Classification Of Spatial Objects Research Articles

Classification of Spatial Objects with the Use of Graph Neural Networks

Classification is one of the most-common machine learning tasks. In the field of GIS, deep-neural-network-based classification algorithms are mainly used in the field of remote sensing, for example for image classification. In the case of spatial data in the form of polygons or lines, the representation of the data in the form of a graph enables the use of graph neural networks (GNNs) to classify spatial objects, taking into account their topology. In this article, a method for multi-class classification of spatial objects using GNNs is proposed. The method was compared to two others that are based solely on text classification or text classification and an adjacency matrix. The use case for the developed method was the classification of planning zones in local spatial development plans. The experiments indicated that information about the topology of objects has a significant impact on improving the classification results using GNNs. It is also important to take into account different input parameters, such as the document length, the form of the training data representation, or the network architecture used, in order to optimize the model.

Ensemble Methods for Spatial Data Stream Classification

In this paper, we study the problem of classification of data in a spatial data stream. The classification of spatial objects in a static data set has been well studied. However, classifying objects in a spatial data stream has received very little attention. We propose an iterative ensemble approach for deep learning of a spatial data stream. Using several deep neural networks, our strategy iteratively performs training and testing of the classifier, with the goal of reaching a desired accuracy, and the same accuracy that would be achieved as a classifier that is trained and tested with the entire dataset. An experimental evaluation and comparison of the ensemble approach shows improvement over a previously proposed iterative deep learning strategy.

Classification of objects in images with distortions based on a two-stage topological analysis

The authors propose a method for automatic classification of spatial objects in images under conditions of a limited data set. The stability of the method to distortions appearing in images due to natural phenomena and partial overlap of urban infrastructure objects is investigated. High classification accuracy, when using existing approaches, requires a large training sample, including data sets with distortions, which significantly increases computational complexity. The paper proposes a method for a two-step topological analysis of images. Topological features are initially extracted by analyzing the image in the brightness range from 0 to 255, and then from 255 to 0. These features complement each other and reflect the topological structure of the object. Under certain deformations and distortions, the object preserves its structure in the form of extracted features. The advantage of the method is a small number of patterns, which reduces the computational complexity of training compared to neural networks. The proposed method is investigated and compared with the modern neural network approach. The study was performed on a DOTA dataset (Dataset for Object deTection in Aerial images) containing images of spatial objects of several classes. In the absence of distortion in the image, the neural network approach showed a classification accuracy of over 98 %, while the proposed method achieved about 82 %. Further distortions such as 90 degree rotation, 50 % narrowing and 50 % edge truncation and their combinations were applied in the experiment. The proposed method showed its robustness and outperformed the neural network approach. In the most difficult combination of the test, the decrease in classification accuracy of the neural network was 46 %, while the described method showed 12 %. The proposed method can be applied in cases with a high probability of distortion in the images. Such distortions arise in the field of geoinformatics when analyzing objects of various scales, under different weather conditions, partial overlap of one object with another, in the presence of shadows, etc. It is possible to use the proposed method in vision systems of industrial enterprises for automatic classification of the parts that belong to superimposed objects.

WYKORZYSTANIE WSPÓŁCZYNNIKA MORANA DO KLASYFIKACJI OBIEKTÓW PRZESTRZENNYCH NA PRZYKŁADZIE CEN GRUNTÓW ROLNICZYCH

W artykule przedstawiono możliwości wykorzystania globalnej statystyki Morana do klasyfikacji obiektów przestrzennych. Przestrzenna autokorelacja jest wykorzystywana przede wszystkim do określenia podobieństwa obiektów, które znajdują się w różnych odległościach od siebie. Sąsiedztwo badanych obiektów, określamy przez jego rząd czyli obiekty, które sąsiadują bezpośrednio ze sobą traktujemy jako sąsiadów pierwszego rzędu. Natomiast dalsi sąsiedzi określani są jako sąsiedztwo drugiego, trzeciego i dalszych rzędów. Współczynniki autokorelacji globalne i lokalne pozwalają określić wielkość zależności przestrzennej, ale służą przede wszystkim do wnioskowania o strukturze przestrzennej. Wykorzystując globalne miary statystyki przestrzennej możemy określić istnienie reżimów przestrzennych, a w konsekwencji klasyfikować badane obiekty w klastry.

Spatial Component Models with Artificial Neural Networks for Spatially Constrained Regionalization

Abstract. The authors have investigated into different geostatistical point data modeling approaches for regionalization purposes that employ the Artificial Neural Network (ANN) techniques. Regionalization is a spatially constrained adjacency classification problem. In this study, regionalization is viewed as classification of spatial objects (non-uniformly distributed points) into a smaller number of geographic regions defined by their spatial and attributive characteristics or regionalized variables. For regionalization, we take into consideration the non-stationarity and autocorrelation properties of the spatial data.

Discovery of topological constraints on spatial object classes using a refined topological model

In a typical data collection process, a surveyed spatial object is annotated upon creation, and is classified based on its attributes. This annotation can also be guided by textual definitions of objects. However, interpretations of such definitions may differ among people, and thus result in subjective and inconsistent classification of objects. This problem becomes even more pronounced if the cultural and linguistic differences are considered. As a solution, this paper investigates the role of topology as the defining characteristic of a class of spatial objects. We propose a data mining approach based on frequent itemset mining to learn patterns in topological relations between objects of a given class and other spatial objects. In order to capture topological relations between more than two (linear) objects, this paper further proposes an extension of the 9-intersection model for topological relations of line geometries. The discovered topological relations form topological constraints of an object class that can be used for spatial object classification. A case study has been carried out on bridges in the OSM dataset for the state of Victoria, Australia. The results show that the proposed approach can successfully learn topological constraints for the class bridge, and that the proposed extended topological model for line geometries outperforms the 9-intersection model in this task.

АНАЛИЗ МЕТОДОВ ПОСТКЛАССИФИКАЦИОННОЙ ОБРАБОТКИ МНОГОКАНАЛЬНЫХ ИЗОБРАЖЕНИЙ

The subject matter of the article is the methods of morphological spatial filtering of images in pseudo-colors obtained as a result of statistical segmentation of multichannel satellite images. The aim is to study the effectiveness of various methods of post-classification image processing in order to increase the probability of correct recognition for observed objects. The tasks to be solved are: to select a mathematical model describing the training sets of objects’ classes; to implement the procedure of statistical controlled classification by the maximum likelihood method; to evaluate the results of objects’ recognition on the test image by the criterion of the empirical probability of correct recognition; to formalize the procedures of local object-oriented filtering of a segmented image; to investigate the effectiveness of rank filtering as well as weighted median filtering procedures taking into account the results of the classification by k-nearest neighbors in the filter window. The methods used are methods of empirical distributions’ approximation, statistical recognition methods, methods of probability theory and mathematical statistics, methods of local spatial filtering. The following results were obtained. A method for synthesizing a universal mathematical model has been proposed for describing non-Gaussian signal characteristics of objects on multichannel images based on a multi-dimensional variant of Johnson SB distribution; this model was used for statistical pixel-by-pixel classification of the original satellite image. Algorithms for local post-classification processing in the neighborhood of the selected segments boundaries have been implemented. The analysis of the developed algorithms’ effectiveness based on estimates of classes’ correct recognition probability is performed. Conclusions. The scientific novelty of the results obtained is as follows: combined approaches to the pattern recognition procedures have been further developed – it has been shown that the use of methods of local object-oriented filtering of segmented images allows to reduce the number of point errors for element-wise classification of spatial objects.

Spatial object classification by radar measurements

UHF ground based radar are often dedicated to defense and space surveillance. The major radar objectives are the detection of spatial objects and then their classification. In this article, we show how orbit determination can be performed with some radar observations (we have considered in this article right ascension, declination, range and Doppler). Since classical methods are not efficient due to the acquisitions' high level of noise, we propose a more robust algorithm based on f and g series to estimate position and velocity at time t. We finally present a basic procedure of classification between different spatial objects (satellites, ballistic missiles …) on real time applications. The influence of radar noise and of the samples number in the accuracy of this classification procedure is also presented.

Radar measurements analysis for spatial object classification

This paper presents a method for estimating orbital parameters of spatial objects detected with a ground based radar dedicated to space surveillance. The radar objective are twofold: detection; classification of the detected objects. We firstly describe how the orbit determination is performed using radar acquisitions (right ascension, declination, range and Doppler). We then present the procedure of differentiation between different spatial objects (satellites, ballistic weapons...) on real time applications. An analysis of the influence of noise and of the samples number in the accuracy of this procedure is also presented.

SPATIAL OBJECTS AND SPATIAL RELATIONSHIPS

ABSTRACT Spatial object and spatial relationship are two basic concepts of GIS. Spatial object is the digital representation of geographical entity or phenomenon, which forms the basis for data management and analysis; spatial relationship is the connexion between spatial objects when geometric properties are considered. The commonly used classification of spatial objects as points, lines and areas is mathematically strict, and suitable for data management, but a bit too generalized for representing real entities and extracting spatial relationships. A good classification model should not only be good for representing real entities, but also good for revealing spatial relationships, therefore good for formalizing spatial analyses.