An Automated Approach for Land Cover Classification Based on a Fuzzy Supervised Learning Framework

This paper proposes an automatic framework for land cover classification. In majority of published work by various researchers so far, most of the methods need manually mark the label of land cover types. In the proposed framework, all the information, like land cover types and their features, is defined as prior knowledge achieved from land use maps, topographic data, texture data, vegetation’s growth cycle and field data. The land cover classification is treated as an automatically supervised learning procedure, which can be divided into automatic sample selection and fuzzy supervised classification. Once a series of features were extracted from multi-source datasets, spectral matching method is used to determine the degrees of membership of auto-selected pixels, which indicates the probability of the pixel to be distinguished as a specific land cover type. In order to make full use of this probability, a fuzzy support vector machine (SVM) classification method is used to handle samples with membership degrees. This method is applied to Landsat Thematic Mapper (TM) data of two areas located in Northern China. The automatic classification results are compared with visual interpretation. Experimental results show that the proposed method classifies the remote sensing data with a competitive and stable accuracy, and demonstrate that an objective land cover classification result is achievable by combining several advanced machine learning methods.     

Mapping Wetland Areas Using Landsat-Derived NDVI and LSWI: A Case Study of West Songnen Plain,Northeast China

Increasing interest in wetlands for environmental management requires an understanding of the location, spatial extent, and configuration of the resource. The National Wetlands Inventory is the most commonly used data source for this information. However, its accuracy is limited in some contexts, such as agricultural and forested wetlands. An large number of studies have mapped wetlands worldwide from the perspective of land use and land cover change. However, information on the actual wetland planting areas annually is limited, which greatly impacts ongoing research. In this case study of the West Songnen Plain, we developed a simple algorithm for the quick mapping of wetlands by utilizing their unique physical features, such as annual display of phenological land-cover change of exposed soils, shallow flooding water, and plants from multi-temporal Landsat images. Temporal variations of the Normalized Difference Vegetation Index (NDVI) and Land Surface Water Index (LSWI) derived from Landsat images in 2010 for wetlands at different growth stages were analyzed. Results show that during the ante-tillering phase, the NDVI value (above zero) is lower than the LSWI value of paddies because of flooding of shallow water; during the reproductive and ripening phases, the NDVI value is higher than the LSWI value (above zero); and during the post-harvest wetland planting phase, the NDVI value is still higher than the LSWI value, but the LSWI value is negative. Wetland areas can be detected using one or two images in the optimum time window. The algorithm based on the difference of NDVI and LSWI values derived from Landsat images was used to extract the actual wetland planting area. Validated alongside statistical data, the algorithm showed high accuracy. Therefore, this algorithm highlights the unique features of wetlands and can help in mapping the actual wetland area annually on a regional scale. Results further indicate that the new method has a classification accuracy of 92 %. In comparison, two traditional methods based on Landsat-7/ETM registered accuracy rates of only 83 % and 87 % respectively.     

Study on Polarized Spectral Characteristics of Soil with Different Water Content

Moisture is one of the important parameters in soil polarized spectrum. It has great significance in soil remote sensing band selection and image interpretation; it also provides the information for soil investigation and analysis on physical and chemical properties. In this paper we tested and analyzed the soil polarized spectrum with different moisture in 350?~?2,500 nm wavelength, to study on the relationship between soil polarized spectral data and moisture, to determine the spectral response and changes in soil moisture, and establish models between spectral data and soil moisture. We also designed a orthogonal test on the various factors that affect soil polarized spectral characteristics, in which we studied soil moisture, polarized angle, detected angle and azimuth of the various factors and their interactions. The results showed it was most significant that the soil moisture and the interaction of soil moisture and polarized angle, followed by the interaction effect of detected angle and moisture, while the polarized angle had a little impact on the soil polarized spectrum.     

Shadow detection and compensation for color aerial images

A method for shadow detection and compensation for color aerial images is presented. It is considered that the intensity value of each image pixel is the product of illumination function and ground object reflection, and the shadowed regions on the image are mainly caused by the short of illumination, so the information compensation for the shadowed regions should concentrate on the illumination adjustment of concerned area on the basis of the analysis of whole image. The shadow detection and compensation procedure proposed by this paper consists of four steps.     

Forward simulation of gravity for crustal structure of Xiachayu-Gonghe profile in eastern Tibetan plateau

The crustal structure of Xiachayu-Gonghe geophysical profile in eastern Tibetan plateau is simulated with Bouguer anomaly corrected for sediments and lithosphere. The forward simulation shows that the thickness of upper crust in eastern Tibetan plateau is about 20 km, and the density is 2.78×103kg/m3. The bottom interface of middle crust changes from 30 km to 40 km, the density of middle crust is 2.89×103kg/m3. The materials with low density of 2.78 ×103kg/m3 exist in middle crust, and those with high density of 3.33 ×103kg/m3 exist at the bottom of middle crust between Wenquan and Tanggemu. The density is 3.10 ×103kg/m3 in lower crust. The shallowest depth of Moho interface is about 56 km, and the deepest one is about 74 km, the undulation of interface is large, the deep Moho is located in Xiachayu, Chayu, Nujiang, and Wenquan. The crustal density of eastern Tibetan plateau is larger than that of central section; the low velocity layers are located in middle crust and bottom in eastern Tibetan plateau and at the bottom of the upper crust in the central plateau.     

Discovering Spatial Interaction Communities from Mobile Phone Data

In the age of Big Data, the widespread use of location‐awareness technologies has made it possible to collect spatio‐temporal interaction data for analyzing flow patterns in both physical space and cyberspace. This research attempts to explore and interpret patterns embedded in the network of phone‐call interaction and the network of phone‐users’ movements, by considering the geographical context of mobile phone cells. We adopt an agglomerative clustering algorithm based on a Newman‐Girvan modularity metric and propose an alternative modularity function incorporating a gravity model to discover the clustering structures of spatial‐interaction communities using a mobile phone dataset from one week in a city in China. The results verify the distance decay effect and spatial continuity that control the process of partitioning phone‐call interaction, which indicates that people tend to communicate within a spatial‐proximity community. Furthermore, we discover that a high correlation exists between phone‐users’ movements in physical space and phone‐call interaction in cyberspace. Our approach presents a combined qualitative‐quantitative framework to identify clusters and interaction patterns, and explains how geographical context influences communities of callers and receivers. The findings of this empirical study are valuable for urban structure studies as well as for the detection of communities in spatial networks.     

Multi-resolution seamless image database

This paper presents the basic concepts and principles, data structure and high efficient spatial index for multi-resolution image database. The database is characterized by arrangement of multi-resource image data and seamless mosaic, distribution-based storage and management, integration with other spatial database software such as GeoStar and GeoGrid developed by Wuhan Technical University of Surveying and Mapping.     

Development of a data mining method for land control

Land resources are facing crises of being misused, especially for an intersection area between town and country, and land control has to be enforced. This paper presents a development of data mining method for land control. A vector-match method for the prerequisite of data mining i. e., data cleaning is proposed, which deals with both character and numeric data via vectorizing character-string and matching number. A minimal decision algorithm of rough set is used to discover the knowledge hidden in the data warehouse. In order to monitor land use dynamically and accurately, it is suggested to set up a real-time land control system based on GPS, digital photogrammetry and online data mining. Finally, the means is applied in the intersection area between town and country of Wuhan city, and a set of knowledge about land control is discovered.     

Definitions of natural-language spatial relations: Combining topology and directions

Because SQL for querying data from spatial databases is ineffective, the query based on natural or visual language becomes an attractive research field gradually. However, how to define and represent natural languages related to spatial data are still gigantic problems. Because existing models of direction relations can't describe by use of some common concepts. First of all, detailed direction relations are proposed to describe the directions related to the interior of spatial objects, such as “east part of a region”, “east boundary of a region”, and so on. Secondly, by integrating the detailed directions with exterior direction relations and topological relations, several NLSRs are defined, such as “a road goes across the east part of a lake”, “a river goes along the east boundary of a province”, etc. Finally, based on the NLSRs abovementioned, a natural spatial query language (NSQL) is formed to retrieve data from spatial databases.     

Data model and visualization of 3D city landscape based on integrated databases

Data acquisition and modeling are the two important, difficult and costful aspects in a Cybercity project. 2D-GIS is mature and can manage a lot of spatial data. Thus 3D-GIS should make the best of data and technology of 2D-GIS. Construction of a useful synthetic environment requires integration of multiple types of information like DEM, texture images and 3D representation of objects such as buildings. In this paper, the method for 3D city landscape data model and visualization based on integrated databases is presented. Since, the data volume of raster are very huge, special strategies (for example, pyramid gridded method) must be adopted in order to manage raster data efficiently. Three different methods of data acquisition, the proper data structure and a simple modeling method are presented as well. At last, a pilot project of Shanghai Cybercity is illustrated.