS applications. It discusses the need to geographically reference different types of information to establish an integrated computing environment that can address a wide range of questions. This includes the conversion of existing maps and aerial photos into georeferenced digital data. It covers the advancements in manual digitizing procedures and direct digital data capture. This includes the evolution of software tools used to build accurate data bases. It also discusses the role of satellite based multispectral scanners for Earth observation and how LiDAR has changed the way that we measure and represent the terrain and structures. Other sections deal with building GIS data directly from street addresses and the construction of parcels to support land record systems. It highlights the way Global Positioning Systems (GPS) technology coupled with wireless networks and cloud-based applications have spatially empowered millions of users. This combination of technology has dramatically affected the way individuals search and navigate in their daily lives while enabling citizen scientists to be active participants in the capture of spatial data. For further information on changes to data capture, see Part 2: Implications and Case Studies.
Advances in technological approaches and tools to capture geospatial data have contributed to a vast collection of applications and enabled capacity for new programs, functions, products, workflows, and whole national-level spatial data infrastructure. In this entry, such outcomes and implications are described, focusing on developmental changes in specific application areas such as land use & land cover inventory, land parcel administration, and business, as well as examples from federal agencies, including the US Geological Survey, the Census Bureau, US Fish and Wildlife Service, and the US Department of Agriculture. These examples illustrate the diverse ways that the dramatic changes in geospatial data capture methods and approaches have affected workflows within agencies and have spatially empowered millions of users and the general public. For additional information on specific technical changes, see Part 1:
The interpretation of images that are created according to electromagnetic energy reflected from or emitted by earth surface features or atmosphere is a common practice to obtain useful information from raw image data. Images acquired by a device that is not in contact with objects and features are generally referred to as remotely sensed data, and the photo interpretation is generally carried out to extract meaningful information from image data for any subsequent uses. Specifically, this chapter covers elements of image interpretation, photo interpretation key, scale of an aerial photograph, heights, distances, and areas of objects in a photo, and land use land cover classification and mapping.