检索结果-内蒙古大学图书馆

MULTIPLE KERNEL RELEVANCE VECTOR MACHINE FOR geospatial OBJECTS DETECTION IN HIGH-RESOLUTION REMOTE SENSING IMAGES

Journal of Electronics(China) 2012年第5期29卷 353-360页

作者： Li Xiangjuan Sun Xian Wang Hongqi Li Yu Sun Hao Institute of Electronics Chinese Academy of Sciences Key Laboratory of Technology in Geo-spatial Information Processing and Application System Graduate University Chinese Academy of Sciences

geospatial objects detection within complex environment is a challenging problem in remote sensing area. In this paper, we derive an extension of the Relevance Vector Machine (RVM) technique to multiple kernel version. The proposed method learns an optimal kernel combination and the associated classifier simultaneously. Two feature types are extracted from images, forming basis kernels. Then these basis kernels are weighted combined and resulted the composite kernel exploits interesting points and appearance information of objects simultaneously. Weights and the detection model are finally learnt by a new algorithm. Experimental results show that the proposed method improve detection accuracy to above 88%, yields good interpretation for the selected subset of features and appears sparser than traditional single-kernel RVMs.

关键词： Object detection Feature extraction Relevance Vector Machine (RVM) Support Vector Machine (SVM) Sliding-window

来源：评论

学校读者我要写书评

暂无评论

Investigations of the dynamics of road pavement reflectance

引用

Chinese Optics Letters 2012年第4期10卷 58-62页

作者：姜亢于凯赵永超 Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Institute of ElectronicsChinese Academy of Sciences Graduate University of Chinese Academy of Sciences

Road pavement reflectance is usually assumed to be invariant in short periods of time in some quantitative remote sensing *** examine its variability,reflectance sequences of concrete and asphalt pavement are measured in field for half a day in visible and near-infarecd（VNIR）spectral range using dual-beam *** much as 20.7%and 3.52%of relative changes are found in asphalt and concrete reflectance data at 550 nm,and all VNIR bands demonstrate similar variations found to correlate with both illumination geometry and the relative portion of diffuse *** this letter,this effect is interpreted from a mathematic *** studies are needed to model the dynamics of reflectance physically.

关键词： Dynamics Remote sensing Roads and streets

来源：评论

学校读者我要写书评

暂无评论

TOPOGRAPHIC CORRECTION OF ETM IMAGES BASED ON SMOOTHED TERRAIN

引用

Journal of Electronics(China) 2012年第3期29卷 271-278页

作者： Jiang Kang Zhao Yongchao Geng Xiurui Tang Hairong Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Beijing 100100China Institute of Electronics Chinese Academy of SciencesBeijing 1001P0China Graduate University Chinese Academy of SciencesBeijing 100040China

A new empirical topographic correction method is proposed in this paper. The main idea of the new method is smoothing the slope angle of terrain in the first place and then performing the cosine correction based on the smoothed terrain. A comparison is conducted among the new method and several other common methods using Landsat-7 ETM+ data. Visual analysis and statistical analysis are adopted to assess the performance of these methods from two aspects: overcorrection, homogeneity within a land cover class. Comparison results indicate that the new method is superior to the cosine correction, Gamma correction, Sun-Canopy-Sensor correction, and Minnaert correction. Compared with common methods, the proposed one can eliminate overcorrection better and is an effective topographic correction method.

关键词： Topographic correction Landsat-7 ETM Smoothed terrain

来源：评论

学校读者我要写书评

暂无评论

HIGH-ACCURACY BAND TO BAND REGISTRATION METHOD FOR MULTI-SPECTRAL IMAGES OF HJ-1A/B

引用

Journal of Electronics(China) 2012年第5期29卷 361-367页

作者： Lu Hao Liu Tuanjie Zhao Haiqing Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Institute of Electronics Chinese Academy of Sciences Graduate University of Chinese Academy of Sciences No. 27 Institute of China Electronics Technology Group Corporation

Band-to-band registration accuracy is an important parameter of multispectral data. A novel band-to-band registration approach with high precision is proposed for the multi-spectral images of HJ-1A/B. Firstly, the main causes resulted in misregistration are analyzed, and a high-order polynomial model is proposed. Secondly, a phase fringe filtering technique is employed to Phase Correlation Method based on Singular Value Decomposition (SVD-PCM) for reducing the noise in phase difference matrix. Then, experiments are carried out to build nonlinear registration models, and images of green band and red band are aligned to blue band with an accuracy of 0.1 pixels, while near infrared band with an accuracy of 0.2 pixels.

关键词： Band-to-band registration Phase correlation Singular Value Decomposition (SVD) Phase fringe filtering HJ-1A/B

来源：评论

学校读者我要写书评

暂无评论

REVERSE-RANGE-DOPPLER METHOD FOR AUTOMATED geoCODING SAR IMAGES

引用

Journal of Electronics(China) 2012年第3期29卷 242-247页

作者： Liu Jiayin Hong Wen Key Laboratory of Technology on Geo-spatial Information Processing and Application System Chinese Academy of SciencesBeijing 100190China National Key Laboratory of Microwave Imaging Technology Beijing 100190China Institute of Electronics Chinese Academy of SciencesBeijing 1001q0China

Range-Doppler (RD) method and Reverse-Range-Doppler (RRD) method are combined together to achieve automatic geocoding of Synthetic Aperture Radar (SAR) image quickly and accurately in the paper. The RD method is firstly used to locate the four corners of the image, then the other pixels of the image can be located by Reverse-Range-Doppler (RRD) method. Resampling is performed at last. The approach has an advantage over previous techniques in that it does not require ground control points and is independent of spacecraft attitude knowledge or control. It can compensate the shift due to the assumed Doppler frequency in SAR image preprocessing. RRD simplifies the process of RD, therefore speeds up the computation. The experimental results show that a SAR image can be automated geocoded in 30 s using the single CPU (3 GHz) with 1 G memory and an accuracy of 10 m is attainable with this method.

关键词： Range-Doppler (RD) Reverse-Range-Doppler (RRD) geolocation Automated geocoding Space-borne Synthetic Aperture Radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A METHOD OF AIRBORNE INSAR DEM RECONSTRUCTION IN LAYOVER AREAS

A METHOD OF AIRBORNE INSAR DEM RECONSTRUCTION IN LAYOVER ARE...

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Fangfang LI Bing HAN Xue LIN Donghui HU Chibiao DING Key Laboratory of Geo-Spatial Information Processing and Application System Technology Chinese Academy of Sciences

ISBN: (纸本)9781467311601

The layover phenomenon of SAR imaging arises when different height contributions collapse in the same range-azimuth resolution cell, due to the presence of strong terrain slopes or discontinuities in the scenarios. Because of the phase discontinuities, for single baseline interferometric SAR, it is difficult to recover the accurate unwrapped phase in layover areas by traditional phase unwrapping methods. In this paper, according to the phase characteristic of layover areas, we propose a new method to retrieve unwrapped phase based on local frequency estimate. It can avoid the unwrapping error resulted from the phase jump at the edge of layover areas. As a result, relative accurate DEM of layover areas can be reconstructed, which is beneficial to afterward geocoding in InSAR topographic mapping.

关键词： SAR interferometry Layover Interferometric phase DEM reconstruction Local frequency estimate phase step resolution cell local frequency Synthetic aperture radar discontinuities Phase indium Radar polarimetry geocoding Topographic Mapping Reconstructions PHASE LAG CHARACTERISTIC

来源：评论

学校读者我要写书评

暂无评论

MEDIUM-EARTH-ORBIT SAR IMAGING BASED ON keySTONE TRANSFORM AND AZIMUTH PERTURBATION

MEDIUM-EARTH-ORBIT SAR IMAGING BASED ON KEYSTONE TRANSFORM A...

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Lijia HUANG Bing HAN Donghui HU Chibiao DING Lihua ZHONG Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences

ISBN: (纸本)9781467311601

Due to the significant azimuth variance property in medium-Earth-orbit (MEO) synthetic aperture radar (SAR) echo, it is difficult for the conventional SAR algorithms to achieve a good compromise between accuracy and efficiency. A novel algorithm based on keystone transform (KT) and azimuth perturbation (AP) is introduced in this paper to handle this problem. The function of KT is to correct the range walk and thus to mitigate the azimuth variance effect on range processing. The function of AP is to equalize the Doppler histories in each range gate and thus to mitigate the azimuth variance effect on azimuth compressing. Simulation results of an L-band MEO SAR with 5 m resolution at 10,000 km altitude demonstrate the capability of our algorithm.

关键词： Azimuth perturbation (AP) keystone transform (KT) Medium-Earth-orbit (MEO) SAR SAR data processing Synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A new endmember extraction algorithm by maximum ASC fraction

A new endmember extraction algorithm by maximum ASC fraction

引用

Workshop on Hyperspectral Image and Signal processing: Evolution in Remote Sensing, WHISPERS

作者： Luyan Ji Xiurui Geng Yongchao Zhao Key Laboratory of Technology in Geo-spatial information Processing and Application System Chinese Academy of Science Beijing China

This paper presents a new simplex-based method for unsupervised endmember extraction, called maximum abundance sum-to-one constraint (ASC) fraction (MAF). The ASC fractions refer to the spectral unmixing results with the abundance sum-to-one constraint unmixing only. The algorithm assumes the existence of the pure pixels in the input data for every endmember in the scene, and exploits the fact that pixels with maximum ASC fractions are corresponding to the vertices of a simplex. In order to demonstrate the performance of the proposed MAF, the N-findr algorithm (N-FINDR) and vertex component analysis (VCA) based merely on PCA dimensional reduction are used for comparison. Experiments using both simulated and real hyperspectral data show that MAF is effective in searching optimal results, with a low computational complexity.

关键词： Abstracts Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Multi-scale semantic model for unsupervised object segmentation

引用

2012 2nd International Conference on Materials Science and information technology, MSIT 2012

作者： Li, Yu Li, Xiangjuan Zhang, Yasen Sun, Xian Wang, Hongqi Institute of Electronics Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783037854389

It is difficult to segment instances of object classes accurately unsupervised in images, because of the complexity of structures, inter-class differences, background interference and so on. A multi-scale semantic model method is proposed to overcome the disadvantages existing in most of the relative methods. This method uses generative model to deal with the objects obtained by multi-scale segmentations instead of whole image, and calculates kinds of visual features to mine the topic information of every object. In the segmentation process, a semantic correlative function of every segment block based on KL divergence is built up and minimized to select the object correct regions. Experimental results demonstrate the effectiveness of the proposed method. © (2012) Trans Tech Publications, Switzerland.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-objects detection in remote sensing images using multiple kernel learning

引用

2012 2nd International Conference on Materials Science and information technology, MSIT 2012

作者： Li, Xiangjuan Sun, Hao Zheng, Xinwei Sun, Xian Wang, Hongqi Institute of Electronics Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783037854389

The objective of this work is multiple objects detection in remote sensing images. Many classifiers have been proposed to detect military objects. In this paper, we demonstrate that linear combination of kernels can get a better classification precision than product of kernels. Starting with base kernels, we obtain different weights for each class through learning. Experiment on Caltech-101 dataset shows the learnt kernels yields superior classification results compared with single-kernel SVM. While such a powerful classifier act as a sliding-window detector to search planes in images collected from Google Earth, results shows the effectiveness of using MKL detector to locate military objects in remote sensing images. © (2012) Trans Tech Publications, Switzerland.

关键词： Object detection

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：