Abstract Title

Fire Monitoring and Assessment Platform (FireMAP): Post Classification Processing

Disciplines

Artificial Intelligence and Robotics | Environmental Indicators and Impact Assessment | Environmental Monitoring | Graphics and Human Computer Interfaces | Numerical Analysis and Scientific Computing

Abstract

Wildland fires are destructive to properties and dangerous to people in close proximity, with the cost of some large fires exceeding $1 billion. The goal of the Fire Monitoring Assessment Platform (FireMAP) is to provide fire managers with the tools and knowledge for acquiring, analyzing, and managing hyper-resolution imagery to map burn severity in a faster, safer, and more affordable manner than is currently possible.

After imagery of the burn area and its surroundings is captured and classified, some aspects of the burn data create fallacious results. Noise in the data results in misleading data points and inaccurately represented burn area borders. Post processed image analysis is done on the imagery to remedy described inaccurate data. White ash is removed during noise cancellation due to being spatially smaller than the full extent of the burned material. To prevent this, white ash will be morphologically expanded to represent the burned material before noise cancellation is applied to still be present after post classification processing.

Comments

Poster #W54

This document is currently not available here.

Share

COinS
 

Fire Monitoring and Assessment Platform (FireMAP): Post Classification Processing

Wildland fires are destructive to properties and dangerous to people in close proximity, with the cost of some large fires exceeding $1 billion. The goal of the Fire Monitoring Assessment Platform (FireMAP) is to provide fire managers with the tools and knowledge for acquiring, analyzing, and managing hyper-resolution imagery to map burn severity in a faster, safer, and more affordable manner than is currently possible.

After imagery of the burn area and its surroundings is captured and classified, some aspects of the burn data create fallacious results. Noise in the data results in misleading data points and inaccurately represented burn area borders. Post processed image analysis is done on the imagery to remedy described inaccurate data. White ash is removed during noise cancellation due to being spatially smaller than the full extent of the burned material. To prevent this, white ash will be morphologically expanded to represent the burned material before noise cancellation is applied to still be present after post classification processing.