Making decisions about which objects to keep or omit is challenging in map design. This process, called selection, constitutes the first operation in cartographic generalization. In this research, a ...method of automatic road selection for creating small-scale maps using machine learning and data enrichment is proposed. First, the problem of contextual information scarcity concerning roads in the source database is addressed. Additional information concerning the relations between roads and other objects was added (such as centrality and proximity measures). Second, machine learning is used to design automatic selection models based on enriched information. Third, three different road selection approaches are implemented. The baseline approach is following the official map design guidelines. The second approach is based on machine learning using the enriched road database. The third approach is based on an existing structural model. The results of all approaches are compared to existing atlas maps designed by experienced cartographers. The results of the Machine Learning Approaches were most similar to the atlas maps (between 81% and 90% accuracy). The least efficient approaches were the Structural Approach with 32% and the Guidelines Approach with 44% accuracy. We conclude that enriching road data with new contextual information concerning roads and using machine learning is beneficial as the achieved results outperform both Guidelines and Structural Approaches.
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK
Digital generalization of spatial data has been the goal of the research in many research centers around the world. This article presents the evolution of cartographic generalization, drawing the ...reader’s attention to the change of its nature from analog to digital. Despite the passage of time and developing technologies, scientists have unfortunately yet to develop a uniform automatic generalization algorithm. One of the factors that hinder this process is the high complexity and complication of the whole process. The article is an attempt to answer this problem and addresses the issue of digital cartographic generalization by creating a proposal of thresholds and stages of cartographic generalization depending on the ratios of the numbers of points of generalized objects. The publication attempts to examine the possibility of applying an objective criterion of drawing recognition by examining digital generalization algorithms and setting its thresholds. The practical aim of the publication is to present generalization thresholds on the example of Chrobak’s algorithm. The proposal to make the selection of generalization thresholds dependent on the percentage share of points is a solution that is as simple to use as it is to implement. The method of defining intervals based on the three-sigma rule is a solution that guarantees that the obtained results will be characteristic of the probability density function of the normal distribution, which will define individual intervals most objectively.
A visualização de mapas por meio de Realidade Aumentada pode facilitar análises topográficas, pois tais ferramentas permitem representar a topografia de maneira interativa e dinâmica em ambientes 3D. ...Porém, muitas vezes isto é feito de forma simples e sem levar em conta princípios de comunicação cartográfica. Este presente trabalho tem como objetivo a proposta de uma metodologia baseada em regras de Generalização Cartográfica para otimizar a visualização de cartas topográficas em ambientes de Realidade Aumentada indoor. Este aprimoramento é almejado visando a manutenção das características originais do relevo. Nos experimentos, o modelo digital do terreno (MDT) foi utilizado para extração de curvas de nível em escala de 1:10.000 e depois em escala reduzida de 1:15.000. Foram analisadas as condições geométricas de Coalescência, Congestionamento, Conflito e Imperceptibilidade. Esses problemas foram solucionados por meio de operadores de Realce, Seleção e Simplificação com os algoritmos de Douglas-Peucker, Passa-baixas e Savitzky- Golay. Os operadores de Realce e Seleção foram aplicados anteriormente à Simplificação, como um pré-processamento.Os algoritmos de Simplificação foram comparados quanto a sua capacidade de reduzir os dados e a preservação da informação geométrica original do relevo. Os resultados apontam que o objetivo pode ser atingido e que os filtros de Douglas - Peucker e de Savitzky-Golay apresentaram melhores resultados.
A generalização cartográfica visa adaptar as feições cartográficas e as suas relações geográficas de acordo com a escala de representação do produto cartográfico. Com o advento dos computadores, os ...operadores permitem observar essa adaptação geométrica e semântica desse conjunto de feições segundo a função e a finalidade estabelecidas para esse produto. Com o propósito de analisar visualmente a generalização cartográfica de feições lineares extraídas do Modelo Digital de Elevação (MDE), a partir da aplicação dos operadores simplificação e suavização, tornou-se o foco deste trabalho. No caso, foram usados os algoritmos POINT-REMOVE, para a simplificação e o PAEK, para a suavização das redes de drenagem extraídas a partir do MDE ASTER e do MDE SRTM, respectivamente, com 30 e 90 metros de resolução espacial. Esses operadores estão disponíveis no software ARCGis 10.1 e a área de estudo foi a bacia hidrográfica do Rio Jordão (MG). Houve controle da qualidade posicional da carta topográfica gerada em meio digital e dos MDEs e a comparação visual ocorreu com a sobreposição desses produtos. Para essa análise visual se valeu dos princípios da fotointerpretação, do modelo de comunicação cartográfica e os resultados apontam maior similitude entre os trechos lineares com a carta topográfica dessa bacia, independentemente do MDE. Por outro lado, a resolução espacial e a topografia interferem na extração dessa rede de drenagem
Machine learning methods are increasingly used in the automatic generalization of river networks, but previous research lacks a comparative analysis of different methods using the same data set. This ...innovative study considers eight river network indicators, such as river length, river grade, river spacing, seasonality, connectivity, catchment area, tributaries at the next grade, and total number of tributaries, which can precisely describe the characteristics of the river network. The experiments were carried out and automated selection of river network was established based on back-propagation neural network (BPNN), support vector machine (SVM) and decision tree (DT) methods. We established that BPNN and SVM have high selection accuracy, but the parameters are complex. SVM is more suitable for small samples. In addition, DT has unique advantages due to its visualized tree structure and the characteristic of derivable rules. We hope that this study will provide a reference for the selection of river generalization methods in the future.
Full text
Available for:
BFBNIB, DOBA, GIS, IJS, IZUM, KILJ, KISLJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Automated generalization is highly desired for effective map production. This research focuses on the initial stage of generalization, namely object selection. The study aims to conduct river network ...automatic selection based on map specifications contained in the Minister of Internal Affairs and Administration regulation. The research covers river network selection from the General Geographic Objects Database from 1:250,000 to 1:500,000 detail level. Within the research scope, three selection variants were designed. The first was a basic variant that only included the implementation of the specifications contained in the regulation. The other two were experimental variants: an extended variant and an extended-modified variant with the parameters and data enrichment proposed by the authors. The extended variant has been supplemented with the Id_MPHP index usage, derived from the Map of Hydrographic Division of Poland (MPHP), which defines the hierarchy of watercourses in the river network. The extended-modified variant was implemented according to the guidelines of the regulation, with the use of the Id_MPHP index and additionally with the help of the parameter denoting “priority” watercourses, which was assigned by the authors. The results of the work constitute the generalization models designed in ArcMap 10.8. with the use of Model Builder functionality as well as the maps presenting the selection variants output visualizations. The results were compared visually as well as verified with the reference atlas map generalized by an experienced cartographer. As a result, the map specifications concerning the selection process presented in the regulation proved to be insufficient to generalize river networks properly. The variants proposed in this research made it possible to improve the selection results and enabled the automation of the river selection process. Additional specifications and parameters proposed in this work may constitute an essential supplement to the guidelines contained in the regulation.
A suitable spatial scale needs to be selected in geographical and landscape ecological research, and this requires great consideration as different scales have profound effect on derived landscape ...spatial patterns. Numerous studies have investigated the effects of different scales on landscape metrics using simulated patterns, but few have been conducted to compare different data sources with variable scale for regional- and landscape-scale assessments. Possibly this has occurred because researchers have been prone to use the best available source, a well-known standard, and easiest to use. This study was conducted to assess the impact of input data resolution on values of landscape pattern metrics in four landscapes at scales 1:10 000, 1:50 000 and 1:100 000. The aim was to determine the applicability of three data sources for thematic models in landscape pattern analyses in the Eastern Baltic region. We found that the utility of CORINE Land Cover data for comprehensive structural assessment in mosaic-type landscapes was very limited, as the level of cartographic generalization excluded many small and linear landscape structure elements with potentially high importance for landscape functioning, such as habitat continuity. We also found that actual area harvested using clearcuts was considerably higher than shown in CORINE data, due to clearcuts size being much smaller than the minimum mapping unit. In the light of this, we suggest using data with spatial resolution corresponding to a cartographic scale of at least 1:50 000, in cases when spatial patches have size up to 25 ha.
•Proximity index is especially sensitive to changes in scale in pattern analyses.•Mosaic-type landscape patterns have to be interpreted separately from contiguous patterns.•Although easily available, Corine Land Cover datasets are inappropriate for detailed landscape analyses.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Abstract
A topological relationship is a key factor in the spatial data processing. Aiming at the problem of topological similarity measurement when the dimension of spatial objects changes in the ...process of map generalization, this paper proposes a topological similarity measurement method based on the global topological concept neighborhood graph. Firstly, all the topological relationships that can be described by the nine intersection model are abstracted, generalized, and classified, and the classified point/point, point/line, point/polygon, line/line, line/polygon, and polygon/polygon local topological concept neighborhood graphs are established. Then, according to the map generalization rules, the mapping between different types of topological concept neighborhood graphs is established, and the global topological concept neighborhood graph is obtained, Finally, the similarity of the topological relationship between different morphological objects is measured. The experimental results show that the proposed method can better meet the topological similarity measurement when the shape of spatial objects changes.
Identifying the spatial configurations of buildings and grouping them reasonably is an important task in cartography. This study developed a grouping approach using graph deep learning by integrating ...multiple cognitive features and manual cartographic experiences. Taking building center points as nodes, adjacent buildings were organized as a graph in which cognitive variables including size, orientation, and shape were defined for each node. Then, a learning model combining the graph convolution and neural network was designed to analyse the adjacent buildings modelled by the graph. The center points of groups were used as labels to train the positions of graph nodes and finally, a k-means algorithm was employed to obtain the grouping results based on the predicted node positions. Experiments confirmed that our approach can extract the inherent features describing the grouping relationship between buildings and performed better than two existing approaches referring to the ARI index (from 0.647 to 0.749).
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK