Extracting and understanding urban areas of interest using geotagged photos

Hu, Yingjie; Gao, Song; Janowicz, Krzysztof; Yu, Bo; Li, Wenwen; Prasad, Sathya

doi:10.1016/j.compenvurbsys.2015.09.001

Cited by 267 publications

(173 citation statements)

References 47 publications

Supporting

Mentioning

168

Contrasting

Unclassified

Order By: Relevance

“…Previous studies have demonstrated that different POI types have distinctive semantic signatures (Janowicz, ) (i.e., spatial, temporal, and thematic distributions) based on crowd‐sourced location‐based social media data analysis, in analogy to spectral bands in remote sensing (McKenzie, Janowicz, Gao, Yang, & Hu, ). There is a growing trend of using location‐awareness sensing data (e.g., trajectories from mobile phones), POI data, and social media feeds to study the spatial and social structure of urban environments (Hu et al, ; Jiang, Alves, Rodrigues, Ferreira, & Pereira, ; Liu et al, ; McKenzie et al, ; Pei et al, ; Steiger, Westerholt, & Zipf, ; Yao et al, ). However, few studies have investigated the latent relationships among different types of POIs and how they spatially interact with each other to support urban functions, such as education, business, and shopping.…”

Section: Introductionmentioning

confidence: 99%

Extracting urban functional regions from points of interest and human activities on location‐based social networks

Gao

Janowicz

Couclelis

2017

Transactions in GIS

Self Cite

361

185

View full text Add to dashboard Cite

Data about points of interest (POI) have been widely used in studying urban land use types and for sensing human behavior. However, it is difficult to quantify the correct mix or the spatial relations among different POI types indicative of specific urban functions. In this research, we develop a statistical framework to help discover semantically meaningful topics and functional regions based on the co‐occurrence patterns of POI types. The framework applies the latent Dirichlet allocation (LDA) topic modeling technique and incorporates user check‐in activities on location‐based social networks. Using a large corpus of about 100,000 Foursquare venues and user check‐in behavior in the 10 most populated urban areas of the US, we demonstrate the effectiveness of our proposed methodology by identifying distinctive types of latent topics and, further, by extracting urban functional regions using K‐means clustering and Delaunay triangulation spatial constraints clustering. We show that a region can support multiple functions but with different probabilities, while the same type of functional region can span multiple geographically non‐adjacent locations. Since each region can be modeled as a vector consisting of multinomial topic distributions, similar regions with regard to their thematic topic signatures can be identified. Compared with remote sensing images which mainly uncover the physical landscape of urban environments, our popularity‐based POI topic modeling approach can be seen as a complementary social sensing view on urban space based on human activities.

show abstract

Section: Introductionmentioning

confidence: 99%

Extracting urban functional regions from points of interest and human activities on location‐based social networks

Gao

Janowicz

Couclelis

2017

Transactions in GIS

Self Cite

361

185

View full text Add to dashboard Cite

show abstract

“…Moreover, the city centre is a special region that consists of several units (commercial land in this paper) with different spatial information. The present methods primarily focus on the spatial patterns (e.g., [37,38]) or non-spatial inequality (e.g., [33,36]). In this paper, we characterised the city centre from commercial land data relating to a series of socio-economic indicators, and propose a methodology considering spatial proximity and attribute similarity for delineating the city centre from commercial land use.…”

Section: Introductionmentioning

confidence: 99%

Building an Urban Spatial Structure from Urban Land Use Data: An Example Using Automated Recognition of the City Centre

Zhu

Sun

2017

IJGI

View full text Add to dashboard Cite

It has been suggested that the method of constructing an urban spatial structure typically follows a forward process from planning and design up to expression, as reflected in both graphic and text descriptions of urban planning. Although unorthodox, the original status structures can be extracted and constructed from an existing urban land-use map. This approach not only provides the methodological foundation for urban spatial structure evolution and allows for a comparative and quantitative analysis between the existing and planned conditions, but also lays a theoretical basis for failure in scientific decision making during the planning phase. This study attempts to achieve this by identifying the city centre (a typical element of the urban spatial structure) from urban land use data. The city centre is a special region consisting of several units with particular spatial information, including geometric attributes, topological attributes, and thematic attributes. In this paper, we develop a methodology to support the delineation of the city centre, considering these factors. First, using commercial land data, we characterise the city centre as units based on a series of indicators, including geometric and thematic attributes, and integrate them into a composite index of "urban centrality"; Second, a graph-based spatial clustering method that considers both topological proximity and attribute similarity is designed and used to identify the city centre. The precise boundary of the city centre is subsequently delimited using a shape reconstruction method based on the cluster results. Finally, we present a case study to demonstrate the effectiveness and practicability of the methodology.

show abstract

“…There are also attempts to mine semantic information in land cover classification and other related areas. Hu et al extracted tags from Flickr photos and proposed a TF-IDF (Term Frequency-inverse Document Frequency) algorithm with textual information from tags, in order to explore urban areas of interest [29]. Specifically, TF-IDF is a method to evaluate how important a word is in the textual information.…”

Section: Semantic Mining For Land Cover Classificationmentioning

confidence: 99%

Employing Crowdsourced Geographic Information to Classify Land Cover with Spatial Clustering and Topic Model

et al. 2017

View full text Add to dashboard Cite

Abstract:Land cover classification is the most important element of land cover mapping and is a key input to many societal benefits. Traditional classification methods require a large amount of remotely sensed images, which are time consuming and labour intensive. Recently, crowdsourcing geographic information (CGI), including geo-tagged photos and other sources, has been widely used with lower costs, but still requires extensive labour for data classification. Alternatively, CGI textual information is available from online sources containing land cover information, and it provides a useful source for land cover classification. However, the major challenge of utilising CGI is its uneven spatial distributions in land cover regions, leading to less reliability of regions for land cover classification with sparsely distributed CGI. Moreover, classifying various unorganised CGI texts automatically in each land cover region is another challenge. This paper investigates a faster and more automated method that does not require remotely sensed images for land cover classification. Spatial clustering is employed for CGI to reduce the effect of uneven spatial distributions by extracting land cover regions with high density of CGI. To classify unorganised various CGI texts in each extracted region, land cover topics are calculated using topic model. As a case study, we applied this method using points of interest (POIs) as CGI to classify land cover in Shandong province. The classification result using our proposed method achieved an overall accuracy of approximately 80%, providing evidence that CGI with textual information has a great potential for land cover classification.

show abstract

Extracting and understanding urban areas of interest using geotagged photos

Cited by 267 publications

References 47 publications

Extracting urban functional regions from points of interest and human activities on location‐based social networks

Extracting urban functional regions from points of interest and human activities on location‐based social networks

Building an Urban Spatial Structure from Urban Land Use Data: An Example Using Automated Recognition of the City Centre

Employing Crowdsourced Geographic Information to Classify Land Cover with Spatial Clustering and Topic Model

Contact Info

Product

Resources

About