A new approach to unsupervised texture segmentation is represented. The method is based on a local texture measure, a Grey Tone Spatial Dependence Matrix. The randomly sampled local measures self-organize to a topolog...
详细信息
In this paper, a Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated. This scheme is a region-based approach in which an image is first segmented into a colle...
详细信息
In this paper, a Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated. This scheme is a region-based approach in which an image is first segmented into a collection of disjoint regions that form the nodes of an adjacency graph. Once the adjacency graph has been determined, image interpretation is achieved through assigning object labels (or interpretations) to the segmented regions (or nodes) using domain knowledge, extracted feature measurements, and spatial relationships between the various regions. In this approach, the interpretation labels are modeled as an MRF on the corresponding adjacency graph, and the image interpretation problem is then formulated as a maximum a posteriori (MAP) estimation rule given domain knowledge and region-based measurements. Simulated annealing is used to find this best realization or optimal MAP interpretation. Through the MRF model and its associated Gibbs distribution, this approach also provides a systematic method for organizing and representing domain knowledge through appropriate design of the clique functions describing the Gibbs distribution representing the pdf of the underlying MPF. We provide a general methodology for the design of the clique functions. Results of image interpretation experiments performed on synthetic and real-world images using this approach are described.
Two methods of automating the process of ocean feature tracking for estimating surface currents in coastal areas are outlined. These methods involve patternrecognition and have certain advantages over the more famili...
详细信息
Two methods of automating the process of ocean feature tracking for estimating surface currents in coastal areas are outlined. These methods involve patternrecognition and have certain advantages over the more familiar maximum cross-correlation technique of Emery et al. (1986). The first method requires three steps in its application, pattern selection, patternrecognition and geometrical calculations to determine both the cross- and the along-isotherm displacements. The second method calculates certain surface motion parameters including rotation and translation in Hough parameter space. Each method is applied to sequential AVHRR IR satellite imagery off the U.S. east coast. Finally, some of the practical problems encountered in the application of these methods are described.
Present remotesensing systems are capable of producing digital image data at rates which far exceed the exploitation capabilities of existing processing systems. Automated image classification and interpretation tool...
详细信息
ISBN:
(纸本)0819409391
Present remotesensing systems are capable of producing digital image data at rates which far exceed the exploitation capabilities of existing processing systems. Automated image classification and interpretation tools are necessary to optimize the use of remotely sensed multispectral imagery. We have investigated the use of artificial neural networks (ANN) for spectral patternrecognition in multispectral imagery for both polarimetric synthetic aperture radar (SAR) and Landsat Thematic Mapper (TM) data. We have used ANN to segment SAR and TM scenes into a few broad land use/land cover (LU/LC) types (e.g., vegetation, bare soil, water, etc.). We believe that these broad landuse classes can be subclassified further into more refined types (e.g., vegetation, class can be partitioned into different vegetation types) using spectral information, spatial shape indicators, and contextual image information such as texture.
Computer vision and image understanding processes are not very robust; small changes in exposure parameters or in internal parameters of algorithms can lead to significantly different results. A combination (fusion) o...
详细信息
Computer vision and image understanding processes are not very robust; small changes in exposure parameters or in internal parameters of algorithms can lead to significantly different results. A combination (fusion) of these results is profitable. The authors introduce an extended fusion concept dealing with different sources of information at external (world, scene, image) and internal (image description, scene description) levels and define the process of fusion. Each level requires its own procedure of quality measure and information fusion in order to yield a combination of components from several sources. Related work in the field is reviewed. Examples from the authors' own work cover remotesensing (improvement of classification results by fusion at the image level), medical imageprocessing of ocular fundus images (automatic control point selection by fusion at the image description level) and the interpretation of Billard scenes (object identification by fusion at the scene description level).< >
In the field of remotesensing (RS) image classification, pattern indeterminacy due to inherent data variability is always present. Class mixture, too, is a serious handicap to conventional classifiers in order to set...
详细信息
ISBN:
(纸本)0819409391
In the field of remotesensing (RS) image classification, pattern indeterminacy due to inherent data variability is always present. Class mixture, too, is a serious handicap to conventional classifiers in order to settle proper class patterns. Fuzzy classification techniques improve the extraction of information yielded by conventional methods, i.e., statistical classification procedures, because both in the design of the classifier and when bringing out classification results, natural fuzziness present in real-world recognition processes is considered. This paper presents first the application of a fuzzy classification algorithm from Kent and Mardia to RS images, along with the analysis of the results and comparison against `hard' classifications. Secondly, we put forward one particular method to display these results (fuzzy partitions) by coding pixels' membership into a pseudocolor representation. This representation is intended to serve as an interface between fuzzy coefficients resulting from the classification process and a very natural way for humans to perceive information such as that of color mixtures.
We investigate the performance of selected texture models for the purpose of land use classification. The texture models are evaluated based on the resulting classification error rates. Three classes of texture models...
详细信息
Due to the low resolution of Landsat images and the multiplicity of the terrain, it is improper to classify each pixel in a Landsat image to one of land cover types by using the conventional remotesensing classificat...
详细信息
Due to the low resolution of Landsat images and the multiplicity of the terrain, it is improper to classify each pixel in a Landsat image to one of land cover types by using the conventional remotesensing classification methods. The concept of fuzzy sets provides a flexible approach to resolve this problem. This paper presents a new two-pass mode unsupervised clustering algorithm incorporated with the underlying fuzzy theory. In the first pass the mean vectors representing the geographic attributes or the land cover types are derived. The second pass is based on the fuzzy theory. That is the mean vectors obtained are used to generate a membership function. The grade of memberships for each pixel with respect to various land cover types is computed according to the distance from the pixel to all the clusters' mean vector.
＜正＞It is very difficult for the traditional patternrecognition methods toprovide satisfactory classification performance in remotesensingpattern *** Neural Networks such as Multi-layered Net can achieve certain ...
＜正＞It is very difficult for the traditional patternrecognition methods toprovide satisfactory classification performance in remotesensingpattern *** Neural Networks such as Multi-layered Net can achieve certain improvement in this *** the remotesensingimage data is complicated and of high dimension,in this paper we discuss upon how to construct proper High-order Net to capture the high order internal structure representation of the pattern features in some direct *** results in simplified training strategies and high training ***,the classification precision of High-order Net is remarkably higher than that of Maximum Likelihood Estimation and Multi-layered BP Net.
暂无评论