Non-linear methods in remotely sensed multispectral data classification

The aim of this research is to develop an effective approach being able to deal with the stochastic nature of remote sensing data. In order to achieve this objective it is necessary to structure the methodological knowledge in the area of data mining and reveal the most suitable methods for the prediction and decision support based on large amounts of multispectral data. The idea is to establish a framework by decomposing the task into functionality objectives and to allow the end-user to experiment with a set of classification methods and select the best methods for specific applications. As a first step, we compare our results from Bayesian classification based on non-parametric probability density estimates of the data to the results obtained from other classification methods. Tree scenarios are considered, making use of a small benchmark dataset, a larger dataset from Corine land cover project for Bulgaria and analyzing different features and feature selection methods. We show that the theoretically optimal Bayesian classification can also achieve optimal classification in practice and provides a realistic interpretation of the world where land cover classes intergrade gradually.     

An optimal selection of probability distribution functions for unsupervised land cover classification of PALSAR-2 data

Different types of classification techniques are available in the literature for the classification of Synthetic Aperture Radar (SAR) data into various land cover classes. Various SAR images are available for land cover classification such as ALOS PALSAR (PALSAR-1, PALSAR-2), RADARSAT and ENVISAT. In this paper, we have attempted to explore probability distribution function (pdf) based land cover classification using PALSAR-2 data. Over 20 different statistical distribution functions are analyzed for different classes based on statistical parameters. Probability distribution functions are selected based on Chi-squared goodness of fit test for each individual class. A decision tree based classifier is developed for classification based on the selected pdf functions and its statistical parameters. The proposed classification approach has an accuracy of 83.93%.     

Development and testing of a statistical texture model for land cover classification of the Black Sea region with MODIS imagery

A statistical model is proposed for analysis of the texture of land cover types for global and regional land cover classification by using texture features extracted by multiresolution image analysis techniques. It consists of four novel indices representing second-order texture, which are calculated after wavelet decomposition of an image and after texture extraction by a new approach that makes use of a four-pixel texture unit. The model was applied to four satellite images of the Black Sea region, obtained by Terra/MODIS and Aqua/MODIS at different spatial resolution. In single texture classification experiments, we used 15 subimages (50 × 50 pixels) of the selected classes of land covers that are present in the satellite images studied. These subimages were subjected to one-level and two-level decompositions by using orthonormal spline and Gabor-like spline wavelets. The texture indices were calculated and used as feature vectors in the supervised classification system with neural networks. The testing of the model was based on the use of two kinds of widely accepted statistical texture quantities: five texture features determined by the co-occurrence matrix (angular second moment, contrast, correlation, inverse difference moment, entropy), and four statistical texture features determined after the wavelet transformation (mean, standard deviation, energy, entropy). The supervised neural network classification was performed and the discrimination ability of the proposed texture indices was found comparable with that for the sets of five GLCM texture features and four wavelet-based texture features. The results obtained from the neural network classifier showed that the proposed texture model yielded an accuracy of 92.86% on average after orthonormal wavelet decomposition and 100% after Gabor-like wavelet decomposition for texture classification of the examined land cover types on satellite images.     

Selection of classification techniques for land use/land cover change investigation

The concerns over land use/land cover (LULC) change have emerged on the global stage due to the realisation that changes occurring on the land surface also influence climate, ecosystem and its services. As a result, the importance of accurate mapping of LULC and its changes over time is on the increase. Landsat satellite is a major data source for regional to global LULC analysis. The main objective of this study focuses on the comparison of three classification tools for Landsat images, which are maximum likelihood classification (MLC), support vector machine and artificial neural network (ANN), in order to select the best method among them. The classifiers algorithms are well optimized for the gamma, penalty, degree of polynomial in case of SVM, while for ANN minimum output activation threshold and RMSE are taken into account. The overall analysis shows that the ANN is superior to the kernel based SVM (linear, radial based, sigmoid and polynomial) and MLC. The best tool (ANN) is then applied on detecting the LULC change over part of Walnut Creek, Iowa. The change analysis of the multi temporal images indicates an increase in urban areas and a major shift in the agricultural practices.     

An improved land cover classification using polarization signatures for PALSAR 2 data

Land cover classification in mixed land cover scenarios is challenging with PolSAR data. Polarimetric decomposition techniques are most popular methods for PolSAR data classification in recent times. These techniques focus on identification of dominant scattering phenomena and hence result in sub-optimal classification in mixed land cover scenarios. Alternatively, polarization signatures (PSs) are good illustrations of SAR target responses as they depict a detailed physical information from target backscatter. Researchers have successfully utilized SAR PSs for land cover (LC) classification. Some reports suggested utilizing correlation between observed PSs and standard target PSs as features for LC classification. This paper presents a study on improved utilization of PSs for optimal LC classification in mixed class scenarios. First, PS based SAR features are derived using fully polarimetric SAR data. The features represent a degree of similarity between observed and standard PSs. The derived features are termed as polarization signatures correlation features or PSCFs. The novel PSCFs are analyzed, evaluated and compared with decomposition based features for the purpose of LC classification. Classification performance indicators highlight potential of PSCFs for mixed LC classification problems. Therefore, further an adaptive and optimal LC class boundary estimation approach for LC classification is proposed and developed. Observed PSs and reference LC class PS statistics are used to build empirical models between classification performance indicators and LC class boundaries. The empirical models are optimized using the evolutionary genetic algorithm to maximize classification performance. A decision tree is constructed based on the optimal class boundaries to prepare LC classification. The proposed classification approach is compared with some recent popular classifiers and comparison suggests that the proposed approach provides satisfactory results for mixed LC classification scenarios.     

Land use/land cover classification using time series Landsat 8 images in a heavily urbanized area

It is of great significance to timely, accurately, and effectively monitor land use/cover in city regions for the reasonable development and utilization of urban land resources. The remotely sensed dynamic monitoring of Land use/land cover (LULC) in rapidly developing city regions has increasingly depended on remote-sensing data at high temporal and spatial resolutions. However, due to the influence of revisiting periods and weather, it is difficult to acquire enough time-series images with high quality at both high temporal and spatial resolution from the same sensor. In this paper we used the temporal-spatial fusion model ESTARFM (Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model) to blend Landsat8 and MODIS data and obtain time-series Landsat8 images. Then, land cover information is extracted using an object-based classification method. In this study, the proposed method is validated by a case study of the Changsha City. The results show that the overall accuracy and Kappa coefficient were 94.38% and 0.88, respectively, and the user/producer accuracies of vegetation types were all over 85%. Our approach provides an accurate and efficient technical method for the effective extraction of land use/cover information in the highly heterogeneous regions.     

Built-up land mapping capabilities of the ASTER and Landsat ETM+ sensors in coastal areas of southeastern China

Worldwide urbanization has accelerated expansion of urban built-up lands and resulted in substantial negative impacts on the global environments. Precisely measuring the urban sprawl is becoming an increasing need. Among the satellite-based earth observation systems, the Landsat and ASTER data are most suitable for mesoscale measurements of urban changes. Nevertheless, to date the difference in the capability of mapping built-up land between the two sensors is not clear. Therefore, this study compared the performances of the Landsat-7 ETM+ and ASTER sensors for built-up land mapping in the coastal areas of southeastern China. The comparison was implemented on three date-coincident image pairs and achieved by using three approaches, including per-band-based, index-based, and classification-based comparisons. The index used is the Index-based Built-up Index (IBI), while the classification algorithm employed is the Support Vector Machine (SVM). Results show that in the study areas, ETM+ and ASTER have an overall similar performance in built-up land mapping but also differ in several aspects. The IBI values determined from ASTER were consistently higher than from ETM+ by up to 45.54% according to percentage difference. The ASTER also estimates more built-up land area than ETM+ by 5.9–6.3% estimated with the IBI-based approach or 3.9–6.1% with the SVM classification. The differences in the spectral response functions and spatial resolution between relative spectral bands of the two sensors are attributed to these different performances.     

Landsat thematic mapper studies of land cover spatial variability related to hydrology

The Landsat 4 and 5 Thematic Mapper (TM) provides increased spatial, spectral, and radiometric capability relative to the Multispectral Scanner (MSS). Visual inspection of TM imagery confirms this. Land cover detail is evident that would be of use in watershed management and planning activities. Specific studies have been conducted in Georgia, West Virginia, Michigan and Maryland to compare MSS and TM for urbanizing watersheds, wetlands, and floodplain mapping situations. These studies show that only modest improvements in classification accuracy (Anderson Level I/II) have been achieved using existing classification approaches. An attempt to identify the visibly apparent interstate highways and secondary and residential streets in TM data via conventional approaches failed due to an inability to derive separable spectral signatures. The basis for a non-parametric approach to classification is presented in which roads are identified by locating linear local minima in the greenness transformed dimension. Preliminary results indicate that such a method provides more reliable road locations than MSS or TM used singly.     

Hydrologic appraisal of rivers plan-form at confluence zone — A case study using Landsat MSS data

In river systems confluences and bifurcations are typical features whose effects are largely dependent on the specific characteristics of the rivers involved. The study makes an attempt to analyse the planform configuration at the confluence zone of the Wainganga and Khobragadi rivers in the central part of India. The data used are the Landsat MSS CCT data of date 17.12.1972 for scene 154-046 and black and white aerial photographs of November, 1969. Supervised method of classification using maximum likelihood classification method is employed. The study confirms that the discharge and sediment transport in the individual rivers constitute the dominating factors in the changes of planform geometry at a confluence. The usefulness of the Landsat MSS data and digital analysis techniques. for generating the necessary data inputs for the study is also validated.     

Satellite data as a basis for planning studies of infrastructure and related rural development in Atacora Province,Benin, West Africa

Landsat satellite data has been used to provide information for integrated land resources, agriculture and rural access road planning in Atacora Province, Benin, to ensure that correct decisions are made on the location of feeder roads and best use is made of the terrain. A significant aspect of the interpretation programme involved using a method of terrain evaluation and land classification to provide a framework for planning and assessing all subsequent development projects and highway engineering activities within the Province. Use of this terrain classification, in conjunction with further sequential satellite coverage, is considered as a basis for monitoring and subsequently analysing the rleationship between feeder road construction and induced benefits within the rural agricultural development sector, and for the establishment of a system of data storage. The value of a data storage system is evaluated as a means of preventing wasteful repetition of survey effort and facilitating the transfer of relevant data on rural development to similar areas within Benin and throughout West Africa.     

航天器构型重构技术研究进展与展望

航天器构型重构技术是航天器在轨服务等重大空间任务必须突破的关键技术之一,将对新一代航天器系统的设计与研发产生深远影响。首先,给出了航天器构型重构的内涵及分类;其次基于主结构变构型等多种典型技术,对构型重构技术的研究现状进行了系统的总结和探讨;随后基于标准化模块设计等方法,给出了航天器构型重构技术体系;接着从支持航天器故障排除等方面出发,对构型重构技术的应用前景进行了归纳;最后,总结了构型重构技术的总体研究进展,并对其未来发展进行了展望。     

Development of autonomous control in a closed microbial bioreactor.

Space-based life support systems which include ecological components will rely on sophisticated hardware and software to monitor and control key system parameters. Autonomous closed artificial ecosystems are useful for research in numerous fields. We are developing a bioreactor designed to study both microbe-environment interactions and autonomous control systems. Currently we are investigating N-cycling and N-mass balance in closed microbial systems. The design features of the system involve real-time monitoring of physical parameters (e.g. temperature, light), growth solution composition (e.g. pH, NOx, CO2), cell density and the status of important hardware components. Control of key system parameters is achieved by incorporation of artificial intelligence software tools that permit autonomous decision-making by the instrument. These developments provide a valuable research tool for terrestrial microbial ecology, as well as a testbed for implementation of artificial intelligence concepts. Autonomous instrumentation will be necessary for robust operation of space-based life support systems, and for use on robotic spacecraft. Sample data acquired from the system, important features of software components, and potential applications for terrestrial and space research will be presented.     

Canadian advanced life support capacities and future directions

Canada began research on space-relevant biological life support systems in the early 1990s. Since that time Canadian capabilities have grown tremendously, placing Canada among the emerging leaders in biological life support systems. The rapid growth of Canadian expertise has been the result of several factors including a large and technically sophisticated greenhouse sector which successfully operates under challenging climatic conditions, well planned technology transfer strategies between the academic and industrial sectors, and a strong emphasis on international research collaborations. Recent activities such as Canada’s contribution of the Higher Plant Compartment of the European Space Agency’s MELiSSA Pilot Plant and the remote operation of the Arthur Clarke Mars Greenhouse in the Canadian High Arctic continue to demonstrate Canadian capabilities with direct applicability to advanced life support systems. There is also a significant latent potential within Canadian institutions and organizations with respect to directly applicable advanced life support technologies. These directly applicable research interests include such areas as horticultural management strategies (for candidate crops), growth media, food processing, water management, atmosphere management, energy management, waste management, imaging, environment sensors, thermal control, lighting systems, robotics, command and data handling, communications systems, structures, in-situ resource utilization, space analogues and mission operations. With this background and in collaboration with the Canadian aerospace industry sector, a roadmap for future life support contributions is presented here. This roadmap targets an objective of at least 50% food closure by 2050 (providing greater closure in oxygen, water recycling and carbon dioxide uptake). The Canadian advanced life support community has chosen to focus on lunar surface infrastructure and not low Earth orbit or transit systems (i.e. microgravity applications). To advance the technical readiness for the proposed lunar missions, including a lunar plant growth lander, lunar “salad machine” (i.e. small scale plant production unit) and a full scale lunar plant production system, a suite of terrestrial developments and analogue systems are proposed. As has been successfully demonstrated by past Canadian advanced life support activities, terrestrial technology transfer and the development of highly qualified personnel will serve as key outputs for Canadian advanced life support system research programs. This approach is designed to serve the Canadian greenhouse industry by developing compliance measures for mitigating environmental impact, reducing labour and energy costs as well as improving Canadian food security, safety and benefit northern/remote communities.     

Life support systems for Mars transit.

The long-held human dream of travel to the stars and planets will probably be realized within the next quarter century. Preliminary analyses by U.S. scientists and engineers suggests that a first trip to Mars could begin as early as 2016. A proposal by U.S.S.R. space planners has suggested that an effort involving the cooperation and collaboration of many nations could begin by 2011. Among the major considerations that must be made in preparation for such an excursion are solidification of the scientific, economic and philosophical rationales for such a trip made by humans, and realistic evaluations of current and projected technical capabilities. Issues in the latter category include launch and propulsion systems, long term system stability and reliability, the psychological and physiological consequences of long term exposure to the space environment, the development and use of countermeasures to deleterious human physiological responses to the space environment, and life support systems that are both capable of the immense journey and reliable enough to assure their continued operation for the duration of the voyage. Many of the issues important in the design of a life support system for a Mars trip are based on reasonably well understood data: the human requirements for food, oxygen and water. However, other issues are less well-defined, such as the demands that will be made on the system for personal cleanliness and hygiene, environmental cleanliness, prevention or reduction of environmental toxins, and psychological responses to the environment and to the diet. It is much too early to make final decisions about the characteristics of the long-duration life support system needed for travel to Mars, or for use on its surface. However, it is clear that life support systems will evolve during the next few decades form the relatively straightforward systems that are used on Shuttle and Soyuz, to increasingly more complex and regenerative systems. The Soviet Union has an operating life support system on Mir that can apparently evolve, and the United States is currently planning the one for Space Station Freedom that will use partial regeneration. It is essential to develop concepts now for life support systems on an advanced Space Station, the lunar outpost (to be launched in about 2004) and the lunar base. Such concepts will build on current technology and capabilities. But because of the variety of different technologies that can be developed, and the potential for coordinating the functions of very diverse sub-systems within the same life support system, the possibility of developing an efficient, reliable mixed process system is high. It is likely that a life support system for Mars transit and base will use a composite of physical, chemical, and biological processes. The purpose of this paper is to explore the potentially useful structural elements of a life support system for use on a Mars trip, and to identify the features that, at this time, appear to be most appropriate for inclusion in the system.     

Assessment of the impact of dimensionality reduction methods on information classes and classifiers for hyperspectral image classification by multiple classifier system

Identification of the appropriate combination of classifier and dimensionality reduction method has been a recurring task for various hyperspectral image classification scenarios. Image classification by multiple classifier system has been evolving as a promising method for enhancing accuracy and reliability of image classification. Because of the diversity in generalization capabilities of various dimensionality reduction methods, the classifier optimal to the problem and hence the accuracy of image classification varies considerably. The impact of including multiple dimensionality reduction methods in the MCS architecture for the supervised classification of a hyperspectral image for land cover classification has been assessed in this study. Multi-source airborne hyperspectral images acquired over five different sites covering a range of land cover categories have been classified by a multiple classifier system and compared against the classification results obtained from support vector machines (SVM). The MCS offers acceptable classification results across the images or sites when there are multiple dimensionality reduction methods in addition to different classifiers. Apart from offering acceptable classification results, the MCS indicates about 5% increase in the overall accuracy when compared to the SVM classifier across the hyperspectral images and sites. Results indicate the presence of dimensionality reduction method specific empirical preferences by land cover categories for certain classifiers thereby demanding the design of MCS to support adaptive selection of classifiers and dimensionality reduction methods for hyperspectral image classification.     

基于光电探测系统的地面车精确定位定向技术

针对地/地导弹发射车、指挥车、侦察车等陆地战车对车载定位/定向系统越来越高的要求,提出了一种利用光电探测系统测量3个已知标志点与地面车辆之间的角度信息来精确确定地面车辆的位置和航向的方法.仿真结果表明:只需依次对3个已知标志点进行1次光电测角,就可以精确确定地面车辆的位置和航向,并且东向和北向定位误差小于0.5m,方位误差小于20″(1σ).这种方法简单、快速,定位定向精度高,且能同时服务于同一场地的多辆地面车,具有重要的实用价值.      

Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas

Urban land cover information extraction is a hot topic within urban studies. Heterogeneous spectra of high resolution imagery—caused by the inner complexity of urban areas—make it difficult. In this paper a hierarchical object oriented classification method over an urban area is presented. Combining QuickBird imagery and light detection and ranging (LIDAR) data, nine kinds of land cover objects were extracted. The Spectral Shape Index (SSI) method is used to distinguish water and shadow from black body mask, with 100% classification accuracy for water and 95.56% for shadow. Vegetation was extracted by using a Normalized Difference Vegetation Index (NDVI) image at first, and then a more accurate classification result of shrub and grassland is obtained by integrating the height information from LIDAR data. The classification accuracy of shrub was improved from 85.25% to 92.09% and from 82.86% to 97.06% for grassland. More granularity of this classification can be obtained by using this method. High buildings and low buildings can, for example, be distinguished from the original building class. Road class can also be further classified into roads and crossroads. The comparison of the classification accuracy between this method and the traditional pixel-based method indicates that the total accuracy is improved from 69.12% to 89.40%.     

AToxMss--from a space proven payload to a validated testsystem in ecotoxicology.

The C.E.B.A.S.-Minimodule (Closed Equilibrated Biological Aquatic System) is a space qualified aquatic microcosm of 8.6 liters volume of water. Several aquatic species can be reared in parallel. Based on its characteristics (closed system, highly standardized, testruns longer than 4 weeks are possible, organisms of different trophic levels can be investigated) an improved module (C.B.R.U.=Closed Biological Research Unit) is under development for scientific and commercial use in ecotoxicology. In a two year project named AToxMss (Aquatic EcoToxicology in a Multispecies System) this goal can be reached. AToxMss is a R&D project of an industry team and two teams of the University of Bremen, funded by industry (OHB-System AG) and the state of Bremen, Germany. Three project phases are already completed: The parameter determination to indicate potential impact of chemicals on biological systems, the selection of test substances, as well as the manufacturing of 3 functional modules, each verified for use in ecotoxicological research. The next phase starts with a series of test runs calibrating the system by using well known toxic substances and chemicals.