Land Use Polygons Research Articles

Fine Object Change Detection Based on Vector Boundary and Deep Learning With High-Resolution Remote Sensing Images

Remote sensing (RS) image change detection analyzes and determines the difference of surface states at different times. Polygons are common vector data to express the surface states in geographic information systems. However, the production and updating of polygons typically depend on manual procedures, which costs significant time and human resources. This article proposes an automatic polygon change detection method based on high-resolution RS images and deep learning image classification. First, bitemporal images are segmented by boundary-preserved masking simple linear iterative clustering based on the boundaries and categories of polygons. Then, the labeled dataset is automatically generated by adaptively cropping image segments according to the center-to-boundary distance. Date-1 data are used to train the model and purified by two different classifiers to improve the model performance. Date-2 data, whose categories are predicted, are the basic units of change detection analysis. Furthermore, an improved bilinear convolutional neural network with a reduced number of parameters and training time is applied to fine-grained classification. Finally, the changed polygons can be retrieved based on category comparison and post-processing. In our experiments, two real datasets with high-resolution RS images and land-use polygons are employed to validate the effectiveness of our proposed method. The results are examined by visual interpretation and show that the precision and recall rates for dataset 1 are 90.5% and 93.1%, respectively, while those for dataset 2 are 87.6% and 90.8%. Through our method, the existing polygons can be used appropriately, and the difficulty of data updating can be reduced.

Aggregating land-use polygons considering line features as separating map elements

ABSTRACT Map generalization is the process of deriving small-scale target maps from a large-scale source map or database while preserving valuable information. In this paper we focus on topographic data, in particular areas of different land-use classes and line features representing the road network. When reducing the map scale, some areas need to be merged to larger composite regions. This process is known as area aggregation. Given a planar partition of areas, one usually aims to build geometrically compact regions of sufficient size while keeping class changes small. Since line features (e.g. roads) are perceived as separating elements in a map, we suggest integrating them into the process of area aggregation. Our aim is that boundaries of regions coincide with line features in such a way that strokes (i.e. chains of line features with small angles of deflection) are not broken into short sections. Complementing the criteria of compact regions and preserving land-use information, we consider this aim as a third criterion. Regarding all three criteria, we formalize an optimization problem and solve it with a heuristic approach using simulated annealing. Our evaluation is based on experiments with different parameter settings. In particular, we compare results of a baseline method that considers two criteria, namely compactness and class changes, with results of our new method that additionally considers our stroke-based criterion. Our results show that this third criterion can be substantially improved while keeping the quality with respect to the original two criteria on a similar level.

Influence of the Selection of Interpolation Method on Revealing Soil Organic Carbon Variability in the Red Soil Region, China

At present, various interpolation methods have been used for obtaining the spatial variability of soil organic carbon (SOC) in some regions. However, systematic research on accuracy comparison and the influence of method selection on revealing SOC variability is still lacking for the hilly red soil region of China. In this study, the spatial distributions of SOC were interpolated via three kriging methods (ordinary kriging (OK), kriging combined with soil type information (KSt), and with land-use information (KLu)) and three polygon-based methods (linking sample points data to the sampling grid (PGr), to soil type polygon (PSt), and to land-use polygon (PLu)) in Yujiang County, Jiangxi Province, China. To illustrate the influence of method selection on revealing SOC variability, the prediction efficiencies of these methods were compared with soil validation samples. The results showed that the KLu and PLu had high prediction accuracy, followed immediately by the KSt and PSt, while the OK and PGr had very low accuracies. Meanwhile, the SOC distribution contours obtained by KLu, PLu, KSt, and PSt could better reflect the real conditions of the study area, as they were consistent with the variation of land-use or soil types. However, the contours from the OK and PGr had poor performance with sketchy borderlines and regular homogeneous grid cells, respectively. Therefore, great differences exist in the prediction efficiency of different methods, and the interpolation method selection has an important impact on revealing SOC variability in the hilly red soil region of China. The results can provide a useful reference for the efficient SOC prediction and simulation in similar soil regions.

Envelope generation and simplification of polylines using Delaunay triangulation

ABSTRACTAs a basic and significant operator in map generalization, polyline simplification needs to work across scales. Perkal’s ε-circle rolling approach, in which a circle with diameter ε is rolled on both sides of the polyline so that the small bend features can be detected and removed, is considered as one of the few scale-driven solutions. However, the envelope computation, which is a key part of this method, has been difficult to implement. Here, we present a computational method that implements Perkal’s proposal. To simulate the effects of a rolling circle, Delaunay triangulation is used to detect bend features and further to construct the envelope structure around a polyline. Then, different connection methods within the enveloping area are provided to output the abstracted result, and a strategy to determine the best connection method is explored. Experiments with real land-use polygon data are implemented, and comparison with other algorithms is discussed. In addition to the scale-specificity inherited from Perkal’s proposal, the results show that the proposed algorithm can preserve the main shape of the polyline and meet the area-maintaining constraint during large-scale change. This algorithm is also free from self-intersection.

Identification and Utilization of Land-use Type Importance for Land-use Data Generalization

A proper characterization of land-use types is critical for constructing generalization constraints to guide and control landuse data generalization. This paper focused on identification and utilization of their importance based upon land-use distributions and application themes. First, this importance was identified using a three-step method that links a diversity index, a multiple attribute decision model and a spatial association analysis. Second, with the importance, a mathematical function was designed to determine minimum area thresholds of land-use polygons as an example of generalization constraints. Third, the importance was used to assist in the selection of generalization operators and evaluation of generalization outcomes. Fourth, a land-use dataset at 1:10 000, describing the land use of a typical rural area in Hubei province of China, was generalized towards a 1:50 000 dataset to verify the effects of the presented method and function. Three additional tests were implemented to analyze the sensitivity of the importance of land-use types on setting the minimum area threshold and generalization operations. The outcome showed that the proposed methods and functions make land-use data generalization more adaptable for in-use datasets and applications.

Detection of discrepancies in existing land-use classification using IKONOS satellite data

Geoinformation systems (GIS) and other spatial databases containing land-use data are usually subjected to intensive change processes that impact the quality of their inherent classification and diminish its relevance. Consequently, with time, these databases accumulate various types of erroneous information (discrepancies) that inconsistent with reality. The aim of the study was to investigate how well the discrepancies in land-use classification could be detected using high-resolution optical IKONOS satellite data based on iterative discriminant analyses (IDA). The approach proposed in the research is intended to update an existing land-use classification with one derived from the IDA classifier. Seven land-use classes were extracted from outdated Israeli National GIS spatial database for the area which was also the extent of recent IKONOS satellite image. In order to detect the discrepancies in the land-use classification, IDA algorithm was applied, utilizing the spectral properties of the land-use polygons, acquired from the image. As result IDA has changed, the classification of discrepant polygons which was found inconsistent with the up-to-date spectral data. The polygons with spectral properties that were found consistent with the original classification have remained assigned to initial land-use classes. The overall fraction of the polygons that were correctly classified by IDA was estimated as 92.6% and the fraction of polygons correctly detected as discrepant was estimated as 84.1%. The main advantage of the proposed detection of discrepancies by the IDA is its analytical simplicity that allows for straightforward employment of original bands and ratio (indices) bands in the classification process. The continuous revision of land-use classification databases by IDA may assist the overcoming of interpreter’s errors and the misclassifications caused by changes in land-use.

Detection of discrepancies in land-use classification using multitemporal Ikonos satellite data

Abstract. Geoinformation systems (GIS) and other spatial databases containing land-use data are usually subjected to intensive change processes that impact the quality of their inherent classification and diminish its relevance. Consequently, with time, databases accumulate various types of erroneous information. The combination of the satellite data with the thematic land-use data from a core national GIS, provides an excellent case for GIS-driven analysis of land-use changes. The aim of this research was to assess the land-use changes using time-series of optical Ikonos satellite data. An area of ∼35 km2 in the north of Israel served as the study case of the research. Seven land-use classes were detected in the relevant National GIS spatial database layers updated in the year 2000 and further in the year 2009. These seven type-classes were: water bodies, residential areas, agricultural fields, badlands, natural forests, build-up areas, and plantations. The Iterative discriminant analysis (IDA) algorithm was applied on both GIS datasets using corresponding Ikonos images acquired in 2002 and 2010, respectfully. The IDA process resulted with a re-classification of the initial land-use polygons. It was assessed by validating the classification of all the land-use polygons. Comparing with Ikonos image from the year 2002, the fraction of the polygons that were correctly detected as consistent with the corresponding GIS dataset (77.9%) was relatively close to the fraction of polygons correctly detected as discrepant (75.5%). Classification of Ikonos image from the year 2010 showed that 81.9% of the land-use polygons were correctly detected as consistent whereas the fraction of polygons that were correctly detected as discrepant was about (78.3%). The main advantage of the proposed GIS-driven methodology for detection of changes in land-use classification is its analytical simplicity that allows for straightforward employment of spectral and spatial data in the classification process.

Reducing Edge Effects in the Classification of High Resolution Imagery

Edge effects have been a problem in image classification especially when scale-based textural methods were included in the classification process. This paper proposes a new approach to reducing edge effects. The essence of the new approach is that all pixels in a moving window make use of the textural information instead of only the center pixel as in the traditional moving window method. The performance of the new approach was tested in three classification scenarios. The results show that the new approach generally produced higher accuracy with larger window size and was much less affected by the edge issues than the traditional moving window method. The new approach yields satisfactory results as long as the window size is smaller than the land-use polygons and the class boundaries are not too complex.

Determining land-use information from land cover through an object-oriented classification of IKONOS imagery

The greater availability of remotely sensed high-resolution imagery and advances in object-oriented analysis have created more opportunities for automated urban land-use classifications. To date, few studies have attempted to classify land use from satellite imagery using object-oriented approaches, and those that have tend to rely on manual digitizing or ancillary data to delineate land-use polygon boundaries. This paper explores an object-oriented land-use classification using land-cover information derived from an IKONOS image to automatically delineate and classify the land-use polygons. The study area is in Mississauga (Ontario, Canada), a diverse urban setting. The first step was to classify land cover from the IKONOS image. This then served as the basis for creating a six-class and more detailed ten-class land-use map. The overall accuracies of the six- and ten-class maps were 90% and 86%, respectively. The high accuracies of individual classes suggest that the object-oriented methodology has great potential for efficiently classifying urban land use. The paper concludes with a discussion of the successes and remaining challenges of this type of work.

MANUFACTURING LOCATION IN A POLYCENTRIC URBAN AREA: A STUDY IN THE COMPOSITION AND ATTRACTIVENESS OF EMPLOYMENT SUBCENTERS

Attention has shifted to the role of subsidiary urban centers as the new “spatial nodes” within metropolitan areas as manufacturing employment has dispersed away from its traditional central city locations over the past decades. Understanding the character and evolving functions of these new “centers” is crucial to predicting (or influencing) future metropolitan spatial patterns. This paper explores the nature and role of the principal employment centers within the Dallas-Fort Worth region from the perspective of locational choices by firms in three-digit SIC Manufacturing. First the centers are empirically identified via a methodology that “maps” employment land-use polygons onto a zip code-level geography. The industrial attributes of firms choosing such centers are then investigated using multinomial logit. The general attractiveness to firms in manufacturing of various spatial characteristics of these centers are next studied through a discrete choice framework. Finally, a “mixed” conditional logit mo...