Images to Maps

Satellite the village of Nukuni on Ono-i-Lau, Fiji. Ono-i-Lau is a group of islands within a barrier reef system in the Fijian archipelago of Lau Islands. Photo © Planet Labs Inc.

Remote sensing images are a grid of pixels with numerical values whereas maps use X and Y coordinates to define the location of points, lines, and areas (polygons) that correspond to map features. Transforming a satellite image into a map that has high accuracy is a process that requires experts and fieldwork.

From satellite image to map of the reef with benthic classes

From satellite image (left) to map of the reef with benthic classes (right). This photograph and map depict Australia’s Heron Island, a coral cay at the southern end of the Great Barrier Reef. Image © Allen Coral Atlas

Image Classification

To create a map from an image, classification techniques are applied. One of the more popular approaches is an object-based image analysis, a recent and powerful image classification technique.

object based classification

Segmentation and classification of an image during an object-based analysis. Image © GISGeography

An object-based image analysis first segments the image into objects. The segmentation is based on the spectral signatures of the pixels, the shape and size of the object, or the texture of the pixels within the object. Once the image is segmented, the user matches each land cover class to a few sample objects. The image is then classified.

Classification Scheme

Classification schemes are used to assign a class to an object on the image. For coral reefs, having prior knowledge of the area will help to identify potential classes to be mapped. These classes are used to form a classification scheme which is used to set up field surveys and target representative areas for training data collection.

Below is an example of a hierarchical classification used for the maps in the Allen Coral Atlas that includes geomorphic and benthic classification and is general enough to be used on a global scale.

aca classification

Example of the Allen Coral Atlas classification scheme for an atoll. Source: Kennedy et al. 2020

Field Surveys

field surveys

Snorkeler finishing a field survey. Photo © Emma Kennedy, University of Queensland

Field data is a key component of creating a map of high quality. Field data builds a link between the image and the mapped features.

Field survey objectives:

  • Identify the habitat classes to be mapped and create a classification scheme
  • Locate representative areas of each habitat class in order to collect training data
  • Generate data needed for image calibration, such as water clarity and depth
  • Collect sufficient stratified random points to evaluate the accuracy of the classification (predicted vs. observed classes)

There are a variety of methods that can be used to collect field data for classification validation besides SCUBA and snorkel surveys. Data can be collected using aerial and surface drones, underwater instruments such as remotely operated vehicles (ROVs), spot checks from the boat using a glass-bottom viewer, or even local knowledge.

diver spectral signature

Diver collecting spectral reflectance signatures for individual bottom types. Photo © Kovacs, University of Queensland

Training Data

Training data are any type of georeferenced field data collected for image classification. They are representative “ground referenced” samples of each class in the classification scheme. They are used to “train” the classification algorithm to recognize the unique spectral reflectance patterns in each of the classes. These can be collected in several ways such as SCUBA and snorkel surveys, aerial and surface drones, remotely operated vehicles (ROVs), boats, or even local knowledge.

Accuracy Assessment

An accuracy assessment is an important part of any classification project and provides a measure of how accurate the map product is. It uses independent “ground referenced” data to calculate a statistically-based accuracy score based on the comparison of the predicted (mapped) class verses observed class in the field. In other words, the classified pixels or classified objects are compared to reality, or what actually exists at that location. While independent field data collection can be time consuming and expensive, these data can also be derived from interpreting high-resolution imagery, existing classified imagery, or local experts.

pporno youjizz xmxx teacher xxx Sex
Translate »