The recent advance of satellite technology has led to explosive growth of high-resolution remote sensing images in both quantity and quality. To address the challenges of high-resolution remote sensing images retrieval in both efficiency and accuracy, a distributed system architecture for satellite images retrieval by combining deep and traditional hand-crafted features is proposed in this paper. On one hand, to solve the problem of higher computational complexity and storage capacity, Hadoop framework is applied to manage satellite image data and to extract image features in parallel environment. On the other hand, deep features based on convolutional neural networks (CNNs) are extracted and combined with traditional features to overcome the limitations of hand-crafted features. Besides, object detection are integrated in the proposed system to realize accurate object locating at the time of retrieval. Experiments are carried on several challenging datasets to evaluate the performance of the proposed distributed system. Standard metrics like retrieval precision, recall and computing time under different configurations are compared and analyzed. Experimental results demonstrate that our system architecture is practical and feasible, both efficiency and accuracy can meet realistic demands.
Illumination variability is one of the most important issues affecting imagery matching performances and still remains a critical problem in the literature, although different levels of improvement have been reported in recent years. This study proposes an illumination robust image matching method. There are three steps in the proposed method: first, local regions are extracted and matched from the input images by using a multiresolution region detector and an illumination robust shape descriptor; second, an algorithm is proposed to estimate the overlapping areas of images and enhance them based on the region matches; finally, general feature detectors and descriptors are combined to process the previous results for illumination robust matching. Experimental results demonstrate that the proposed matching method provides significant improvement in robustness for illumination change images compared with traditional methods.
Accurate estimation of forest aboveground biomass is crucial for monitoring ecosystem responses to environmental change. Passive optical and active microwave remote sensing plays an important role in retrieving the forest biomass. However, optical spectral reflectance gets saturated in the relatively high-density vegetation area and microwave backscattering is largely influenced by the soil underneath when the vegetation coverage is relatively low. Both of these conditions affect the biomass retrieval accuracy. A synergistic biomass retrieval model through the integration of optical (PROSAIL) and microwave (MIMICS) radiative transfer models was put forward. The proposed model unified the vegetation and soil conditions of PROSAIL and MIMICS models, and determined the optical-alone model, microwave-alone model, and the contributions of key optical and microwave factors to biomass retrieval with the simulated database. The database consisted of the optical bidirectional reflectance and full polarization microwave backscattering of the broad-leaved forest canopy under various conditions. The synergistic model was verified by comparing with the ground measurements and the results of the optical-alone and microwave-alone models. The results indicated that the proposed synergistic retrieval model was more effective than the optical-alone or microwave-alone model, and showed considerable potential in forest aboveground biomass retrieval by integrating passive optical and active microwave remote sensing.
Most of the Antarctic continent is covered with ice and snow. However, it’s hard to distinguish clouds from ice and snow
in remote sensing images because they both have similar characteristics in visible reflectances and infrared brightness
temperatures. Thus there exist great difficulties in determining the precise locations and distribution of clouds in remote
sensing images. To solve this problem, a new method is proposed to identify clouds for Landsat imagery over the
Antarctic region. Top of atmosphere reflectance and brightness temperature of Landsat imagery are used as inputs.
Several spectral tests combining with morphological operations are employed to highlight clouds, especially thin clouds.
The results show that the new method can not only greatly eliminate the effects of snow and ice, but also extract thin
clouds effectively, and thus improve cloud detection accuracy over the Antarctic region.
Texture features are widely used in image retrieval literature. However, conventional texture features are extracted from grayscale images without taking color information into consideration. We present two improved texture descriptors, named color Gabor wavelet texture (CGWT) and color Gabor opponent texture (CGOT), respectively, for the purpose of remote sensing image retrieval. The former consists of unichrome features computed from color channels independently and opponent features computed across different color channels at different scales, while the latter consists of Gabor texture features and opponent features mentioned above. The two representations incorporate discriminative information among color bands, thus describing well the remote sensing images that have multiple objects. Experimental results demonstrate that CGWT yields better performance compared to other state-of-the-art texture features, and CGOT not only improves the retrieval results of some image classes that have unsatisfactory performance using CGWT representation, but also increases the average precision of all queried images further. In addition, a similarity measure function for proposed representation CGOT has been defined to give a convincing evaluation.
This paper presents a method on how to organize 3D remote sensing images and how to publish these images quickly.
We use two levels of grid-based spatial index to organize massive images. First, we divide a huge digital city image into
many map sheets (big images). All of map sheets construct a matrix structure. We use row number and column number
to encode every map sheet. Second, by using resample and bilinear interpolation method, we build pyramid for every
map sheet to form multi-scale hierarchical structure. At the same time building pyramid, we adopt JPEG compression
technology to produce JPEG image format files. The number of output image files equals to the number of pyramid
layers. Third, divide every pyramid layer image into many small image tiles. The size of each tile image is 256*256
pixels. All of small tiles of each pyramid layer image also construct a matrix structure. We also use row number and
column number to encode every small image tile. We create a file directory for each map sheet in order to store all of
small image tiles. we neatly combine the spatial index structure with the file name of each tile, which make server be
able to return tile to browser side very quickly without any query operation. With the proposed method, we can provide
users with a fast and efficiently tool to publish their own spatial information without involving any programming work.
The system performance is very good and the response time is almost identical for different size images.
This paper proposes the theory framework of spatial information sharing on digital city, and analyzes its technical
characteristics. According to the Service Oriented Architecture (SOA) framework, a geospatial information sharing
platform is put forward. The spatial data sharing model based on SOA is designed. A prototype platform of realizing
multiple-source spatial information sharing based on ArcGIS Server is developed.
Geospatial metadata, data, and services have been widely collected, developed and deployed in recent years. This
flourishing of geospatial resources also added to the problem of geospatial heterogeneity. Interoperability research and
implementation are needed for advancement in potential solutions to integrate and interoperate these widely dispersed
geospatial resources. We design and implement Wuhan Geospatial Information Sharing Platform based on existing
WMS. This platform consists of three components: Web Client, Metadata Catalog, and Data Services. Data Services
provide WMS. All spatial information from different sources has been published as WMS. These WMS have been
described by geospatial metadata compatible with geospatial metadata standard. These geospatial metadata has been
stored in Metadata Catalog. Web Client provides functionalities to access and process WMS described by geospatial
metadata in Metadata Catalog.
Spatial information systems and spatial information in different geographic locations usually belong to different organizations. They are distributed and often heterogeneous and independent from each other. This leads to the fact that many isolated spatial information islands are formed, reducing the efficiency of information utilization. In order to address this issue, we present a method for effective spatial information integration based on web service. The method applies asynchronous invocation of web service and dynamic invocation of web service to implement distributed, parallel execution of web map services. All isolated information islands are connected by the dispatcher of web service and its registration database to form a uniform collaborative system. According to the web service registration database, the dispatcher of web services can dynamically invoke each web map service through an asynchronous delegating mechanism. All of the web map services can be executed at the same time. When each web map service is done, an image will be returned to the dispatcher. After all of the web services are done, all images are transparently overlaid together in the dispatcher. Thus, users can browse and analyze the integrated spatial information. Experiments demonstrate that the utilization rate of spatial information resources is significantly raised thought the proposed method of distributed spatial information integration.
Geospatial portals use Web Services to publish available geospatial data and processing services, help applications find
them and invoke services or retrieve data. OGC has developed Geospatial Portal Reference Architecture to assist to
implement a standards-based geospatially enabled portal application. The Geospatial Portal Reference Architecture is a
major for E-Government, National Spatial Data Infrastructures, enterprises and Information Communities. It enables
geoprocessing interoperability that makes it possible to exchange heterogeneous geographic information content and
share a wide variety of geospatial services over the World Wide Web. In this article, we study the Geospatial Portal
Reference Architecture. On the basis of this reference, we design and implement a geospatial portal. This article
describes the architecture of this portal, development and deployment of this portal.
In this paper, the technical attribute developing from the fixed wireless broadband technology (IEEE802.16-2004) to
mobile wireless broadband technology (IEEE802.16e-2005) is discussed. A mobile WiMAX (Worldwide Interoperability for Microwave Access) network structure is designed for the special needs of mobile digital city. This paper designed and optimized the specific network structure. The function of mobile wireless video, audio, data service
and others, which can manage and service for the mobile digital city are realized based on the mobile WiMAX network.
Traditional GIS caused obstacles and inconveniences for sharing and services of global spatial information. In this paper,
spatial information multi-grid (SIMG) is presented to institute a uniformed, rigorous, and continuous national spatial
information infrastructure for national service. Firstly, its fundamental theories and key technologies are brief
introduced. Then, this paper discusses its theoretical framework, notional model, data structure and relative methods
designed for service. At last, a prototype system is cited to verify its feasibility and validity.
Grid computation and the Theory of Ontology provide opportunities for the integration and interoperation of Geographic
Information Systems (GIS). In this paper we integrate the two technologies into the field of GIS for the semantic
interoperability of the geographic information. First, we build geographic data ontology and geographic function
ontology to represent geographic data and geographic functions since we consider GIS as an organic system composed
of geographic data and kinds of functions related to space such as space query and space analysis and so on. Second, we
present how to wrap geographic data with geo-data ontology and how to describe the geographic function with geofunction
ontology. Third, we introduce an architecture which composed of Semantic Registration, Consumer Service
Center and Semantic Matchmaker for ontology-based geographic information semantic grid services. Finally, we analyze
future work need to do for geographic information semantic interoperability.
Spatial Information Multi-grid (SIMG) is regarded as a new method of spatial information expression considering the
characters of nature and attributes of society. The focus of this paper is on a dynamic spatio-temporal expression for
spatial information based on the framework of SIMG. Traditional Spatio-temporal Data Models (STDMs) lack enough
abilities to meet the requirements of expressing and organizing spatial information based on the framework of SIMG. In
this paper, the three characters (space, attribute, time) of SIMG spatial features are studied, systematic classification of
spatio-temporal changes of SIMG spatial feature are described, and a Spatio-temporal Semantic Model based on SIMG
How to recognize man-made objects from high-resolution remote sensing images has been considered an attractive and important research field in remote sensing applications undoubtedly. In this paper we try to present a feasible contour-based retrieval strategy of remote sensing images. The merit of our strategy is it can avoid the impact caused by the difficult of automatic manmade object discrimination so far and the deficiency of huge computational volume aroused by template matching. Besides, on the basis of analyzing the limitations of common descriptors such as Fourier descriptor and Hu invariant moments, invariant relative moments are adopted to describe shape feature of man-made objects in our retrieval strategy. After describing contour feature extraction method, feature matching method and retrieval process based on shape feature, a prototype system is also designed and implemented to prove the validity and accuracy of our strategy mentioned above. In our experiments three types of man-made objects with different shape feature, i.e., boat, oilcan and buildings with flat-roof, are selected as our research targets. Experimental results illustrate that our strategy is feasible and the corresponding retrieval performance is analyzed, followed by conclusions and future works.
Based on the significance and strategic prospect of geo-informatization system, this paper researches the orientation of geo-informatization system in detail. It also discusses the architecture of geo-informatization system according to its development trend. At last, the five phases of geo-informatization system are compared and analyzed comprehensively.
With lower speed of geographical data upgrades than the corresponding demands for them, geographical data update becomes the bottleneck that geographical Information Systems (GIS) face at present. Remote sensing images are the most available data source of geographical data upgrade. In this paper, a strategy of selecting the maximum variance between clusters to detect the changed area is put forward. Based on the changed area, the geographical data can be updated using remote sensing images. The validity of the strategy is proved at the last of the paper.
In this paper, a topology-based strategy for 3D reconstruction of complicated buildings from stereo image pair is put forward. It comes from our investigation on the applicability of topology analysis and a strongly topology-driven process that combines different levels of geometrical description with different levels of topological abstraction.
The authors emphasize the topology-based strategy on different levels of geometrical description: Firstly a topology-based 3D data model is presented in which the topological relationships within a building or between geometrical objects are described implicitly or explicitly. Secondly based on description of vertexes level, interested vertexes are collected from stereo image pair and saturated attribute of each interior vertex is defined, furthermore an adjacency table is defined to store the connection attributes of verges automatically. Thirdly surfaces are looked on as polygons with closed verges on the basis of bi-directional querying of the adjacency table. Finally complicated buildings are described as graphs with interior and exterior topological attributes. Based on the strategy mentioned above, a software platform for 3D reconstruction of complicated buildings is built up. The efficiency of suggested method is examined through practical experiments.
The 3D model of interchanges is one of the fundamental components of the city models and has got researcher’s extensive concern in recent years. However, solution to automatic extraction of 3D man-made complicated objects is still unavailable up to now because automatic interpretation of spatial image lacks required performance for practical applications. In this paper, an integrated method involving stereo image pair, CAD, DPW and VR technology for 3D reconstruction of the interchange is put forward and various solutions are presented to meet the demands of the Cyber City according to application requirements. Besides, the semantics of interchange as a whole is used to control and to evaluate the quality of interchange model extraction in all the reconstruction process. Finally, a software platform for 3D reconstruction of the interchange using OpenGL and VC++ is built up and the efficiency of suggested method is examined through practical case studies.