检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Huang, Zhongling Dumitru, Corneliu Octavian Pan, Zongxu Lei, Bin Datcu, Mihai Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Huairou District Beijing101408 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Wessling82234 Germany

The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes' problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What's more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%. Copyright © 2020, The Authors. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

HDEC-TFA: An unsupervised learning approach for discovering physical scattering properties of single-polarized SAR image

TechRxiv

引用

TechRxiv 2020年

作者： Huang, Zhongling Datcu, Mihai Pan, Zongxu Qiu, Xiaolan Lei, Bin Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Huairou District Beijing101408 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Wessling82234 Germany

Knowing the physical properties and scattering mechanisms contributes to Synthetic Aperture Radar (SAR) image interpretation. For single-polarized SAR data, however, it is difficult to extract the physical scattering mechanisms due to lack of polarimetric information. Time-frequency analysis (TFA) on complex-valued SAR image provides extra information in frequency perspective beyond the’image’ domain. Based on TFA theory, we propose to generate the sub-band scattering pattern for every object in complex-valued SAR image as the physical property representation, which reveals backscattering variations along slant-range and azimuth directions. In order to discover the inherent patterns and generate a scattering classification map from single-polarized SAR image, an unsupervised hierarchical deep embedding clustering algorithm based on time-frequency analysis (HDEC-TFA) is proposed to learn the embedded features and cluster centers simultaneously and hierarchically. The polarimetric analysis result for quad-pol SAR images is applied as reference data of physical scattering mechanisms. In order to compare the scattering classification map obtained from single-polarized SAR data with the physical scattering mechanism result from full-polarized SAR, and to explore the relationship and similarity between them in a quantitative way, an information theory based evaluation method is proposed. We take Gaofen-3 quad-polarized SAR data for experiments and the results and discussions demonstrate that the proposed method is able to learn valuable scattering properties from single-polarization complex-valued SAR data, and to extract some specific targets as well as polarimetric analysis. At last, we give a promising prospect to future applications. © 2020, CC BY.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Transform-Invariant Convolutional Neural Networks for Image Classification and Search

arXiv

引用

arXiv 2019年

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation & Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https: ACM ISBN 978-1-4503-2138-9. Copyright © 2019, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

A TOPSAR Calibration Method for processing System of GF3 Next Generation 6

A TOPSAR Calibration Method for Processing System of GF3 Nex...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Yin, Di Han, Bing Sun, Jili Chen, Aiping Zhao, Liangbo Yuan, Xinzhe Zhong, Lihua Hu, Yuxin University of Chinese Academy of Sciences Beijing100049 China Institute of Electronics Chinese Academy of Sciences Beijing100190 China Beijing Institute of Telemetry and Telecommunications Technology Beijing100094 China Chinese Academy of Space Technology Beijing100094 China National Satellite Ocean Application Service State Oceanic Administration Beijing100081 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Institute of Electronics Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781728129129

TOPSAR is an earth-imaging technique, which can provide wide swath coverage. The paper introduces a TOPSAR focusing and calibrating experiment based on the TOPSAR data acquired by Gaofen3(GF3). In this paper, we firstly derive the processor calibration factors under the demands of keeping signal energy invariant. After that, we fully analyze the impact of antenna electronic steering on TOPSAR products. Aimed to be applied to TOPSAR mode processing system of a SAR satellite, the next generation of GF3, calibration methods to processor and electronic steering was proposed in this paper. © 2019 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Approach of SAR images simulations for target interpretations

Approach of SAR images simulations for target interpretation...

引用

IET International Radar Conference 2018, IRC 2018

作者： Zhang, Yueting Ding, Chibiao Lei, Bin Li, Fangfang Qiu, Xiaolan Institute of Electronics Chinese Academy of Sciences Beijing China Key Laboratory of Geo-spatial Information Processing and Application System Technology Chinese Academy of Sciences Zhongguancun Beiyitiao No. 9 Beijing China University of Chinese Academy of Sciences Yuquan Road No. 19 Beijing China

In this work, a novel approach for the simulation of synthetic aperture radar (SAR) images is proposed. Also, this approach aims to interpret the mechanisms of the dominated scattering centres in the SAR image. An attributed model based on typical structures is used to characterise the 3D geometry of the targets. The physical optics and the geometry optics are used to calculate the main scattering mechanisms of the specified typical structures. Also, based on scattering properties and the imaging process, the simulation approach is set up. The experiments based on the Terra-SAR data of an airplane are implemented to test the validity of the simulation. The work presented would be useful for SAR automatic target recognition. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Physical optics

来源：评论

学校读者我要写书评

暂无评论

Progressive unsupervised person re-identification by tracklet association with spatio-temporal regularization

arXiv

引用

arXiv 2019年

作者： Xie, Qiaokang Zhou, Wengang Qi, Guo-Jun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Huawei Cloud EI Product Department Huawei Noah's Ark Laboratory

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model. To facilitate the study, we have collected a new 4K UHD video dataset named Campus-4K with full frames and full spatio-temporal information. Experimental results show that with the spatio-temporal constraint in the training phase, the proposed approach outperforms the state-of-the-art unsupervised methods by notable margins on DukeMTMC-reID, and achieves competitive performance to fully supervised methods on both DukeMTMC-reID and Campus-4K datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

THE DUAL-ASPECT geoMETRIC TERRAIN CORRECTION METHOD USING GF-3 SATELLITE DATA

THE DUAL-ASPECT GEOMETRIC TERRAIN CORRECTION METHOD USING GF...

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Jiayin Liu Xiaolan Qiu Baoquan Zhang Feng Wang Lei Li Key Laboratory of Technology on Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Institute of Electronics Chinese Academy of Sciences Beijing China

The GF-3 satellite is the first full-polarization SAR satellite in China, which operates in the C band with a resolution of 1m. This paper presents a dual-aspect geometric terrain correction method to overcome the inherent shortages of SAR image such as foreshortening, shadow and layover. The results using GF-3 satellite data show that the method can effectively eliminate layover and shadow distortions in SAR images. This method solves the geometric correction problem that cannot be solved with a single SAR image.

关键词： Satellites Radar polarimetry Synthetic aperture radar Mathematical model Orbits Image resolution Satellite broadcasting

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient Carry-Free Inner Product Unit

An Energy Efficient Carry-Free Inner Product Unit

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Wen Yan Miloš D. Ercegovac Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China University of California Los Angeles CA USA

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

An energy efficient truncated inner product unit is proposed in this paper. The proposed unit is pipelined and processes the m pairs of n-bit operands in serial, so that only one unit is required and it can be reused in each recurrence. Truncated inner product is produced so that no accumulation is needed for the lower part. The array reduction unit is bit-level pipelined to improve throughput and reduce the initial delay. A two-level [4:2] adder is proposed to accumulate redundant vectors with non-uniform input arrival. The proposed inner product is compared with other truncated inner product units using fully merged arithmetic, partially merged arithmetic and the counter based inner product for different precision and vector length. Our proposed inner product unit has significant reduction in area, power and energy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Patch reordering: A novel way to achieve rotation and translation invariance in convolutional neural networks

arXiv

引用

arXiv 2019年

作者： Shen, Xu Tian, Xinmei Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street UltimoNSW2007 Australia

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the model from the need to learn them. To enable the model to focus on learning the content of objects other than their locations, we propose to conduct patch ranking of the feature maps before feeding them into the next layer. When patch ranking is combined with convolution and pooling operations, we obtain consistent representations despite the location of meaningful objects in input. We show that the patch ranking module improves the performance of the CNN on many benchmark tasks, including MNIST digit recognition, large-scale image recognition, and image retrieval. The code is available at https://***//jasonustc/caffe-multigpu/tree/TICNN. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A sub-pixel level map projection conversion method for high resolution of GF3 satellite products 12

A sub-pixel level map projection conversion method for high ...

引用

12th European Conference on Synthetic Aperture Radar, EUSAR 2018

作者： Wang, Wentao Liu, Jiayin Huang, Lijia Key Laboratory of Technology on Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783800746361

The GF-3 satellite launched in August 2016, is a C-band synthetic aperture radar(SAR) in China. With a resolution up to 1 m, GF-3 SAR imagery have made feasible the generation large-scale high resolution maps which need a high precision image registration technique. However, different remote sensing data usually have different geocoded formats. It causes misregistration when register SAR image with different projection formats. This paper discusses the method that convert the images from various projection coordinate to the unified geographic coordinate with a conversion accuracy of sub-pixel level. © VDE VERLAG GMBH • Berlin • Offenbach.

关键词： Synthetic aperture radar

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：