The authors present a novel neural network model for visual information processing. The model uses a hierarchical network with local connectivity as a stem network. This network generates hypotheses about the expected...
详细信息
The authors present a novel neural network model for visual information processing. The model uses a hierarchical network with local connectivity as a stem network. This network generates hypotheses about the expected image content, and then selectively uses small neural network modules on parts of the image to check these hypotheses. The resulting neural network is able to use different spatial resolutions, and is both modular and hierarchical. Applying this model to remotely sensed image classification (Landsat TM) is described. A slightly better classification accuracy was achieved at reduced computational cost, compared to classification without the model.< >
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
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 topological feature map. The topological feature map is used as a set of reference vectors later on when the whole image is processed in raster scan manner by the local texture measurement. The label of a region is the address on the topological feature map. The interpretation of a label is given by identified samples. The method has been applied in segmentation of remotesensingimages and aerial photographs.< >
The paper describes the results of a programme of research aimed at developing a mechanism for identifying and describing particular cloud patterns in weather satellite images. The ability to automatically track a def...
详细信息
The paper describes the results of a programme of research aimed at developing a mechanism for identifying and describing particular cloud patterns in weather satellite images. The ability to automatically track a defined cloud formation across a time sequence of images would be very useful in the prediction of wind speed and direction, and the ability to register the way in which a cloud formation evolves with time would support forecasts of future weather events. The application of such techniques is not limited to weather satellite images, however, but can also be used in other fields, such as medical imaging, where non-static images are also to be found.< >
Navigation and imagery in the orbit, descent, and landing phases during an interplanetary mission require methods that are able to derive the elevation map of a planetary body using remotesensing tools. The authors p...
详细信息
Navigation and imagery in the orbit, descent, and landing phases during an interplanetary mission require methods that are able to derive the elevation map of a planetary body using remotesensing tools. The authors propose stereovision techniques for this task. An algorithm for correspondence matching, which is one of the crucial steps in automatic terrain modeling, is introduced. It uses well known pyramid-based data structures, but is novel in its direct application of methods from statistical patternrecognition. Feature vectors for correspondence matching and feature selection techniques are used to find optimal features. These include grey-level statistics (mean variance) as well as more sophisticated features derived from operators like local frequency edge gradient or, as an extension, Moravec-, Gabor- or Fourier-features. The applicability of the algorithm in the remotesensing scenario of interplanetary missions is verified using a mockup simulation of the Martian surface.< >
A method is presented to remove noise from images as a preprocessing step for segmentation. It is based on the analysis of the slope of the gradient profile in a moving window after sorting its elements. By classifyin...
详细信息
A method is presented to remove noise from images as a preprocessing step for segmentation. It is based on the analysis of the slope of the gradient profile in a moving window after sorting its elements. By classifying the slope segments, rules can be applied for smoothing. These rules can be adapted for edge preservation.< >
A classification method for IRS (Indian remotesensing Satellite) images is presented. The image is segmented into six classes using minimum distance classifier where the centres are chosen on the basis of spectral kn...
详细信息
A classification method for IRS (Indian remotesensing Satellite) images is presented. The image is segmented into six classes using minimum distance classifier where the centres are chosen on the basis of spectral knowledge of the corresponding classes. Two bands (green and infrared) have been used for classification. The results are presented in the form of photographs.< >
Presents a scene interpretation architecture in the context of multi-sensor fusion. This architecture is based on blackboard and multi-specialist concepts, and offers knowledge representation capabilities to express k...
详细信息
Presents a scene interpretation architecture in the context of multi-sensor fusion. This architecture is based on blackboard and multi-specialist concepts, and offers knowledge representation capabilities to express knowledge about an application in an explicit way. Knowledge description includes the characteristics of the sensors, and a semantic object description independent of the sensor characteristics. The detection strategy is based on the fundamental notion of spatial context linking the objects of the scene, and the notion of salient object. An interpretation is a semantic model of the real observed scene, including object location, object characteristics and relations between objects. This architecture has a highly modular structure allowing easy incorporation of new knowledge, and new specialists. To demonstrate the reliability of the approach, an application of SAR/SPOT data fusion developed with this architecture is briefly presented, and the results of an interpretation session are shown.< >
Presents the study of the sensibility, relative error and error probability of projective invariants of planar objects. The study is applied to configurations of groups of five points which define a planar object. The...
详细信息
Presents the study of the sensibility, relative error and error probability of projective invariants of planar objects. The study is applied to configurations of groups of five points which define a planar object. The results are general for any type of projective invariant. The paper shows that given the precision (or tolerance) and the maximum allowed error probability, the sensibility and relative error can be used to decide the correct configurations for the matching procedure between the model and the projective view of a physical object. The last result is general for any type of geometric invariant.< >
There have been many new developments in neural network (NN) research, and many new applications have been studied. The classification of remotely sensed multispectral data using classical statistical methods has been...
详细信息
There have been many new developments in neural network (NN) research, and many new applications have been studied. The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Among the multispectral data, we concentrate on the Landsat-5 Thematic Mapper (TM) image data which has been available since 1984. Using this classical maximum likelihood approach, a category is modeled as a multivariate normal distribution; however, the distribution for Landsat images is unknown. It is well known that NN approaches have the ability to classify without assuming a distribution. We apply the NN approach to the classification of Landsat TM images in order to investigate the robustness of this approach for multi-temporal data classification. The authors confirmed that the NN approach is effective for the classification even if the test data is taken at the different time.< >
In this work we apply a texture classification network to remotesensingimage analysis. The goal is to extract the characteristics of the area depicted in the input image, thus achieving a segmented map of the region...
ISBN:
(纸本)9781558602748
In this work we apply a texture classification network to remotesensingimage analysis. The goal is to extract the characteristics of the area depicted in the input image, thus achieving a segmented map of the region. We have recently proposed a combined neural network and rule-based framework for texture recognition. The framework uses unsupervised and supervised learning, and provides probability estimates for the output classes. We describe the texture classification network and extend it to demonstrate its application to the Landsat and Aerial image analysis domain.
暂无评论