Xiang Zhang

Xiang Zhang
Sun Yat-Sen University | SYSU · School of Geospatial Engineering and Science

PhD

About

58
Publications
15,818
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
536
Citations
Introduction
Hi, I am Xiang Zhang and currently working at Sun Yat-Sen University. My research field lies in GIScience and Cartography. Currently I am working on VGI (i.e. crowd-sourced geographic data and trajectories) related topics spanning from its fitness-for-use and uncertainty issues via processing to knowledge discovery (including visual analytics). This can be funny and raises many interesting applications at the cross-border of geography and other fields.
Additional affiliations
October 2021 - present
Sun Yat-Sen University
Position
  • Professor (Associate)
January 2015 - September 2021
Wuhan University
Position
  • Professor (Associate)
January 2013 - December 2014
Wuhan University
Position
  • PostDoc Position
Description
  • worked on the quality aspect (or fitness-for-use) of crowd-sourced geo-information

Publications

Publications (58)
Article
Crowd-sourced geographic information has great potential in scientific and public domains, and is recently under consideration by geospatial professionals as an alternative to traditional spatial data collection. The success, however, implies a need to build long-term reliance on the crowd-sourcing projects, and poses growing concern over the quali...
Article
Integrating updates from timely sources such as volunteered geographic information (VGI) into the spatial data maintained at official agencies is becoming a more demanding requirement but presents many challenges. This paper proposes an approach to addressing the technical challenge of propagating updates from timely sources (e.g. OpenStreetMap) to...
Article
The aim of matching spatial data at different map scales is to find corresponding objects at different levels of detail (LODs) that represent the same real-world phenomena. This is a prerequisite for integrating, evaluating and updating spatial data collected and maintained at various scales. However, matching spatial data is not straightforward du...
Article
Full-text available
Knowledge or rule-based approaches are needed for quality assessment and assurance in professional or crowdsourced geographic data. Nevertheless, many types of geographic knowledge are statistical in nature and are therefore difficult to derive rules that are meaningful for this purpose. The rules of continuity and symmetry considered in this paper...
Article
Full-text available
Building patterns are important features that should be preserved in the map generalization process. However, the patterns are not explicitly accessible to automated systems. This paper proposes a framework and several algorithms that automatically recognize building patterns from topographic data, with a fo- cus on collinear and curvilinear alignm...
Article
Full-text available
Recently, many researchers tried to generate (generalised) maps using deep learning, and most of the proposed methods deal with deep neural network architecture choices. Deep learning learns to reproduce examples, so we think that improving the training examples, and especially the representation of the initial geographic information, is the key is...
Article
Full-text available
Deep learning techniques have recently been experimented for map generalization. Although promising, these experiments raise new problems regarding the evaluation of the output images. Traditional map generalization evaluation cannot directly be applied to the results in a raster format. Additionally, the internal evaluation used by deep learning m...
Article
The vegetative cover in and surrounding the Rohingya refugee camps in Ukhiya-Teknaf is highly vulnerable since millions of refugees moved into the area, which led to severe environmental degradation. In this research, we used a supervised image classification technique to quantify the vegetative cover changes both in Ukhiya-Teknaf and thirty-four r...
Article
The marginal ice zone (MIZ) around Antarctica is an important air–ice–ocean–wave interaction area and a crucial habitat for marine life. Given its dynamic nature, it is essential to understand and quantify both the short- and long-term changes of its extent. In this study, we investigated the MIZ extent time series using multifractal spectrum and [...
Article
New insights into urban functional zones with a specific focus on leisure is of great significance for human‐oriented urban development. The spatiotemporal pattern of urban leisure functional zones (ULFZ) reflects to what extent human psychological needs are satisfied. This article aims to discern ULFZ and reveal their changing regularity based on...
Article
Full-text available
This article presents how a generative adversarial network (GAN) can be employed to produce a generalised map that combines several cartographic themes in the dense context of urban areas. We use as input detailed buildings, roads, and rivers from topographic datasets produced by the French national mapping agency (IGN), and we expect as output of...
Conference Paper
Full-text available
The use of deep learning techniques for map generalisation raises new problems regarding the evaluation of the results: (1) images are used as input/output instead of vector data; (2) the deep learning processes do not guarantee results that follow cartographic principles; (3) the deep learning models are black boxes that hide the causal mechanisms...
Article
Full-text available
Among cartographic generalisation problems, the generalisation of sinuous bends in mountain roads has always been a popular one due to its difficulty. Recent research showed the potential of deep learning techniques to overcome some remaining research problems regarding the automation of cartographic generalisation. This paper explores this potenti...
Article
Full-text available
As a result of the increasing popularity of indoor activities, many facilities and services are provided inside buildings; hence, there is a need to visualize points-of-interest (POIs) that can describe these indoor service facilities on indoor maps. Over the last few years, indoor mapping has been a rapidly developing area, with the emergence of m...
Preprint
Full-text available
The vegetative cover in and surrounding the Rohingya refugee camps in Ukhiya-Teknaf is highly vulnerable since millions of refugees moved into the area, which led to severe environmental degradation. In this research, we used a supervised image classification technique to quantify the vegetative cover changes both in Ukhiya-Teknaf and thirty-four r...
Article
Full-text available
The shrimp-farming area and shrimp yield are continuously changing in the southwestern coastal districts of Bangladesh. The three southwestern coastal districts, Bagerhat, Satkhira, and Khulna, along with Rampal, a subdistrict of Bagerhat, contribute 75% of the total shrimp yield of Bangladesh. However, the shrimp yield and farming area have declin...
Article
The rapid increase in movement trajectory data causes data storage, transmission, computational processing, and visualization problems. These issues can be alleviated through trajectory simplification, which removes unnecessary details from raw trajectories. Most existing studies that focused on trajectory simplification considered freely moving ob...
Article
The automation of map generalization has been keeping researchers in cartography busy for years. Particularly great progress was made in the late 90s with the use of the multi-agent paradigm. Although the current use of automatic processes in some national mapping agencies is a great achievement, there are still many unsolved issues and research se...
Article
Full-text available
Crowd-sourced geographic information is becoming increasingly available, providing diverse and timely sources for updating existing spatial databases to facilitate urban studies, geoinformatics, and real estate practices. However, the discrepancies between heterogeneous datasets present challenges for automated change detection. In this paper, we i...
Data
Distributions of nr − Jrr for typical cities. nr − Jrr = 1 indicates the strongest form of spatial order. (TIF)
Data
Distributions of the number of segments in natural streets for typical cities. (TIF)
Data
Typical situations where parallel road detection algorithm gives acceptable and unsatisfactory results. Recognizing divided highways in cases like (g) is highly challenging even for a human subject. (TIF)
Data
Distribution of zrr for groups of road segments formed by different strategies. (a) non-continuous random; (b) continuous random; (c) self-best-fit; (d) every-best-fit; (e)-(h) corresponding scatterplot of zrr against N (number of segments in a group/stroke) for each strategy (street data: Nav). (TIF)
Data
Distributions of zrs for typical cities. zrs for all natural streets are shown in blue; zrs for selected natural streets (N ≥ 10) are superimposed on top of the blue ones (red); red vertical line indicates z = 0. (TIF)
Article
The continuous multi-scale representation is one of attractive problems in mapping technology. Conventional mapping which uses the subdivision of multilevel tiles or multi-version storage to accomplish spatial multi-scale representations has the problems including data redundancy, inconsistency between diffident levels, the dramatic change in scale...
Article
The availability of geospatial data has increased significantly over recent decades. As a result, the question of how to update spatial data across different scales has become an attractive topic. One promising strategy is to use an updated larger-scale dataset as a reference for detecting and updating changed objects represented in a to-be-updated...
Article
Full-text available
This study proposes a template matching simplification method from the perspective of shape cognition based on the typical template characteristics of building distributions and representations. The method first formulates a series of templates to abstract the building shape by generalizing their polygons and analyzing their symbolic meanings, then...
Article
Full-text available
In recent years, main cities in China have been suffering from hazy weather, which is gaining great attention among the public, government managers and researchers in different areas. Many studies have been conducted on the topic of urban air quality to reveal different aspects of the air quality problem in China. This paper focuses on the visualiz...
Article
Street patterns reflect the distribution characteristics of a street network and affect the urban structure and human behavior. The recognition of street patterns has been a topic of interest for decades. In this study, a linear tessellation model is proposed to identify the spatial patterns in street networks. The street segments are broken into c...
Article
Full-text available
To address the cartographic problems in map mash-up applications in the Web 2.0 context, this paper studies a clutter-free technique for visualizing large symbols on Web maps. Basically, a quadtree is used to select one symbol in each grid cell at each zoom level. To resolve the symbol overlaps between neighboring quad-grids, multiple offsets are a...
Conference Paper
Full-text available
Ontology-driven concept inference has the merit of high flexibility and transparency. Users can composite and reuse atomic primitive concepts and relationship to interpret complex geographical concept without the need to retouch or even know the technical details. The major issue that we are focusing on is the implicit geometry problem. That is, th...
Chapter
Ontology-driven concept inference has the merit of high flexibility and transparency. Users can composite and reuse atomic primitive concepts and relationship to interpret complex geographical concept without the need to retouch or even know the technical details. The major issue that we are focusing on is the implicit geometry problem. That is, th...
Chapter
OpenStreetMap (OSM) is mostly a good map for viewers to look at but it lacks of sufficient quality in certain applications like navigation. Quality issues are usually related to how roads are ‘drawn’ (modeled) by OSM contributors. First of all, this paper identifies several issues in tagging and modeling OSM road network by case studies, and also g...
Article
In map generalization, the displacement operation attempts to resolve proximity conflicts to guarantee map legibility. Owing to the limited representation space, conflicts may occur between both the same and different features under different contexts. A successful displacement should settle multiple conflicts, suppress the generation of secondary...
Article
Full-text available
In the representation of topographic data, the distribution of hydrographic networks should be constrained by the contour model’s landform features. During the integration of topographic databases, however, spatial conflicts may destroy these constraints, generating inconsistencies. This study presents a method to detect and correct inconsistencies...
Chapter
This paper presents a first-order representation to formalize cartographic constraints for automated quality evaluation of multi-scale data. Formalizing constraints for cartographic applications is a challenging task. It requires precise definition of entities, spatial and semantic relationships for individuals, groups and classes of objects, and t...
Article
Understanding inundation in wetlands may benefit from a joint variation analysis in changes of size, shape, position and extent of water bodies. In this study, we modeled wetland inundation as a random spread process and used random sets to characterize stochastic properties of water body extents. Periodicity, trend and random components were captu...
Article
Full-text available
To meet the requirements of multi-scale mapping in maritime applications, marine charts need to be produced at various levels of detail (LOD) using map generalization. As a prominent geographic feature, the coastline has to be generalized considering the geomorphologic characteristics rather than from a pure geometric perspective. Morphologic and d...
Chapter
This chapter presents the context, the issues and the research associated with the evaluation of map generalisation output as well as of map readability. Two main approaches of evaluation are described, i.e. visual and quantitative evaluation. Visual evaluation is subjective, qualitative, and time-consuming, while it is argued that quantitative eva...
Article
Full-text available
Evaluation is a key step to examine the quality of generalized maps with respect to map requirements. Map generalization facilitates the recognition of pattern generating processes by preserving and highlighting the patterns at smaller scales. This article focuses specifically on the evaluation of building patterns in topographic maps that are gene...
Article
o setle spatial conflicts by displacement operations,the map generalization algorithms has to take into account the conflicts resulted from diferent contexts and to retain the spatial paterns and relations among spatial objects.A multi-source force field based method deals with the displacement of polygon cluster considering the aspects above.The d...
Thesis
Full-text available
To meet the increasing demand for geospatial information at multiple scales, and to shorten update cycles for up-to-date geo-data, national mapping agencies (NMAs) and other data providers have introduced, or are considering the use of, (semi-)automated generalization systems in their production lines. Map generalization inevitably changes certain...
Chapter
Automated evaluation of generalization output relies largely on well defined map specifications or cartographic constraints to formalize quality criteria or user requirements, and on enriched information to fully automate the process. Previous studies suggest that the formalization and evaluation of legibility constraints (i.e. those improving the...
Conference Paper
Full-text available
Matching of building polygons with different levels of detail is crucial in the maintenance and quality assessment of multi-representation databases. Two general problems need to be addressed in the matching process: (1) Which criteria are suitable? (2) How to effectively combine different criteria to make decisions? This paper mainly focuses on th...
Chapter
Building patterns are important settlement structures in applications like automated generalization and spatial data mining. Previous investigations have focused on a few types of building patterns (e.g. collinear building alignments); while many other types are less discussed. In order to get better known of the building patterns available in geog...
Article
Full-text available
Investigations in data quality and uncertainty modeling are becoming key topics in geoinformation science. This paper models a collection of outcomes from a standard segmentation algorithm as a random set. It quantifies extensional uncertainties of extracted objects using statistical characteristics of random sets. The approach is applied to a synt...
Conference Paper
Full-text available
The paper presents a computational model of spatialautocorrelation based on a Voronoi-like auxiliary structure. It shows that the Voronoi-like partition of map objects can be used to discern spatial patterns (e.g. clustered or dispersed) of geographic phenomena. In this paper, we transform the problem of characterizing the patterns for different ge...
Article
Full-text available
Spatial distribution density is an important constraint in map generalization, which acts on a group of objects at meso level or a whole thematic class at macro level. However, the spatial distribution density is difficult to be formalized and evaluated, due to the lack of both common understanding and appropriate measurements. The paper proposes a...
Article
Full-text available
The map requirements (constraints) can be interpreted by computer programs using their basic embedded functionalities. There are a huge number of constraints available to define the objective of various generalization outputs. Some of the constraints contain high-level knowledge which is not easy to interpret. This needs a huge amount of efforts to...
Article
True color image city map is a sort of new-style map which combines the high resolution image and map symbols and shows both advantages in visualization. At the same time, the map unification and harmonization should be taken into account during the design process, since some visual conflicts appear when map symbols overlaid on the true color image...
Chapter
Full-text available
This paper presents a model for building cluster distribution analysis based on the Delaunay triangulation skeleton. The skeleton connection within the gap area among the building polygons obtains a special geometric construction similar to Voronoi diagram that spatially partitions the gap area equally. Each building polygon is surrounded by a part...

Network

Cited By

Projects

Projects (5)
Project
Utilizing geospatial big data , social and remote sensing data combined with the power of computing and artificial intelligence to tackle environmental and sustainable development issues.
Project
The ultimate goal of this research is to identify the critical factors behind the declining of vegetative cover in the Ukhiya-Teknaf of Bangladesh, as well as quantify Rohingya refugee camps with highly vegetative vulnerable using RS, GIS, and machine learning techniques.