检索结果-内蒙古大学图书馆

2011 International Symposium on Image and Data Fusion, ISIDF 2011

作者： Xu, Jian Fu, Kun Sun, Xian Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781457709692

Automatic inshore ship detection from remote sensing imagery has many important applications, such as ship change detection and harbor dynamic surveillance. Stable performance of inshore ship detection is vital to the analysis of ship change and then determines the harbor surveillance effect. However, it is hard to detect inshore ships utilizing the traditional area-based method because the grayscale and texture character of inshore ships are similar to that of the shore. In this paper, a new method based on invariant generalized Hough transform is introduced to extract ship shape using the evidence-gathering procedure. In contrast with other shape extraction methods used in inshore ships detection, our method is specially tolerant to noise and occlusion, and also invariant to translation, scale and rotation transformation. Moreover, our method can be used to separate ships moored together that can benefit to ship recognition. Experiment results are demonstrated on the optical remote sensing imagery from Google Earth. © 2011 IEEE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Analysis and Prediction of Vehicle Exhaust Emission Using ANN 36

Analysis and Prediction of Vehicle Exhaust Emission Using AN...

引用

第36届中国控制会议

作者： Zhenyi Xu Yu Kang Wenjun Lv Department of Automation and State Key Laboratory of Fire Science University of Science and Technology of China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences

ISBN: (纸本)9781538629185

This paper focused on the analysis of vehicle emission based on the Hefei remote sensing data during the last three *** we propose a three-layer artificial neural network model for predicting vehicle exhaust emission using remote sensing ***,we take adaptive-lasso algorithm to analyze the various factors from the emission data,and determine the principal ***,after doing principal components analysis and selecting algorithm and architecture,the Back-Propagation neural network model with 7-12-1 architecture was established as the optimal ***,we give the prediction results on the testing data-set and prove the potentiality and validity of the proposed method in the prediction of vehicle exhaust emission.

关键词： Vehicle Exhaust Emission Adaptive-Lasso Artificial Neural Network

来源：评论

学校读者我要写书评

暂无评论

A novel synthetic aperture radar scattering model for sea surface with breaking waves

引用

Acta Oceanologica Sinica 2022年第4期41卷 138-145页

作者： Xiaochen Wang Yuxin Hu Bing Han Wei Tian Chunhua Zhang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of SciencesBeijing 100190China The box51111 Beijing 100190China

In this study a novel synthetic aperture radar(SAR)scattering model for sea surface with breaking waves is *** with existing models,the proposed model considers an empirical relationship between wind speed and wave breaking scattering to present the contribution of wave ***,the scattering weight factor p,and wave breaking rate q,are performed to present the contribution of the quasi-specular scattering term,Bragg scattering term,and wave breaking scattering term to the total scattering from the sea *** explore the modeling accuracy of sea-surface scattering,a simulated normalized radar cross-section(NRCS)and measured NRCS are *** proposed model generated the simulated NRCS and a matching GF-3 dataset was used for the measured *** was revealed that the performance of the VV polarization of our model was much better than that of HH polarization,with a correlation of 0.91,bias of-0.14 dB,root mean square error(RMSE)of 1.26 dB,and scattering index(SI)*** addition,the novel model is explored and compared with the geophysical model of CMODs and satellite-measured NRCS from GF-3 SAR wave mode *** an incidence angle 40°–41°,the relationship between the NRCS and wind speed,relative wind direction is *** with the SAR-measured NRCS,the performance of VV polarization was much better than HH polarization,with a correlation of 0.99,bias of-0.25 dB,RMSE of 0.64 dB,and SI of-0.04.

关键词： synthetic aperture radar scattering model sea surface wave breaking

来源：评论

学校读者我要写书评

暂无评论

AF2S: An Anchor-Free Two-Stage Tracker Based on a Strong SiamFC Baseline 16th

AF2S: An Anchor-Free Two-Stage Tracker Based on a Strong Sia...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： He, Anfeng Wang, Guangting Luo, Chong Tian, Xinmei Zeng, Wenjun CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China Microsoft Research Asia Beijing China

ISBN: (纸本)9783030682378

Siamese network based trackers have become a mainstream in visual object tracking. Recently, several high-performance multi-stage trackers have been proposed and some of them adopt SiamRPN for the first-stage region proposal. We argue that an anchor-based region proposal network is not necessary for the tracking task, as a tracker has a strong prior about the location and size of the target. In this paper, we propose a two-stage visual tracker which uses SiamFC for region proposal. SiamFC defines a bounding box by its center, which is a typical anchor-free (AF) network, so we dub our tracker AF2S. As the model size of SiamFC is only about 1/10 that of SiamRPN, AF2S results in a significantly lighter model than its SiamRPN-based counterparts. In the design of AF2S, we first build a strong AlexNet-based SiamFC baseline which improves the AUC on OTB-100 from 0.582 to 0.665. Further, we propose a position-sensitive convolutional layer which can be stacked after SiamFC backbone to increase the robustness of proposals without losing localization precision. Finally, a relation network is used for box refinement. Experimental results show that AF2S achieves the best performance on OTB-100 and VOT-18 among the state-of-the-art trackers which use AlexNet as backbone. On LaSOT-test, AF2S achieves an AUC of 0.480, which is among the first-tier performance even when trackers with more powerful backbone and much larger model size are considered. © 2020, Springer Nature Switzerland AG.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

An Approach for Spaceborne InSAR DEM Inversion Integrated with Stereo-SAR Method 6

An Approach for Spaceborne InSAR DEM Inversion Integrated wi...

引用

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

作者： Li, Fangfang Zhang, Yueting Qiu, Xiaolan Key Laboratory of Geo-spatial Information Processing and Application System Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728129129

Spaceborne Interferometric Synthetic Aperture Radar (InSAR) has the capability of high precise topographic mapping for large area. However, on the one hand, digital elevation models (DEM) inversion needs at least one ground control points (GCP) to obtain absolute interferometric phase as the unwrapped phase is just a relative value. On the other hand, the baseline value used for DEM inversion also needs to be calibrated using GCPs due to the measure error. In practice, it is difficult to manually deploy GCPs especially in the area of steep topography. At present, with the improvement of orbital measure accuracy and system time accuracy for spaceborne SAR satellite, high precise absolute 3D location information of some stable point scatterers can be obtained by stereo SAR using data from different viewing angles. Therefore, this paper combines stereo SAR with InSAR. These point scatters are used as GCPs to calibrate baseline and estimate absolute phase. As a result, high accurate DEM generation without GCPs can be achieved. The experiment using TerraSAR-X data verifies the effectiveness of this method. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A cloud detection method based on a time series of MODIS surface reflectance images

引用

International Journal of Digital Earth 2013年第S01期6卷 157-171页

作者： Hairong Tang Kai Yu Olivier Hagolle Kang Jiang Xiurui Geng Yongchao Zhao Key Laboratory of Technology in Geo-spatial information Processing and Application System Institute of ElectronicsChinese Academy of ScienceBeijingChina CESBIO Universite´de ToulouseUnite´mixte CNES CNRS IRD UPSToulouse Cedex 4France

The Moderate Resolution Imaging Spectroradiometer(MODIS)-Terra surface reflectance product(MOD09A1),with bands 1 to 7,is a gridded,eight-day composite product derived from the MODIS-Terra top of atmosphere reflectance *** performs cloud detection and corrects for the effects of atmospheric gases and *** cloud mask(CM)algorithms for MODIS are based on empirical thresholds on spectral reflectance and brightness *** the spatial resolution of the thermal band is 1000 m,while that of MOD09A1 is 500 m,many undetected and false clouds are observed in *** errors always result in temporal and spatial inconsistencies in higher-level *** this paper,a cloud detection algorithm(TSCD)based on a MOD09A1 time series is *** series cloud detection(TSCD)algorithm is based on the relative stability of ground reflectance and the sudden variations in reflectance that result from cloud *** algorithm first searches the clear-sky reference data,and then discriminates clouded and unclouded pixels by detecting a sudden change of reflectance in the blue wavelength and spectral correlation coefficient at the pixel *** with cloud cover assessments obtained from MODIS’original CM,TSCD provides similar or better discrimination in most situations when the land surface changes slowly.

关键词： MODIS surface reflectance time series cloud detection BRDF

来源：评论

学校读者我要写书评

暂无评论

Improved S2ANet based on attention mechanism for small target detection in remote sensing images

Improved S2ANet based on attention mechanism for small targe...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Lu, Dongdong Tie, Wenjie Lei, Songlin Qiu, Xiaolan Suzhou Aerospace Information Research Institute Laboratory of Spatial Information Intelligent Processing System Suzhou China Chinese Academy of Sciences Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Beijing China

ISBN: (纸本)9781665498142

Deep learning has achieved remarkable results in the field of target detection and recognition. For small targets in images, image pyramid can be used to fuse multi-scale features to improve detection performance. However, when test on remote sensing images, it is found that some important small goals will still be missed. Aiming at the problems of small target detection in remote sensing images, this paper proposes two S2ANet improved network variants based on the attention mechanism for synthetic aperture radar(SAR) payload and optical payload: for SAR images, CBAM(Convolutional Block Attention Module) attention is added to the backbone network to increase the attention of the feature extraction network for small targets in the channel and space dimensions;For optical images, firstly increase the CBAM channel attention and spatial attention in the backbone, secondly, the SE(Squeeze And Excitation) channel attention is added to the input features before the channel dimension fusion of the pyramid structure, then the attention-enhanced targets are fully integrated through up-sampling and horizontal splicing operations to improve the missed alarm rate and recall rate of small remote sensing targets. Finally, a comparative verification was carried out on the constructed airborne KU-band SAR data set and the optical remote sensing aircraft data set composed of some DOTA1.5 and FAIR1M data sets. The experimental results proved that the designed two variant networks can be used for small remote sensing. There have been certain improvements in the missed alarm rate, accuracy rate, and recall rate of the target. © 2021 IEEE.

关键词： Radar remote sensing Radar detection Object detection Radar imaging Optical imaging Feature extraction Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

A novel error concealment algorithm for H.264/AVC 21

A novel error concealment algorithm for H.264/AVC

引用

21st International Conference on MultiMedia Modeling, MMM 2015

作者： Zhang, Jinlei Li, Houqiang Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

ISBN: (纸本)9783319144443

To benefit network transmission, the bit stream of the whole frame coded by H.264/AVC is usually grouped into one packet. However, the packet loss during transmission will lead to the distortion of the reconstructed video and the error propagation. To deal with this problem, error concealment (EC) strategy is widely used to recover the lost frames and to weaken the effect of error propagation. In this paper, we propose a new EC method which uses both the forward and backward motion information to recover the motion information of the current lost frame. Besides, for the pixels whose motion information is quite different compared with its neighboring pixels, we propose to use the spatial correlation to fill up the pixels by minimizing the total variation (TV) *** the help of our proposed algorithm, we can obtain the motion vectors of the lost frames and improve the accuracy of motion vectors derived by the unidirection recovery method. Besides, the optimization strategy, minimizing the TV-norm for the pixels with quite different motion vectors, can help the decoder to recover the reconstructed frames more accurately. Experimental results show that the proposed algorithm can achieve both better objective performance and subjective performance compared to well-known schemes. © Springer International Publishing Switzerland 2015.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Linear distance preserving pseudo-supervised and unsupervised hashing 16

Linear distance preserving pseudo-supervised and unsupervise...

引用

24th ACM Multimedia Conference, MM 2016

作者： Wang, Min Zhou, Wengang Tian, Qi Zha, Zhengjun Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China China Computer Science Department University of Texas at San Antonio United States

ISBN: (纸本)9781450336031

With the advantage in compact representation and efficient comparison, binary hashing has been extensively investigated for approximate nearest neighbor search. In this paper, we propose a novel and general hashing framework, which simultaneously considers a new linear pair-wise distance preserving objective and point-wise constraint. The direct distance preserving objective aims to keep the linear relationships between the Euclidean distance and the Hamming distance of data points. Based on different pointwise constraints, we propose two methods to instantiate this framework. The first one is a pseudo-supervised hashing method, which uses existing unsupervised hashing methods to generate binary codes as pseudo-supervised information. The second one is an unsupervised hashing method, in which quantization loss is considered. We validate our framework on two large-scale datasets. The experiments demonstrate that our pseudo-supervised method achieves consistent improvement for the state-of-the-art unsupervised hashing methods, while our unsupervised method outperforms the state-of-the-art methods. ©2016 ACM.

关键词： Hamming distance

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：