Spatial Topological Relationship for Remote Sensing Image Analysis

To solve the disadvantages of high difficulty and complexity in studying the spatial topological relation method on different resolution remote sensing images, this paper proposes a spatial topological relationship model based on GeoSOT, which is one of the global subdivision grids. To express spatial objects on different resolution remote sensing images, this paper introduces the spatial objects subdivision location identification. Then, the model calculates spatial topological relation by comparing location identifications in combined table. At last, test shows that it is feasible to analyze the spatial objects topological relations based on GeoSOT and it has high efficiency operation significantly, especially for complicated spatial objects.

The development of formal models of spatial relations is a topic of great importance in spatial reasoning, geographic information systems (GIS) and computer vision, and has gained much attention from researchers across these research areas during the past two decades. In recent years significant achievements have been made on the development of models of spatial relations between spatial objects with precisely defined boundaries. However, these models cannot be directly applied to spatial objects with indeterminate boundaries which are found in many applications in geographic analysis and image understanding. This article develops a method for approximately analyzing binary topological relations between geographic regions with indeterminate boundaries based upon previous work on topological spatial relations and fuzzy sets. In addition, examples are given to demonstrate the method and related concepts. It is shown that the eight binary topological relations between regions in a two-dimensional space can be easily determined by the method.

Representing topological information for the Semantic Web often involves qualitative defined natural language terms such as “In”. This can be the case when exact coordinates of spatial regions are not available or they are unreliable. Topological spatial relations are the most important aspect of spatial representation and reasoning. In addition to topology, often the exact size of regions is not known as well, but the relations between sizes (e.g., larger, equal) are known. In this work we propose and evaluate an integrated representation of topological relations (RCC-5 and RCC-8) and qualitative size relations using OWL object properties and axioms, combined with reasoning rules expressed using SWRL, embedded into the ontology. Different representations are implemented and evaluated.KeywordsSpatial Representation and ReasoningSemantic WebRules

Cloud computing technology is changing the mode of the spatial information industry which is applied and provides new ideas for it. Since Hadoop platform provides easy expansion, high performance, high fault tolerance and other advantages, we propose a novel vector spatial data storage schema based on it to solve the problems on how to use cloud computing technology to directly manage spatial data and present data topological relations. Firstly, vector spatial data storage schema is designed based on column-oriented storage structures and key/value mapping to express spatial topological relations. Secondly, we design middleware and merge with vector spatial data storage schema in order to directly store spatial data and present geospatial data access refinement schemes based on GeoTools toolkit. Thirdly, we verify the middleware and the data storage schema through Hadoop cluster experiments. Comprehensive experiments demonstrate that our proposal is efficient and applicable to directly storing large-scale vector spatial data and timely express spatial topological relations.

5 - Geographic Relations

Landform recognition is one of the most significant aspects of geomorphology research, which is the essential tool for landform classification and understanding geomorphological processes. Watershed object-based landform recognition is a new spot in the field of landform recognition. However, in the relevant studies, the quantitative description of the watershed generally focused on the overall terrain features of the watershed, which ignored the spatial structure and topological relationship, and internal mechanism of the watershed. For the first time, we proposed an effective landform recognition method from the perspective of the watershed spatial structure, which is separated from the previous studies that invariably used terrain indices or texture derivatives. The slope spectrum method was used herein to solve the uncertainty issue of the determination on the watershed area. Complex network and P–N terrain, which are two effective methodologies to describe the spatial structure and topological relationship of the watershed, were adopted to simulate the spatial structure of the watershed. Then, 13 quantitative indices were, respectively, derived from two kinds of watershed spatial structures. With an advanced machine learning algorithm (LightGBM), experiment results showed that the proposed method showed good comprehensive performances. The overall accuracy achieved 91.67% and the Kappa coefficient achieved 0.90. By comparing with the landform recognition using terrain indices or texture derivatives, it showed better performance and robustness. It was noted that, in terms of loess ridge and loess hill, the proposed method can achieve higher accuracy, which may indicate that the proposed method is more effective than the previous methods in alleviating the confusion of the landforms whose morphologies are complex and similar. In addition, the LightGBM is more suitable for the proposed method, since the comprehensive manifestation of their combination is better than other machine learning methods by contrast. Overall, the proposed method is out of the previous landform recognition method and provided new insights for the field of landform recognition; experiments show the new method is an effective and valuable landform recognition method with great potential as well as being more suitable for watershed object-based landform recognition.

The research of parallel mechanism (PM) configuration involves many problems. From topology to configuration, dimensional constraint, etc., how to establish the relationship between topology and configuration with effective methods is a long-term challenge for the configuration design. In this paper, the chemical molecular spatial structure (CMSS) is linked with the configuration of symmetrical parallel mechanism (SPM). Starting from the methane molecule (CH4), a spatial structural topological relation is obtained. Based on graph theory and the spatial structural topological relation, a new expression method with topological graph and its kinematic pair adjacency matrix for spatial SPM is proposed. Then, the expression and analysis for the characteristics of spatial SPM are obtained. Finally, by taking the 3-RPS PM and the 3-RRC PM as examples, the effectiveness and corresponding consistency of the proposed expression method are successfully verified. The proposed new expression method paves the way for the subsequent digital and automated design and analysis of the SPM configuration.

Identifying the geographic distribution and erosion risks of various soil erosion regions are critical inputs to the implementation of extensive and effective land protection planning. To obtain more accurate and sufficient erosion information on a large scope, this paper introduced the complex network theory to quantitatively simulate the topographic spatial structure and topological relationship of the erosion area. The watershed was selected as the basic study unit and the directed weighted complex network (DWCN) of each watershed was constructed from DEM data. The directed weighted complex network factor (DWCNF) of each watershed was calculated by the DWCN. After combining DWCNFs with existing SEEF, the soil erosion types and risks of sample areas in the Chinese Loess Plateau were identified by the random forest model. The results show that in both typical and atypical sample areas, the identification performance of soil erosion by combining DWCNFs with existing SEEFs was performed better than that by employing only the DWCNFs or SEEFs dataset. It is suggested that the quantitative description of the spatial structure and topological relationship of the watershed from the perspective of a complex network contributes to obtaining more accurate soil erosion information. The DWCNF of structural entropy, betweenness centrality, and degree centrality were of high importance, which can reliably and effectively identify the types and risks of soil erosion, thus providing a broader factor reference for relevant research. The method proposed in this paper of vectoring terrain into complex network structures is also a novel sight for geological research under complex terrain conditions.

Spatial modeling is one of the most important parts in the area of spatial relations, and it is necessary to develop a new model with high practicality. Firstly this paper analyzes the characteristics and defects of present models; secondly introduces in detail the construction method of quadtree histogram; thirdly cloud model are used to judge spatial directional relation. The experimental results show that the model is feasible. Computer vision is concerned with automatic extraction of useful information from images. The description for human space perception is an important task of the computer vision research. The description of spatial relation is a basic ability of human cognition, it is an important basic task for computer audio-visual information processing to build automatically the description of spatial relation between objects in the image. Spatial relation is mainly constituted of directional relation, topological relation and distance relation. The fundamental theories of topology relation and distance relation are comparatively perfect, but the fundamental theories of directional relation have not any unified standard. There are three main approaches for assessing the basic directional relation. The first one is based on cone model (1) which assimilates an object to the centroid, but it doesn't take into account shape, size and distance information. The second one is based on projection model such as minimum bounding rectangles (2), and directional relation matrix (3), etc., but these models assimilate an object to the minimum bounding rectangle, so shape, size and distance information also can't be taken into account. The third one is based on angle-histogram model (4). Given an object of target A and a reference object B, the angle-histogram is computed from the angles between any two points in both objects and normalized by the maximum frequency. This histogram represents the directional relations of the object A with respect to the reference object B. This model has taken into account shape, size and distance information. But this model has high computational complexity, so it is not practical. Numerous studies are based on this notion of angle-histogram, e.g., (5-8). In (5-7), R-histogram, R*-histogram and F-histogram are proposed, and they can reduce the computational complexity. In (8), a quadtree histogram model of spatial directional relation is proposed, and it can get high accuracy and small computational complexity together.

As we all know, remote sensing (RS) images contain multi-scale and numerous RS objects, along with massive and complex spatial topological relationships, such as the adjacency, proximity relations of same-scale objects, and inclusion relations of cross-scale objects. However, the existing semantic segmentation methods have never explored the cross-scale relations, which are especially important when comes to the situation that the RS objects cannot be accurately identified, they could be supplemented by the surrounding contents. To address the above concern, we propose a scale-relation joint decoupling network (SRJDN) for the semantic segmentation of RS images by simultaneously considering decoupling scales and decoupling relations to excavate more complete relationships of multi-scale RS objects. The SRJDN is performed by following three steps, namely scale decoupling (SD), relation decoupling (RD), and fine-granularity guided fusion (FGF). The SD module uses dilated convolution with different rates to decouple RS objects into different scale feature groups, from small to large scales. Afterward, the RD considers all the spatial topological relationships and decouples these relationships according to the scale, which is divided into two parts, including same-scale relation extraction (SSRE) and cross-scale relation extraction (CSRE). The SSRE establishes the graph structures at each scale independently to mine the relationships of same-scale RS objects and the CSRE constructs the graph in a unified pattern between cross-scales to explore cross-scale target relationships. Third, the FGF module regards small-scale features as fine-granularity representation and applies its attention map to guide the learning of other scale features, which could mine more reliable and comprehensive saliency information and improve the feature consistency. Numerical experiments conducted on two large-scale fine-resolution RS image datasets empirically demonstrate the robustness of the proposed joint decoupling strategy and the effectiveness of the fine-granularity guided fusion in RS image semantic segmentation tasks.

Spatial reasoning, where novel spatial relationships are inferred based on trained relationships, can be conceptualized as arbitrarily applicable spatial relational responding. Here, we conducted two experiments to develop and validate, for the first time, a laboratory procedure to establish arbitrarily applicable spatial relational responding in adult humans. In Experiment 1, participants were trained on nonarbitrary spatial relational tasks designed to establish contextual cues for left of, right of, above, and below. Contextual cues were then used to train a series of arbitrary spatial relations involving four abstract shapes. Following training in a subset of arbitrary relations (A is left of B, B is above C, C is right of D), subsequent testing examined the emergence of untrained spatial relations (B is right of A, C is below B, D is left of C, D is below A and A is above D). When absent in initial tests, spatial relational responding was facilitated by a remedial training procedure incorporating nonarbitrary relational guidance. Participants showed patterns of spatial relational responding consistent with test relations. In Experiment 2, a variant reversal design yielded predictable, reversed spatial relational responses. Overall, the present procedures represent the first empirical demonstration of arbitrarily applicable spatial relational responding and thus, arguably, the first functional analytic model of spatial reasoning.

Models for data representation and presentation in WebGIS systems are based on concepts of borderlines, nets, territory, space and place, and the representation of abstract concepts are transmitted through graphic form, by means of images, photographs or cartographic representations of regions. The topological, projective, and Euclidean spatial relations connected with the process of world construction and conception promote experiences lived in space and that involve sensations, perception, and conception, which together with human emotional and rational characteristics, allow the elaboration of mental models. This paper presents a model and its prototype for interpretation, representation and presentation of geographical information based on sounds so as to allow information interpretation and analysis in WebGIS systems. In order to check the efficiency and effectiveness of the proposed methodology, a computer prototype applied to Google Maps was developed, in which the proposed method was applied and tested with a group of blind people.

Spatial relation between spatial objects is a very important topic for spatial reasoning, query and analysis in global GIS. However, the most popular models in current use, which are based on the 2D Euclidean space (such as raster), exist some fundamental deficiency in theory for spatial relation reasoning in the spherical digital space (SDS). In this paper, a reasoning method of spatial relations in the SDS based on manifold is approached, in which: (1) the topological definitions, properties, and descriptions of spatial objects in SDS are presented; (2) appropriate operators from set operators (i.e. intersection, difference, difference by, symmetric difference, etc.) are utilized to distinguish the spatial relations between neighboring spatial objects; and (3) the value of the Euler number of symmetric difference is used for the detailed computational results of set operations; In this method, the 8 types basic topological relations between spatial objects in SDS can be distinguished accurately and easily from simple to detailed level for different requirements.

The integration of the raster data cube alongside another form of geospatial data (e.g., vector data) raises considerable challenges when it comes to managing and representing it using knowledge graphs. Such integration can play an invaluable role in handling the heterogeneity of geospatial data and linking the raster data cube to semantic technology standards. Many recent approaches have been attempted to address this issue, but they often lack robust formal elaboration or solely concentrate on integrating raster data cubes without considering the inclusion of semantic spatial entities along with their spatial relationships. This may constitute a major shortcoming when it comes to performing advanced geospatial queries and semantically enriching geospatial models. In this paper, we propose a framework that can enable such semantic integration and advanced querying of raster data cubes based on the virtual knowledge graph (VKG) paradigm. This framework defines a semantic representation model for raster data cubes that extends the GeoSPARQL ontology. With such a model, we can combine the semantics of raster data cubes with features-based models that involve geometries as well as spatial and topological relationships. This could allow us to formulate spatiotemporal queries using SPARQL in a natural way by using ontological concepts at an appropriate level of abstraction. We propose an implementation of the proposed framework based on a VKG system architecture. In addition, we perform an experimental evaluation to compare our framework with other existing systems in terms of performance and scalability. Finally, we show the potential and the limitations of our implementation and we discuss several possible future works.

A novel spatial tessellation scheme, spatial chromatic tessellation (SCT), is proposed for representing and exploring space–entity relationship. The objective of this article is briefly introducing the basic concepts, structure, and properties of SCT. Our study mainly focuses on the arranged chromatic diagram (ACD), which is the most typical type of SCT. A few examples show that ACD can be used to analyze spatial topology, statistics, computations, database, and Voronoi diagrams. ACD also contains many implications on spatial analysis theory. With respect to each entity in a space, SCT partitions the space into a number of small unit cells and gives each cell a unique chromatic code. The spatial topological relationships among these cells are able to be represented and computed by their codes. Based on the different statistical rules on cellular codes, cells could be merged into larger clusters, such as a variety of Voronoi diagrams. Moreover, because cells are coded with the same data structure, it is easy to store and manage these codes in relational database, and then any spatial analytical operation could be realized simply by structured queries. SCT establishes a basic framework that not only provides a theoretical tool for spatial analysis and computations but also helps us to understand the space–entity relationship insightfully.