Urban Landmarks Extraction Based On Basic Geographic Information Database

Urban landmarks are spatial features that are relatively more prominent than their neighbors.This prominence includes being different from neighboring features in appearance or shape,being in an important location(for example,features that divide an urban space,are easy to access,or are located at decision points),or having a special function or cultural significance.As a carrier of geographical information,urban landmarks have played an indispensable role in spatial cognition.These landmarks are frequently used and have broad prospects for application in various aspects of way-finding and in representations of spatial knowledge.By using landmarks as spatial references,spatial cues,and symbols,people can more easily define the locations of other features,judge their own positions,and better recognize spatial patterns.People also prefer route guidance by using landmarks because these features are more understandable and elicit better results than other route guidance methods.Most researchers recognize that city landmarks have a cognitive hierarchy.Usually,this hierarchy is quantitatively ascertained by measuring landmark salience and reference regions.These kinds of partition methods without clear definition for multiple-scale landmarks,ignoring the differences,especially the differences except salience of landmarks among scales.In terms of urban landmarks extraction,common evaluation and extraction methods mainly include saliency estimation methods and data mining methods.Assessing the salience of urban landmarks is difficult.Moreover,no method exists to rapidly extract urban landmarks from basic geographic information databases.The goal of this paper is to solve these problems from the dual aspects of spatial knowledge representation and public spatial cognition rules.Landmarks are divided by spatial scales,characteristics of landmarks in multi-scale are studied separately,and a clear and systematic definition for multiple-scale urban landmarks is proposed,together with a category reference for extracting small-and medium-scale urban landmarks and a model for the large-scale automatic extraction of urban landmarks.In large-scale automatic urban landmark extraction model,the salience is expressed by two weighted parameters:the check-in totals and local accessibility.The extraction threshold is set according to a predefined number of landmarks to be extracted.Experiments show that the extraction results match the reference data well.