Guangdong Key Laboratory for Urbanization and Geo simulation

Guangzhou, China

Guangdong Key Laboratory for Urbanization and Geo simulation

Guangzhou, China

Time filter

Source Type

Zhang X.,Sun Yat Sen University | Zhang X.,Guangdong Key Laboratory for Urbanization and Geo simulation | Luo G.,Sun Yat Sen University | Luo G.,Guangxi Teachers Education University | And 3 more authors.
ISPRS International Journal of Geo-Information | Year: 2017

Multi-scale object matching is the key technology for upgrading feature cascade and integrating multi-source spatial data. Considering the distinctiveness of data at different scales, the present study selects residential areas in a multi-scale database as research objects and focuses on characteristic similarities. This study adopts the method of merging with no simplification, clarifies all the matching pairs that lack one-to-one relationships and places them into one-to-one matching pairs, and conducts similarity measurements on five characteristics (i.e., position, area, shape, orientation, and surroundings). The relevance vector machine (RVM) algorithm is introduced, and the method of RVM-based spatial entity matching is designed, thus avoiding the needs of weighing feature similarity and selecting matching thresholds. Moreover, the study utilizes the active learning approach to select the most effective sample for classification, which reduces the manual work of labeling samples. By means of 1:5000 and 1:25,000 residential areas matching experiments, it is shown that the RVM method could achieve high matching precision, which can be used to accurately recognize 1:1, 1:m, and m:n matching relations, thus improving automation and the intelligence level of geographical spatial data management. © 2017 by the authors.


Zhou C.,Sun Yat Sen University | Zhou C.,Guangdong Key Laboratory for Urbanization and Geo simulation | Hu J.,Sun Yat Sen University | Hu J.,Guangdong Key Laboratory for Urbanization and Geo simulation | And 3 more authors.
Dili Xuebao/Acta Geographica Sinica | Year: 2016

Research into urban socio- spatial structure was first introduced to Chinese geographers in 1986. Since the beginning of the free-market economic reform in 1987, Chinese cities have changed rapidly and have attracted substantial attention from academia. Chinese case studies have predominantly concerned megacities such as Beijing, Shanghai, and Guangzhou. As the pioneer of China's reform and opening-up, Guangzhou is representative of large Chinese cities in the transformation of the socio-spatial structure. The first research was initiated in the social areas of Guangzhou in 1985. Zhou used data from the fifth population census of 2000 to analyze the social areas of Guangzhou and identified three evolution modes of the socio-spatial structure: the first is based on the development of the old city, the second fouses on the development of the educational or industrial "enclave", and the third presents the development of agricultural areas. The research on the evolution of urban socio- spatial structure, as a vital part of urban geography study, needs a long- term follow- up survey and analysis. Thus, using the Factor Ecological Analysis (FEA), this paper analyzes the social area in Guangzhou with the Sixth National Population Census data of 2010, and further divides the social area into 7 sub-types based on the 7 main factors. Comparing the studies of the 2000s and 1985, we found that: (1) Most of the principal factors are available for the years of 1985-2010, and they have played an increasingly important role during the period studied. In addition, some individual principal factors only appear in a certain year, thus have strong distinct characteristics. (2) The evolution of social areas in Guangzhou has been mainly characterized by type conversion and followed by regional spatial differentiation in 1985-2000; and vice versa in 2000- 2010. (3) This study further found evidence of the three evolution modes proposed in 2000 based on the development of the old town, development of enclave of industry and education, and development of the rural community; then it put forward a new model based on the development of the social areas in suburban towns; (4) The market mechanism, administrative mechanism and the family life cycle mechanism work together to the evolution of socio-spatial structure. © 2016, Science Press. All right reserved.


Guo T.,Sun Yat Sen University | Zhang X.,Sun Yat Sen University | Zhang X.,Guangdong Key Laboratory for Urbanization and Geo simulation
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica | Year: 2013

To realize automatic extraction of change information in GIS vector data updating, a change information recognition method based on neural network decision tree is proposed. A change information hierarchical detection method based on quad-tree was designed and realized in this paper. With the comparison of vertex-edge characteristics, this method could rapidly locate change areas. Based on the matching of correspondent objects, a neural network decision tree method was applied to recognize the change information. This method combined the effective logical judgment of decision tree and adaptive processing of neural network. 1:2000 Topographical data were used to verify the effectiveness of the method. Experimental result shows that this method can achieve high computing speed and effectively detect the change pattern of vector data, which can improve the automation and intelligence level of dynamic updating in GIS database.


Sun Y.,Sun Yat Sen University | Zhang X.,Sun Yat Sen University | Zhang X.,Guangdong Key Laboratory for Urbanization and Geo simulation | Kang T.,Foshan Urban Planning Design and Surveying Research Institute | And 2 more authors.
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica | Year: 2013

Improved GAC Model based on the initial curve and the external force is proposed. It is a new method for automatic building extraction from LiDAR point clouds combined with the aerial image. The morphological alternating sequential filtering is used to access the initial curve automatically, and then the external force is improved by the LiDAR depth gradient image, so the improved geodesic active contour (IGAC) model is proposed. Experiment indicates that this method can inhibit the weak boundary leakage and produce high accuracy and completeness of building boundary.


Luo G.,Sun Yat Sen University | Luo G.,Guangxi Teachers Education University | Zhang X.,Sun Yat Sen University | Zhang X.,Guangdong Key Laboratory for Urbanization and Geo simulation | Guo T.,Sun Yat Sen University
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica | Year: 2014

The change-only information is important to the recording of object life cycle, the establishment of spatial-temporal database and the updating of GIS database. To solve the problem of low efficiency of traditional method in change detection when the data volume is large, we proposed a highly efficient method of change detection based on the grid-partitioning of data and the comparison of synthesis of spatial and attribute information. This method only detects the changed grid to reduce the detection region. In order to solve the matching problem of old features and new features, we propose a method named optimal combination-matching method. The method selects the optimally matched features through the comparison of the characteristic of spatial information and semantic information. The method's high efficiency and accuracy in change detection of large volume of spatial data and matching of changed features is validated by experiment. ©, 2014, SinoMaps Press. All right reserved.


Sun Y.,Sun Yat Sen University | Zhang X.,Sun Yat Sen University | Zhang X.,Guangdong Key Laboratory for Urbanization and Geo simulation | Luo G.,Sun Yat Sen University
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica | Year: 2014

Based on the edge and the local region information, a new active contour model is proposed in this paper, which can process multi-spectral image. And it is used to extract the building roof boundary from LiDAR data. The input image of this model is processed by microstation software, the LiDAR point cloud is classified firstly and then the classified results are converted to raster format. This model is solved by variational level set method, and the minimal solution is the exact building roof boundary. It can eliminate the restrictions on the initialization and the image types of ACM, and it is suitable for the automatic extraction of any shape of building roof boundaries. In addition, the computational time of the new model is reduced by adding the level set rules. Building roof boundary extraction experiment result indicates that this model can obtain higher accuracy in matched rate, shape similarity and positional accuracy than that of the IAC model and the GACcolor model.


Zhou S.,Sun Yat Sen University | Zhou S.,Guangdong Key Laboratory for Urbanization and Geo simulation | Xie M.,United Investment Group Co. | Kwan M.-P.,University of Illinois at Urbana - Champaign | Kwan M.-P.,University Utrecht
Habitat International | Year: 2015

The social and spatial patterns of ageing population in urban China illuminate the influence of the socioeconomic transformation associated with the dual economic system. Guangzhou, one of China's megacities, is used as a case study in this paper. Data from the 2010 National Census were used to examine the spatial differentiation and the related factors of ageing communities in Guangzhou. Using social area analysis, the study identified six categories of ageing communities: traditional inner-city communities, traditional danwei residential communities, commercial housing ageing communities, danwei compound ageing communities, immigrant ageing communities, and rural ageing communities. The paper analyses the reasons and processes leading to the clustering of the elderly population in each category of areas associated with distinctive spatial patterns of ageing differentiation. These patterns suggest that the socio-spatial differentiation of ageing communities is a joint outcome of urban development, housing policies, personal status and family relationships. The dynamics of both ageing in place and ageing with migration had a dual impact on the spatial, social and ecological patterns of ageing communities. The spatial differentiation of ageing communities in the study area should be taken into account when formulating urban planning and public policies. In addition, a dynamic public facility and service allocation system is also necessary to meet the needs associated with evolving socio-spatial urban restructuring. © 2015 Elsevier Ltd.


Zhou S.,Sun Yat Sen University | Zhou S.,Guangdong Key Laboratory for Urbanization and Geo simulation | Deng L.,Guangzhou Panyu Urban Planning and Design Institute | Huang M.,University College London
Chinese Geographical Science | Year: 2013

Metropolitan cities in China are commonly confronted with unresolved traffic congestion issues, primarily due to rapidly increasing traffic demand. Group disparity between commuting mode choice and its spatial distribution on road networks has enabled us to examine the factors that give rise to the discrepancies and the fundamental spatial causes of traffic congestion. In recent years, micro-perspective, individual, and behavior-based spatial analysis have mushroomed and been facilitated with effective tools such as temporal geographic information systems (T-GIS). It is difficult to study the interrelations between transport and space on the basis of commuting mode choice since the mode choice data are invisible in a specific space such as a particular road network. Therefore, in the field of transport, the classical origin destination (OD) four-stage model (FSM) is usually employed to calculate data when studying commuting mode choice. Based on the relative principles of T-GIS and the platform of ArcGIS, this paper considers Guangzhou as a case study and develops a spatio-temporal tool to examine the daily activities of residents. Meanwhile, the traffic volume distribution in rush hours, which was analyzed according to commuting modes and how they were reflected in the road network, was scrutinized with data extracted from travel diaries. Moreover, efforts were made to explain the relationship between traffic demand and urban spatial structure. Based on the investigation, this research indicates that traffic volumes in divergent groups and on the road networks is driven by: 1) the socio-economic characteristics of travelers; 2) a jobs-housing imbalance under suburbanization; 3) differences in the spatial supply of transport modes; 4) the remains of the Danwei (work unit) system and market development in China; and 5) the transition of urban spatial structure and other factors. © 2013 Science Press, Northeast Institute of Geography and Agricultural Ecology, CAS and Springer-Verlag Berlin Heidelberg.


Chen Y.,Sun Yat Sen University | Chen Y.,Guangdong Key Laboratory for Urbanization and Geo simulation | Li X.,Sun Yat Sen University | Li X.,Guangdong Key Laboratory for Urbanization and Geo simulation | And 4 more authors.
International Journal of Geographical Information Science | Year: 2012

In recent years, agent-based models (ABMs) have become a prevalent approach for modelling complex urban systems. As a class of bottom-up method, ABMs are capable of simulating the decision-making as well as the multiple interactions of autonomous agents and between agents and the environment. The definition of agents' behaviour is a vital issue in implementing ABMs to simulate urban dynamics. Urban economic theory has provided effective ways to cope with this problem. This theory argues that the formation of urban spatial structure is an endogenous process resulting from the interactions among individual actors that are spatially distributed. However, this theory is used to explain urban phenomena regardless of spatial heterogeneity in most cases. This study combines GIS, ABM and urban economic models to simulate complex urban residential dynamics. The time-extended model is incorporated into an ABM so as to define agents' behaviour on a solid theoretical basis. A spatial variable is defined to address the neighbourhood effect by considering spatial heterogeneity. The proposed model is first verified by the simulation of three scenarios using hypothetical data: (1) single dominated preference; (2) varying preferences on the basis of income level; and (3) spatially heterogeneous environment. Then the model is implemented by simulating the residential dynamics in Guangzhou, China. © 2012 Copyright Taylor and Francis Group, LLC.


Zhou S.,Sun Yat Sen University | Zhou S.,Guangdong Key Laboratory for Urbanization and Geo simulation | Hao X.,Sun Yat Sen University | Hao X.,Guangdong Key Laboratory for Urbanization and Geo simulation | And 3 more authors.
Acta Geographica Sinica | Year: 2014

Urban multi-center phenomenon is very common in many countries, which challenges urban models with the assumption of single center. Although there are literatures trying to explain the mechanism of multi-center urban system using models based on multicenter, the lack of empirical research makes the models being questioned. Under the pattern of multi-center, does the traditional classical geographic model like law of distance decay exist? What factors will disturb the model? This study aims to analyze and validate the spatiotemporal discipline of attration and mutual relationship between two commercial centers, based on spatio-temporal data mining of floating cars' GPS data and the recognition of two important commercial centers in Shenzhen City, China. The study reveals that the attraction between two commercial centers shows distinct power function relationship, which validates the law of geographic spatial decay. At the same time, the spatial decay's law shows some local disturbances due to a series of causes, such as the mutual attraction from other important and crowded areas, the influence of infrastructure to accessibility, urban spatial layout factor like landform and humanity factors like consumer behavior and preference etc. ©, 2014, Science Press. All right reserved.

Loading Guangdong Key Laboratory for Urbanization and Geo simulation collaborators
Loading Guangdong Key Laboratory for Urbanization and Geo simulation collaborators