检索结果-南通市图书馆

2015 5th International Conference on Computer Sciences and Automation Engineering(ICCSAE 2015)

作者： Qigejian Wang Xinyu Zhang Huazhong University of Science and Technology Graduate School of Art and Science (Statistics) Columbia University

This paper presents a novel visual saliency guided high resolution remote sensing image change detection（CD） algorithm. This approach is based on closed-loop process made up of the three procedures.（1） Generating the difference image as the foundation for further processing;（2） Use the modified saliency extraction algorithm to select the regions with higher attractiveness;（3） Adopt the revised fuzzy clustering to finalize the real changed regions（RCR）. Our algorithm could fuse the traditional change analysis patterns with the saliency prior which could enhance the overall efficiency. Experiments carried out on the different sets of high resolution multi-temporal images acquired by the satellite. The experimental result shows that our method could achieve better performance.

关键词： Visual Saliency Remote Sensing Change Detection High resolution image

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Target localization method of non-cooperative spacecraft on on-orbit service

引用

Chinese Journal of Aeronautics 2022年第11期35卷 336-348页

作者： Yingxiao LI Ju HUO Ping MA Ruiye JIANG Control and Simulation Center Harbin Institute of TechnologyHarbin 150001 China

With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods based on machine learning intractable to break through the two difficulties of solving scale transformation problem of the targets in image and accelerating detection rate of high-resolution images. To overcome the two challenges, we propose a novel noncooperative target detection method using the framework of deep convolutional neural network.Firstly, a specific spacecraft simulation dataset using over one thousand images to train and test our detection model is built. The deep separable convolution structure is applied and combined with the residual network module to improve the network’s backbone. To count the different shapes of the spacecrafts in the dataset, a particular prior-box generation method based on K-means cluster algorithm is designed for each detection head with different scales. Finally, a comprehensive loss function is presented considering category confidence, box parameters, as well as box confidence. The experimental results verify that the proposed method has strong robustness against varying degrees of luminance change, and can suppress the interference caused by Gaussian noise and background complexity. The mean accuracy precision of our proposed method reaches 93.28%, and the global loss value is 13.252. The comparative experiment results show that under the same epoch and batchsize, the speed of our method is compressed by about 20% in comparison of YOLOv3, the detection accuracy is increased by about 12%, and the size of the model is reduced by nearly 50%.

关键词： Spacecraft service High resolution image Object detection Complex environment Lightweight model

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

The Surface Rupture Zone and Coseismic Deformation Produced by the Yutian Ms7.3 Earthquake of 21 March 2008,Xinjiang

引用

Acta Geologica Sinica(English Edition) 2012年第1期86卷 256-265页

作者： SHAN Xinjian QU Chunyan WANG Chisheng ZHANG Guifang ZHANG Guohong SONG Xiaogang GUO Liming LIU Yunhua State Key Laboratory of Earthquake Dynamics Institute of GeologyChina Earthquake Administration Beijing 100029China Institute of Remote Sensing Application Chinese Academy of SciencesBeijing 100101China

On 21 March 2008, a Ms7.3 earthquake occurred at Quickbird, Yutian County, Xinjiang. We attempt to reveal the features of the causative fault of this shock and its coseismic deformation field. Our work is based on analysis and interpretation to high-resolution satellite images as well as differential interferometric synthetic aperture radar （D-InSAR） data from the satellite Envisat SAR, coupled with seismicity, focal mechanism solutions and active tectonics in this region. The result shows that the 40 km-long, nearly NS trending surface rupture zone by this event lies on a range-front alluvial platform in Qira County. It is characterized by distinct linear traces and simple structure with 1-3-m-wide individual seams and maximum 6.5 m width of a collapse fracture. Along the rupture zone many secondary fractures and fault-bounded blocks are seen, exhibiting remarkable extension. The eoseismic deformation affected a large area 100~100 km2. D-InSAR analysis indicates that the interferometric deformation field is dominated by extensional faulting with a small strike-slip component. Along the causative fault, the western wall fell down and the eastern wall, that is the active unit, rose up, both with westerly vergence. Because of the big deformation gradients near the seismogenic fault, no interference fringes are seen on images, and what can be determined is a vertical displacement 70 cm or more between the two fault walls. According to the epicenter and differential occurrence times from the National Earthquake Information Center, China Earthquake Network Center, Harvard and USGS, it is suggested that the seismic fault ruptured from north to south.

关键词： Yuntian Earthquake High resolution image D-InSAR surface rupture zone coseismic deformation field

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Small Object Detection in high-resolution images Based on Multiscale Detection and Re-training

Small Object Detection in High-Resolution Images Based on Mu...

引用

作者： Guang-min SUN Jia-yang CHEN Bing LI Dong YAN Yu LI Gang XIE Faculty of information Technology Beijing University of Technology China National Tobacco Corp.Beijing Corp

Most of the current small object detection algorithms are designed for low-resolution images. They can neither directly process high-resolution images nor make full use of the information contained. In this paper, an algorithm is proposed to detect small objects in highresolution images directly. The process of the algorithm is as follows: Firstly, an original detection task is split logically into several relevant detection sub-tasks at different scales. Secondly, a corresponding low-resolution object detector is trained for each sub-task. Thirdly, the detectors are deployed to get detection results at different scales. Finally, the multi-scale detection results are logically combined to derive the final detection results of the small objects. Besides, the detector is re-trained at small scale by introducing negative samples. The algorithm proposed in this paper was tested in the task of defect detection on building wall surface. Experimental results show the reliability and efficiency of our approach.

关键词： High resolution image Small object detection Multiscale Negative feedback mechanism Defect detection of building wall surface

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

high resolution STUDY OF TWINS IN Al_(20)Cu_2Mn_3 PHASE

引用

Acta Metallurgica Sinica(English Letters) 1992年第4期5卷 227-230页

作者： LI Chunzhi WANG Shuncai JIN Yan Institute of Aeronautical Materials,Beijing,Laboratory of Atomic Imaging of Solids,Institute of Metal Research,Academia Sinica,Shenyang,China Inst of Aeronautical Materials Beijing China

The dispersoid phase Al_(20)Cu_2Mn_3 in a 2024 Al alloy is commonly composed of twins,An ob- servation of corresponding High resolution image shows that the twin boundary plane is a glide plane other than mirror one.Two neighbouring components of twins are not symmetry of re- flection or rotation,but of glide reflection.The“diamond”glide plane is(101)and the glide vector is(1/4)(-).Components of twins in the phase take shape of prism with the longitudinal edge being parallel to[010]and side faces being{101}and{100}.

关键词： twin glide reflection High resolution image Al-Cu-Mn alloy

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

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：