作者:
Gasteratos, AntoniosZafeiridis, PanagiotisAndreadis, IoannisLaboratory of Robotics and Automation
Section of Production Systems Department of Production and Management Engineering Democritus University of Thrace Building of University’s Library Kimmeria XanthiGR-671 00 Greece Laboratory of Electronics
Section of Electronics and Information Systems Technology Department of Electrical and Computer Engineering Democritus University of Thrace Vassilisis Sophias 12 XanthiGR-671 00 Greece
Content based image retrieval is an active research area of patternrecognition. A new method of extracting global texture energy descriptors is proposed and it is combined with features describing the color aspect of...
详细信息
Multisensor image registration is a difficult problem. In this paper, we give a new registration method using direct histogram specification technique. We find that after using histogram specification, the resulting i...
详细信息
Multisensor image registration is a difficult problem. In this paper, we give a new registration method using direct histogram specification technique. We find that after using histogram specification, the resulting images with the same view look more similar, though the original images gained by different sensors differ much in intensity. Based on this property, a novel approach to find matching block pairs is proposed. The centers of the block pairs are used as control points (cps). We also use the cluster method of the nearest function criterion to test the correctness of the cps and discard wrong ones. The algorithm has been tested by many aerial images of different sensors. The effectiveness is illustrated by the experimental results.
image segmentation is a process frequently used in several different areas including Cartography. Feature extraction is a very troublesome task, and successful results require more complex techniques and good quality ...
详细信息
Hyperbolae are common features in typical GPR scans that may result from localised reflectors (such as rocks), or from a buried cylindrical-shaped objects (such as pipes or drums). The shapes of these hyperbolae are i...
详细信息
ISBN:
(纸本)9090179593
Hyperbolae are common features in typical GPR scans that may result from localised reflectors (such as rocks), or from a buried cylindrical-shaped objects (such as pipes or drums). The shapes of these hyperbolae are influenced by both the nature of the subsurface reflector as well as the relative permittivity of the medium in which the objects are located. It is this uncertainty about what a hyperbola in a GPR scan actually represents, that has made it very difficult to make accurate estimations from GPR data, with regard to the buried object itself on one hand, and to the medium surrounding it on the other. In this paper, a novel general equation for hyperbolae which result from buried cylinders is presented which allows for cylinders of arbitrary radius, resulting in a more accurate estimation of the relative permittivity of the surrounding medium and of the depth, in addition to the radius information. This is achieved by subjecting the radargrams to a series of imageprocessing stages followed by a curve-fitting procedure specifically developed for hyperbolae. The fitting technique is applied on a variety of synthetic hyperbolae that are generated to emulate reflections from targets of varying depth and radius and buried in a range of dielectrics. The results indicate this technique is fully capable of successfully estimating the depth and radius to within 1%. Further application to control site data has also given similar results, validating the method and justifying the assumptions used.
In this paper, we propose an unsupervised land use classification method for multispectral image. Especially, we present a novel spatial mean shift procedure and an automatic band selection method. We make full use of...
详细信息
In this paper, we propose an unsupervised land use classification method for multispectral image. Especially, we present a novel spatial mean shift procedure and an automatic band selection method. We make full use of the edge information from the mean shift procedure to improve the over-segmentation. Experimental results on Landsat TM images validate the efficiency of the proposed method.
The general trend in remotesensing is on one hand to increase the number of spectral bands and the geometric resolution of the imaging sensors which leads to higher data rates and data volumes. On the other hand the ...
详细信息
ISBN:
(纸本)0819451177
The general trend in remotesensing is on one hand to increase the number of spectral bands and the geometric resolution of the imaging sensors which leads to higher data rates and data volumes. On the other hand the user is often only interested in special information of the received sensor data and not in the whole data mass. Concerning these two tendencies a main part of the signal pre-processing can already be done for special users and tasks on-board a satellite. For the BIRD (Bispectral InfraRed Detection) mission a new approach of an on-board data processing is made. The main goal of the BIRD mission is the fire recognition and the detection of hot spots. This paper describes the technical solution and the first results, of an on-board image data processing system based on the sensor system on two new IR-Sensors and the stereo line scanner WAOSS (Wide-Angle-Optoelectronic-Scanner). The aim of this data processing system is to reduce the data stream from the satellite due to generations of thematic maps. This reduction will be made by a multispectral classification. For this classification a special hardware based on the neural network processor NI1000 was designed. This hardware is integrated in the payload data handling system of the satellite.
Advances in hyperspectral sensor technology increasingly provide higher resolution and higher quality data for the accurate generation of terrain categorization/classification (TERCAT) maps. The generation of TERCAT m...
详细信息
ISBN:
(纸本)0819454966
Advances in hyperspectral sensor technology increasingly provide higher resolution and higher quality data for the accurate generation of terrain categorization/classification (TERCAT) maps. The generation of TERCAT maps from hyperspectral imagery can be accomplished using a variety of spectral pattern analysis algorithms;however, the algorithms are sometimes complex, and the training of such algorithms can be tedious. Further, hyperspectral imagery contains a voluminous amount of data with contiguous spectral bands being highly correlated. These highly correlated bands tend to provide redundant information for classification/feature extraction computations. In this paper, we introduce the use of wavelets to generate a set of Generalized Difference Feature Index (GDFI) measures, which transforms a hyperspectral image cube into a derived set of GDFI bands. A commonly known special case of the proposed GDFI approach is the Normalized Difference Vegetation Index (NDVI) measure, which seeks to emphasize vegetation in a scene. Numerous other band-ratio measures that emphasize other specific ground features can be shown to be a special case of the proposed GDFI approach. Generating a set of GDFI bands is fast and simple. However, the number of possible bands is capacious and only a few of these "generalized ratios" will be useful. Judicious data mining of the large set of GDFI bands produces a small subset of GDFI bands designed to extract specific TERCAT features. We extract/classify several terrain features and we compare our results with the results of a more sophisticated neural network feature extraction routine.
We introduce a set-based approach for estimating image motion based on an optical flow constraint and a finite number of arbitrary differential constraints describing physically plausible vector fields. Compared to re...
详细信息
We introduce a set-based approach for estimating image motion based on an optical flow constraint and a finite number of arbitrary differential constraints describing physically plausible vector fields. Compared to related variational estimation approaches, our approach strictly satisfies each separate constraint and becomes not more involved in the presence of higher-order differential operators. The approach is implemented using established subgradient projection schemes onto the set of feasible solutions. Our approach is particularly suited if quantitative prior knowledge about structural flow properties is available, and for the regularized estimation of highly non-rigid image motion.
Similarity measure is usually used to study the method for guiding to select a similarity measure or a dissimilar degree between multi-source data, which is the basis of patternrecognition on spatial data. For it is ...
详细信息
ISBN:
(纸本)0780385675
Similarity measure is usually used to study the method for guiding to select a similarity measure or a dissimilar degree between multi-source data, which is the basis of patternrecognition on spatial data. For it is the core technique in content-based image retrieval, similarity measure has very wide applications. In this work eight similarity measures are experimental investigated through some remotesensingimage retrieval. The features extracted in the experiments are frequency histogram and cumulative histogram vectors. From the experiment results it can be found that X/sup 2/ statistical distance measure and cosine of the angle measure perform better than others. The results described in This work are of significance in applications to multi-source data analysis.
Recent advancements in sensors, wireless technology, and a reduction in the form factor of computing devices, provide the realization of true autonomy in mobile sensing systems. Past field-deployable sensing systems f...
详细信息
Recent advancements in sensors, wireless technology, and a reduction in the form factor of computing devices, provide the realization of true autonomy in mobile sensing systems. Past field-deployable sensing systems for health-biomedical applications and even environmental sensing have been designed for data collection and data transmission at pre-set intervals, rather than for on-board processing. This lack of true autonomy has resulted in systems with lower lifetimes and those that require large amounts of bandwidth to transmit all sensory data at all times. The use of a new, general machine learning architecture that can be used for a variety of autonomous sensing applications that have very limited computing, power, and bandwidth resources is proposed in this paper. The general solutions for efficient processing in a multi-tiered (three-tier) machine learning framework that is suited for remote, mobile sensing systems with low computing capabilities is provided. Simple patternrecognition methods are used at the sensor level to filter significant events. Novel dimensionality reduction techniques that are designed for classification are used to compress each individual sensor data and pass only relevant information to the mobile multisensor fusion module (second-tier). Statistical classifiers that are capable of handling missing/partial sensory data due to sensor failure or power loss are used to detect critical events and pass the information to the third tier (central server) for manual analysis and/or analysis by advanced patternrecognition techniques. The applicability of the proposed technology in mobile health & alcohol monitoring is shown. Other uses of the provided solutions are also discussed.
暂无评论