Semi-automated segment generation for geographic novelty detection using edge and area metrics
Access Status
Authors
Date
2012Type
Metadata
Show full item recordCitation
Source Title
ISSN
School
Collection
Abstract
An approach to generating accurate image segments for land-cover mapping applications is to model the process as an optimisation problem. Area-based empirical discrepancy metrics are used to evaluate instances of generated segments in the search process. An edge metric, called the pixel correspondence metric (PCM), is evaluated in this approach as a fitness function for segmentation algorithm free-parameter tuning. The edge metric is able to converge to user-provided reference segments in an earth observation mapping problem when adequate training data are available. Two common metaheuristic search functions were tested, namely particle swarm optimisation (PSO) and differential evolution (DE). The edge metric is compared with an area-based metric, regarding classification results of the land-cover elements of interests for an arbitrary problem. The results show the potential of using edge metrics, as opposed to area metrics, for evaluating segments in an optimisation-based segmentation algorithm parameter-tuning approach.
Related items
Showing items related by title, author, creator and subject.
-
Kloser, Rudolf J (2007)The background to this thesis is Australia’s Oceans Policy, which aims to develop an integrated and ecosystem-based approach to planning and management. An important part of this approach is the identification of natural ...
-
Gillespie, T.; Keppel, Gunnar; Pau, S.; Price, J.; Jaffre, T.; O'Neill, K. (2013)Aim: We examine variation in woody plant species richness and endemism within tropical dry forest on oceanic islands and determine what climatic and biogeographic metrics best explain native species richness and endemism ...
-
Ren, Yan; Xiaodong, Liu; Liu, Wan-Quan (2012)In this paper we propose a new density based clustering algorithm via using the Mahalanobis metric. This is motivated by the current state-of-the-art density clustering algorithm DBSCAN and some fuzzy clustering algorithms. ...