期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2008
卷号：XXXVII Part B3b
页码：545-548
出版社：Copernicus Publications
摘要：The growing neuron gas (GNG) algorithm is an excellent self-organization tool, which efficiently combines the graph and neural network techniques. The gas formation starts with two connected neurons and during the training both the neurons (nodes) and their connections are iteratively added.The most relevant advantage of this technology is that it forms the final graph structure considering the input data points regarding the control parameters, but without the strict requirement of any prior hypothesis of the graph.Although the graph nodes can represent data points of any arbitrary number of dimensions, in this specific application they are taken as two-dimensional ones. The data points derived by simple image processing operations, like thresholding the intensity values and by other similar low-level segmentation techniques. The algorithm is fast and can handle even larger set of data points.The paper gives an overview about the main self-organizing and unsupervised neural network techniques. It's followed by the description of the growing neuron gas algorithm, and then its application in road network detection is presented. The illustration of the proposed method with aerial and satellite imagery also contains accuracy and performance analysis, of course in comparison with other detection methodologies
