检索结果-内蒙古大学图书馆

International Conference on Information Fusion

作者： M.G. Mostafa A.A. Farag E. Essock Department of Electrical and Computer Engineering Computer Vision and Image Processing Laboratory University of Louisville Louisville KY USA Department of Psychology University of Louisville Louisville KY USA

Multi-modality image registration and fusion are essential steps in building 3D models from remote sensing data. In this paper, we present a neural network technique for the registration and fusion of multi-modality remote sensing data for the reconstruction of 3D models of terrain regions. A feedforward neural network is used to fuse the intensity data sets with the spatial data set after learning its geometry. Results on real data are presented. Human performance evaluation is assessed on several perceptual tests in order to evaluate the fusion results.

关键词： image registration Neural networks Hyperspectral sensors remote sensing image reconstruction Geometry remote monitoring Intelligent sensors Satellites Laser radar

来源：评论

学校读者我要写书评

暂无评论

Unsupervised seed determination for a region-based color image segmentation scheme

Unsupervised seed determination for a region-based color ima...

引用

IEEE International Conference on image processing

作者： N. Ikonomakis K.N. Pataniotis A.N. Venetsanopoulos Department of Electrical and Computer Engineering Digital Signal & Image Processing Laboratory University of Toronto Toronto ONT Canada University of Toronto Toronto ON CA

ISBN: (纸本)0780362977

A color image segmentation technique is presented for use in coding and/or compression of video-conferencing sequences. The proposed technique utilizes the perceptual HSI (hue, saturation, intensity) color space and incorporates an unsupervised seed determination algorithm that finds the seed pixels that are in the spatial center of the regions in the image. The algorithm employs a hierarchy system where seeds found at the highest level produce the best results. The region growing algorithm uses these seeds to grow regions by appending to each seed pixel those neighboring pixels that satisfy a certain homogeneity criterion. The technique is found to be robust and relatively computationally inexpensive. The effectiveness of the algorithm is found to be much improved over techniques used in the past.

关键词： Color image segmentation Pixel image coding image converters Signal processing image processing Laboratories Robustness Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Volume-imaging UHF radar measurement of atmospheric turbulence

Volume-imaging UHF radar measurement of atmospheric turbulen...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Jie Li F.J. Lopez-Dekker T. Ince S.J. Frasier Microwave Remote Sensing Laboratory Department of Electrical & Computer Engineering University of Massachusetts Amherst MA USA University of Massachusetts Amherst Amherst MA US

The Turbulent Eddy Profiler (TEP) is a volume-imaging 915 MHz radar designed for atmospheric boundary layer turbulence studies. TEP is a pulsed, phased-array radar using digital beamforming techniques to provide four-dimensional images of refractive index fluctuations and wind vectors on grid scales comparable to those of large-eddy simulations. During October 1999, TEP was deployed during the Cooperative Atmospheric Surface Exchange Study (CASES'99) held near Wichita, KS. The authors present observations from this experiment which focused on the evolution and dynamics of the stably-stratified nocturnal boundary layer. Unlike the convective boundary layer, radar echoes are characterized by intermittent bursts of shear-induced turbulence. The scales of turbulence features are generally smaller than the resolution of the UHF radar. This is demonstrated by comparison with a co-located S-band FMCW radar. Estimation of turbulence intensity is also complicated by the presence of significant bird and insect scatter.

关键词： Radar measurements Phased arrays Radar imaging Radar remote sensing Calibration Laboratories Array signal processing Atmospheric modeling Spatial resolution Electromagnetic heating

来源：评论

学校读者我要写书评

暂无评论

A rate-distortion approach to wavelet-based encoding of predictive error frames

A rate-distortion approach to wavelet-based encoding of pred...

引用

IEEE International Conference on image processing

作者： E. Asbun P. Salama E.J. Delp Video and Image Processing Laboratory School of Electrical and Computer Engineering Purdue University West Lafayette IN USA Department of Electrical and Computer Engineering Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis Indianapolis IN USA

We develop a framework for efficiently encoding predictive error frames (PEF) as part of a rate scalable, wavelet-based video compression algorithm. We investigate the use of rate-distortion analysis to determine the significance of coefficients in the wavelet decomposition. Based on this analysis, we allocate the bit budget assigned to a PEF to the coefficients that yield the largest reduction in distortion, while maintaining the embedded and rate scalable properties of our video compression algorithm.

关键词： Rate-distortion Encoding image coding Video compression computer errors Redundancy Wavelet analysis Decoding Scalability Transform coding

来源：评论

学校读者我要写书评

暂无评论

Design tradeoffs in a hardware implementation of the k-means clustering algorithm

Design tradeoffs in a hardware implementation of the k-means...

引用

Sensor Array and Multichannel Signal processing Workshop

作者： M. Leeser J. Theiler M. Estlick J.J. Szymanski Department of Electrical and Computer Engineering Northeastern University Boston MA USA Space and Remote Sensing Sciences Group Los Alamos National Laboratory Los Alamos NM USA

Hyperspectral imagery provides exquisitely detailed information but poses a serious challenge to the image analyst. Massive quantities of data must be reduced in a way that identifies useful features. Pixel clustering algorithms provide one approach: each pixel is assigned to a class based on the spectral similarity of that pixel to other members of the class. An image where each pixel is represented by its class provides a single picture (not hundreds of channels) for the analyst to interpret. Opportunities for fine-grain parallelism in this computationally intensive calculation motivate the consideration of specialized hardware. We are developing an FPGA-based implementation of the k-means clustering algorithm, because FPGAs can provide considerable speedup yet are sufficiently flexible to permit the testing of variants and tradeoffs. Assigning pixels to classes requires a definition of spectral similarity. The standard choice is the Euclidean distance. We consider two alternative distances: the Manhattan (sum of the absolute coordinate differences) and the Max (maximum of the absolute differences). The Euclidean distance is optimal in the sense of minimizing within-class variance, but requires computing many squares. The Manhattan and Max distances eliminate this squaring, and furthermore reduce the number of bits needed to store intermediate calculations. We conducted two sets of experiments to assess the tradeoff between quality of clustering and efficiency of hardware implementation. The first considered an idealized setup for assessing mis-classification rates and their effect on within-class variance. The second evaluated within-class variance for real 224-channel AVIRIS data sets. Both experiments confirmed that the highest quality clusters are achieved using the Euclidean metric, and quantified the difference.

关键词： Hardware Euclidean distance image analysis Clustering algorithms Hyperspectral sensors Hyperspectral imaging Information analysis Pixel Parallel processing Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

Focusing of synthetic aperture radar images of moving targets using minimum entropy adaptive filters

Focusing of synthetic aperture radar images of moving target...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： D. Kasilingam Junfeng Wang Jong-Sen Lee R. Jensen Department of Electrical and Computer Engineering University of Massachusetts Dartmouth MA USA Remote Sensing Division Naval Research Laboratory Inc. Washington D.C. DC USA

Synthetic aperture radar (SAR) imaging systems are used for generating high-resolution images for target detection and identification. However, when imaging moving targets, the imaging process is degraded by target motion. These effects generally manifest as a form of smearing in the azimuthal direction. Since the motion parameters are generally not known, it requires a processing technique that can estimate the motion information from the SAR measurements and use these estimates to reconstruct the image. Adaptive filters are well suited to do this. In this study, an adaptive technique based on the minimum entropy filter is developed to minimize the effect of smearing in SAR images of moving targets. The minimum entropy filter utilizes the entropy function as the cost function to be optimized. The use of the minimum entropy filter with simulated SAR measurements of moving targets clearly shows significant improvement in the image quality when the entropy function is optimized. The filters were tested on images of targets with many different motion parameters. The minimum entropy filter consistently produced the best motion compensation. The filters were also tested with field images of ships obtained from a C-band, SAR flown over the coast of Denmark. The filter was able to adaptively reduce the effects of azimuthal smearing.

关键词： Focusing Entropy High-resolution imaging Adaptive filters Motion estimation Testing Synthetic aperture radar image generation Object detection Degradation

来源：评论

学校读者我要写书评

暂无评论

Ocean wave slope spectra from polarimetric SAR images of the ocean surface

Ocean wave slope spectra from polarimetric SAR images of the...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： D. Kasilingam Honglei Chen D. Schuler J.-S. Lee Department of Electrical and Computer Engineering University of Massachusetts Dartmouth North Dartmouth MA USA Remote Sensing Division Naval Research Laboratory Inc. Washington D.C. DC USA

Fully-polarimetric SAR measurements have been used successfully to estimate the slopes of natural surfaces in the azimuth direction. The primary thrust of these previous studies has been the use of polarimetric measurements to generate digital elevation maps (DEM) of terrain. In this study, fully-polarimetric SAR measurements of ocean waves from NASA/JPL's AIRSAR are used to estimate the azimuth wave slopes of surface waves. These slope estimates are then used to generate wave slope spectra. The technique follows the approach developed by Schuler and Lee for estimating DEMs. Since the wave slope measurements are small and are extremely sensitive to errors, different algorithms for estimating the slopes were investigated. In addition to this technique for estimating the azimuth wave slopes, a new processing technique is developed for using polarimetric SAR measurements for estimating the range directed wave slopes. The range slope estimates are obtained by using the phase difference between the HH and VV complex images. Initial results indicate that this technique may help to 'fill-in' the spectrum for wave components traveling close to the range direction. The slope spectra derived from the fully-polarized, signatures appear to agree well with the slope spectra derived from the image spectra.

关键词： Ocean waves Surface waves Sea surface Sea measurements Azimuth Polarization Rough surfaces Surface roughness remote sensing Phase estimation

来源：评论

学校读者我要写书评

暂无评论

On the joint use of QSCAT and QRAD over the Arctic and Antarctic oceans

On the joint use of QSCAT and QRAD over the Arctic and Antar...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： R. Ezraty W. Lindwood Jones J. Zec Département d Océanographie Spatiale IFREMER Centre de Brest Plouzane France Central Florida Remote Sensing Laboratory Electrical and Computer Engineering Department University of Central Florida FL

On an individual orbit basis, QSCAT data does not permit an efficient separation of sea ice from open water. It is shown how the use of the simultaneous H-pol temperatures provided by the radiometer-like processing of... 详细信息

关键词： Arctic Antarctica Oceans Sea ice Radiometry Radar measurements Polarization Extraterrestrial measurements Sea measurements Measurement standards

来源：评论

学校读者我要写书评

暂无评论

Polarization and look-direction dependencies observed in radar imagery of the Chesapeake Bay Outflow Plume front

Polarization and look-direction dependencies observed in rad...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： M.A. Sletten E. Twarog D.J. McLaughlin X. Zhang G. Marmorino Remote Sensing Division Naval Research Laboratory Inc. Washington D.C. DC USA Northeastern University Boston MA USA Department of Electrical and Computer Engineering University of Massachusetts Amherst MA USA

In May 1997 and May 1999, the remote sensing Division of the Naval Research laboratory conducted phases Two and Five of the Chesapeake Bay Outflow Plume Experiment (COPE2 and COPE5, respectively). In both experiments, an airborne, X-band, real-aperture radar was used to image the outflow plume front that forms in the mouth of the Chesapeake Bay. On an interleaved, pulse-to-pulse basis, both horizontally and vertically polarized imagery was collected. In COPE5, backscatter intensity were observed polarization when the look direction and grazing angle were varied, with the largest across-the-front backscatter contrast occurring at an 80 degree incidence angle when a landward look direction was used. The strongest backscatter was observed on the continental shelf side, regardless of look direction. In COPE2, large contrasts in backscatter intensity were also observed for horizontal polarization, but the look dependency was reversed: larger contrasts were observed when a seaward look direction was used, and the strongest backscatter was observed on the plume-side of the front. In this paper, these observations will be quantified, and an explanation for this interesting behavior will be given that involves the interaction of wind waves and opposing currents.

关键词： Polarization Radar imaging Backscatter Rough surfaces Surface roughness Radar remote sensing remote sensing Laboratories Surface waves Pulse modulation

来源：评论

学校读者我要写书评

暂无评论

Kalman filtering approach to multispectral/hyperspectral image classification

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 1999年第1期35卷 319-330页

作者： Chang, CI Brumbley, C IEEE Remote Sensing Signal and Image Processing Laboratory Dept. of Computer Science and Electrical Engineering University of Maryland Baltimore County

Linear unmixing is a widely used remote sensing image processing technique for subpixel classification and detection where a scene pixel is generally modeled by a linear mixture of spectral signatures of materials present within the pixel. tin approach, called linear unmixing Kalman filtering (LUKF), is presented which incorporates the concept of linear unmixing into Kalman filtering so as to achieve signature abundance estimation, subpixel detection and classification for remotely sensed images. Zn this case, the linear mixture model used in linear unmixing is implemented as the measurement equation in Kalman filtering. The state equation which is required for Kalman filtering but absent in linear unmixing is then used to model the signature abundance. By utilizing these two equations the proposed LUKF not only can detect abrupt change in various signature abundances within pixels, but also can detect and classify desired target signatures. The performance of effectiveness and robustness of the LUKF is demonstrated through simulated data and real scene images, Satellite Pour l'Observation de la Terra (SPOT) and Hyperspectral Digital imagery Collection (HYDICE) data.

关键词： .Baltimore County abundance image classification Equation image processing unmixing Kalman filtering SUBPIXEL spectral signatures Linear Mixture Model HYDICE LUKF

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：