Unsupervised spatio-temporal data mining framework for burned area mapping

摘要

A method reduces processing time required to identify locations burned by fire by receiving a feature value for each pixel in an image, each pixel representing a sub-area of a location. Pixels are then grouped based on similarities of the feature values to form candidate burn events. For each candidate burn event, a probability that the candidate burn event is a true burn event is determined based on at least one further feature value for each pixel in the candidate burn event. Candidate burn events that have a probability below a threshold are removed from further consideration as burn events to produce a set of remaining candidate burn events.

主权项

1. A method of reducing processing time required to identify locations burned by fire, the method comprising:
receiving a feature value for each pixel in an image, each pixel representing a sub-area of a location; grouping pixels based on similarities of the feature values to form candidate burn events; for each candidate burn event, determining a probability that the candidate burn event is a true burn event based on at least one further feature value for each pixel in the candidate burn event; and removing candidate burn events that have a probability below a threshold from further consideration as burn events to produce a set of remaining candidate burn events.