Supervised and unsupervised classification
Supervised classification uses the spectral signature defined in the training set. For example, it determines each class on what it resembles most in the training set. The common supervised classification algorithms are maximum likelihood and minimum-distance classification.
Unsupervised classification is an easy way to segment and understand an image.In unsupervised classification, it first groups pixels into “clusters” based on their properties. In order to create “clusters”, analysts use image clustering algorithms such as K-means and ISODATA. After picking a clustering algorithm, you identify the number of groups you want to generate.
Land use / Land cover mapping
Land management and land planning requires a knowledge of the current state of the landscape. Understanding current land cover and how it is being used, along with an accurate means of monitoring change over time, is vital to any person responsible for land management. Measuring current conditions and how they are changing can be easily achieved through land cover mapping, a process that quantifies current land resources into a series of thematic categories, such as forest, water, and paved surfaces. By using remotely sensed imagery and semi-automated classification methods, Cape provides cost-effective and accurate means to derive land resource information and maintain its currency into the future.
Enhancements are used to make it easier for visual interpretation and understanding of imagery. The advantage of digital imagery is that it allows us to manipulate the digital pixel values in an image. Although radiometric corrections for illumination, atmospheric influences, and sensor characteristics may be done prior to distribution of data to the user, the image may still not be optimized for visual interpretation. Remote sensing devices, particularly those operated from satellite platforms, must be designed to cope with levels of target/background energy which are typical of all conditions likely to be encountered in routine use.
Georeferencing and Rectification
Georeferencing is the process of taking a digital image, it could be an airphoto, a scanned geologic map, or a picture of a topographic map, and adding geographic information to the image so that GIS or mapping software can ‘place’ the image in its appropriate real world location. This process is completed by selecting pixels in the digital image and assigning them geographic coordinates. In rare instances, one may already know the geographic coordinates of certain pixels in an image; more frequently, a non-georeferenced image is georeferenced to an existing image that already has embedded geographic information.
Mineral identification and exploration
Hyperspectral remote sensing and other high-resolution multispectral satellites are used for mineral identification and exploration.
Remote sensing images are used for mineral exploration in two key ways:
- Mapping the geology, faults and fractures of an ore deposit.
- Recognizing hydrothermally altered rocks by their spectral signature.
Images are gathered either through optical sensors, or through synthetic aperture sensors. Optical sensors measure the spectral data of sunlight reflected from the Earth’s surface. Synthetic aperture sensors are able to sense electromagnetic data by transmitting microwaves and receiving the back-scatter waves from the Earth’s surface.