检索结果-内蒙古大学图书馆

Unsupervised Domain-Adaptive Object Detection via Localization Regression Alignment

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第11期35卷 15170-15181页

作者： Piao, Zhengquan Tang, Linbo Zhao, Baojun Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Adv Technol Res Inst Jinan 250300 Peoples R China Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China

Unsupervised domain-adaptive object detection uses labeled source domain data and unlabeled target domain data to alleviate the domain shift and reduce the dependence on the target domain data labels. For object detection, the features responsible for classification and localization are different. However, the existing methods basically only consider classification alignment, which is not conducive to cross-domain localization. To address this issue, in this article, we focus on the alignment of localization regression in domain-adaptive object detection and propose a novel localization regression alignment (LRA) method. The idea is that the domain-adaptive localization regression problem can be transformed into a general domain-adaptive classification problem first, and then adversarial learning is applied to the converted classification problem. Specifically, LRA first discretizes the continuous regression space, and the discrete regression intervals are treated as bins. Then, a novel binwise alignment (BA) strategy is proposed through adversarial learning. BA can further contribute to the overall cross-domain feature alignment for object detection. Extensive experiments are conducted on different detectors in various scenarios, and the state-of-the-art performance is achieved;these results demonstrate the effectiveness of our method. The code will be available at: https://***/zqpiao/LRA.

关键词： Location awareness Object detection Detectors Task analysis Feature extraction Training Data models Adversarial learning localization regression neural networks object detection unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

The First Helicopter Platform-Based Equivalent GEO SAR Experiment With Long Integration time

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2020年第12期58卷 8518-8530页

作者： Zhang, Tianyi Ding, Zegang Zhang, Qingjun Zhao, Bingji Zhu, Kaiwen Li, Linghao Gao, Yongpeng Dai, Chao Tang, Zhihua Long, Teng Beijing Inst Technol Sch Informat & Elect Radar Res Lab Beijing 10081 Peoples R China Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China Beijing Inst Spacecraft Syst Engn Beijing 100081 Peoples R China

Geosynchronous synthetic aperture radar (GEO SAR)-related technologies are being mature, and the first GEO SAR satellite is expected to launch in the next ten years. Under this circumstance, some equivalent experiments should be conducted at the current stage to validate some key characteristics or parameters, which could significantly increase the success possibility of the GEO SAR project. To validate the feasibility of GEO SAR imaging with long integration time, which is the most important and fundamental characteristic of GEO SAR, the first helicopter platform-based equivalent GEO SAR experiment with long integration time was performed in Qianxi County of China on May 22, 2019. The integration time of it is 80 s, which is carefully designed to maintain the consistence between itself and the integration time of the GEO SAR. Furthermore, the azimuth signal-to-noise ratio gain with long synthetic aperture time is analyzed. Moreover, the 2-D space-variant motion error introduced by the complex helicopter trajectory and the performances of different imaging algorithms are analyzed to choose the proper imaging algorithms;to overcome the flaws and unclarities of existing algorithms, some improvements are proposed to obtain the well-focused SAR image. What is more, the equivalence of this experiment is also analyzed detailedly to demonstrate the effectiveness of this experiment. At last, the imaging result with synthetic aperture time of 100 s and the comparison between itself and the optic photograph validate the success of this equivalent experiment and the feasibility of GEO SAR imaging with long integration time.

关键词： Synthetic aperture radar Helicopters Apertures Imaging Signal to noise ratio Radar polarimetry Azimuth Equivalent experiment geosynchronous synthetic aperture radar (GEO SAR) helicopter platform long integration time

来源：评论

学校读者我要写书评

暂无评论

A unified reconfigurable floating-point arithmetic architecture based on CORDIC algorithm 16

A unified reconfigurable floating-point arithmetic architect...

引用

16th IEEE International Conference on Field-Programmable Technology (ICFPT)

作者： Li, Bingyi Fang, Linlin Xie, Yizhuang Chen, He Chen, Liang Beijing Inst Technol Sch Informat & Elect Radar Res Lab Beijing Peoples R China Beijing Key Lab Embedded Real Time Informat Proc Beijing Peoples R China

ISBN: (纸本)9781538626566

This paper presents the design methodology and implementation of reconfigurable coordinate rotation digital computer (CORDIC) architecture that can be configured to operate in different modes and rotations to achieve single-precision floating point division, multiplication and square-root operations. Through introducing pre- and post- processing, the float-point operations can be integrated into a unified CORDIC iteration procedure. According to the characteristics of different operations, we propose a pipeline-parallel mixed architecture to optimize the area-delay-efficiency. Finally, the prototype based on Xilinx XC7VX690T has been established to test the performance of the proposed design. The result shows the related error with arithmetic computation is less than 10(-6), and the resource-consumption of the proposed design is less than the sum of existing IP cores.

关键词： reconfigurable floating-point CORDIC FPGA

来源：评论

学校读者我要写书评

暂无评论

A Gaussian Mixture PHD Filter for Multitarget Tracking in Target-Dependent False Alarms

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2024年第4期60卷 4808-4824页

作者： Jiang, Qi Wang, Rui Ni, Na Dou, Libin Hu, Cheng Beijing Inst Technol Sch Informat & Elect Radar Res Lab Beijing 100081 Peoples R China Beijing Key Lab Real Time Informat Proc Technol Em Beijing 100081 Peoples R China

Tracking individuals within a group is one of the major tasks of group target observation. Tracking radar must feature high frame rate and high range-angular resolution to achieve the stable multitarget tracking performance. However, two major problems arise from this scenario. First, the narrow beam of the tracking radar does not allow the complete observation of group target, causing the fluctuation of target number as the radar-target geometry changes;second, false alarms may be target-dependent and distributed around the targets, which is contrary to the traditional spatially uniform clutter model. This article proposes a Gaussian mixture probability hypothesis density (PHD) filter for multitarget tracking using a collaborative radar system. The system consists of one scanning radar and one tracking radar. The former outputs the group's collective states (centroid, extension, etc.), which are used as the priors for the tracking radar. The tracking radar is responsible for the multitarget tracking. The density of target birth and death are set according to the priors. The update equation of the PHD in target-dependent false alarms is derived and simplified to meet the practical application requirements. Finally, the effectiveness of the proposed filter is verified by the simulation and experimental results.

关键词： Radar tracking Target tracking Radar Doppler effect Mathematical models Geometry Drones GM-PHD filter multitarget tracking random finite set target-dependent false alarms

来源：评论

学校读者我要写书评

暂无评论

DEM-ASSISTED BACK-PROJECTION ALGORITHM IN HIGH RESOLUTION GEOSYNCHRONOUS SAR IMAGING 36

DEM-ASSISTED BACK-PROJECTION ALGORITHM IN HIGH RESOLUTION GE...

引用

36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Li, YuanHao Dong, XiChao Cui, Kai Hu, Cheng Ao, DongYang Long, Teng Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China

ISBN: (纸本)9781509033324

Since geosynchronous synthetic aperture radar (GEO SAR) has curved trajectories, back-projection algorithm (BPA) greatly fits for its imaging. However, for a scene with height variation, the reference range based on the fixed-height imaging grid under curved trajectories is inaccurate in azimuth back-projection. Resultantly, the GEO SAR image quality will be obviously deteriorated in high resolution imaging. To address the issue, this paper proposed the digital elevation model (DEM)-assisted BPA to realize the accurate high resolution GEO SAR imaging for the scene with height variation. DEM information is utilized to construct the imaging grid in the new method for generating the accurate reference range. Simulation results validate that the proposed method achieves good imaging performance for the scene with height variation.

关键词： SAR imaging GEO SAR Back-projection Algorithm DEM

来源：评论

学校读者我要写书评

暂无评论

Target Scattering Centers Reconstruction based on C-means method for Radar Network

Target Scattering Centers Reconstruction based on C-means me...

引用

IEEE International Conference on Signal processing, Communications and Computing (ICSPCC)

作者： Liu, Feifeng Feng, Wenling Zeng, Tao Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China

ISBN: (纸本)9781509027088

Conventional synthetic aperture radar (SAR) and inverse SAR (ISAR) techniques need long integration time, i.e. 1 second or more, to get the high azimuth resolution. Radar network with widely separated transmitters and receivers has the ability to simultaneously acquire the high range resolution profiles (HRRPs) from different angles and thus has the potential to reconstruct the target image by combining the information from these HRRPs. This paper proposed a target reconstruction algorithm based on the C-means method for radar network. The reconstruction could be accomplished by using fuzzy clustering of C-means method based on these HRRPs. The simulation results validated the proposed algorithm.

关键词： scattering centers reconstruction radar network C-means method

来源：评论

学校读者我要写书评

暂无评论

Open Set Radar HRRP Recognition Based on Random Forest and Extreme Value Theory

Open Set Radar HRRP Recognition Based on Random Forest and E...

引用

International Conference on Radar (RADAR)

作者： Wang, Yanhua Chen, Wei Song, Jia Li, Yang Yang, Xiaopeng Beijing Inst Technol Sch Informat & Elect Beijing Peoples R China Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc Beijing Peoples R China

ISBN: (纸本)9781538672174

Most of the progresses achieved in radar high range resolution profile (HRRP) recognition rely on the closed set condition, where the test sample is from a known class. In realistic scenario, however, the test sample may be drawn from unknown classes, which is regarded as an open set recognition task. In such cases, conventional recognition algorithms will inevitably make a wrong prediction. In this paper, the open set problem is addressed by incorporating the extreme value theory (EVT) into the random forest (RF) classifier. The outputs of RF are analyzed to determine whether the test sample should be rejected as an unknown class. At the training phase, a Weibull-based extreme-value meta-recognition is introduced to describe the statistical characteristics of the known classes. At the testing phase, a probability estimation method is introduced to compute the probabilities of the test sample belonging to known and unknown classes based on trained Weibull distributions. The test sample is assigned to the class of highest probability. Experimental results demonstrate that the proposed method outperforms the state-of-art NN, 1-vs-set machine and W-SVM in rejecting unknown classes.

关键词： open set recognition random forest high range resolution profile (HRRP) extreme value theory

来源：评论

学校读者我要写书评

暂无评论

Accurate Three Dimensional Deformation Retrieval in Geosynchronous SAR by Multi-aperture Interferometry processing

Accurate Three Dimensional Deformation Retrieval in Geosynch...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Hu, Cheng Li, Yuanhao Dong, Xichao Long, Teng Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China

ISBN: (纸本)9781509060931

The information of the three dimensional (3D) surface deformation is important in geographic applications. Considering the advantages of large and continuous coverage of GEO SAR, the paper studies a novel 3D deformation field retrieval approach with a higher accuracy based on the geosynchronous SAR (GEO SAR) Multiple Aperture Interferometry (MAI) processing. We discuss the method and several key issues to obtain the 3D deformation field by combining the MAI phase and the GEO D-InSAR data from an additional view angle. Simulations are conducted and the good performance is obtained. When the optimal sub-apertures are utilized, a 3D deformation field with the accuracy of mm level in the vertical direction and the cm level in the north-south direction and the east-west direction is obtained.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Resolution Analysis Based on Distinguishable Ellipse in Squinted SAR under Maneuvering Flight

Resolution Analysis Based on Distinguishable Ellipse in Squi...

引用

IEEE International Conference on Signal processing, Communications and Computing (ICSPCC)

作者： Gao, Jing Li, Feng Ma, Zhixun Wang, Zhen Beijing Inst Technol Sch Informat & Elect Beijing Peoples R China Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc Beijing Peoples R China

ISBN: (纸本)9781509027088

Geometric configuration of imaging varies significantly over time in squinted synthetic aperture radar (SAR) when platform is under maneuvering flight. The classic resolution analysis in the traditional SAR is not suitable in this case. In order to illustrate a general description of the resolution characteristics of the system, a method of resolution analysis based on distinguishable ellipse in squinted SAR under different geometric configurations is presented. In addition, two options for finding the optimal synthetic aperture of target identification by estimating resolution are proposed. The simulation results show that this method is adaptive to conditions of different flight parameters and geometric configurations in squinted SAR under maneuvering flight.

关键词： SAR maneuvering flight resolution analysis

来源：评论

学校读者我要写书评

暂无评论

A novel TOA estimation method for unknown signal based on intra-pulse correlation accumulation

A novel TOA estimation method for unknown signal based on in...

引用

IEEE International Conference on Signal processing, Communications and Computing (ICSPCC)

作者： Xu, Jiacen Wang, Zhongyi Liu, Quanhua Ren, Lixiang Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc Beijing Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing Peoples R China

ISBN: (纸本)9781509027088

This paper presents a novel low complexity time-of arrival (TOA) estimation method for unknown intra-pulse modulated signal under low SNR condition. The received signal is firstly pre-processed by delayed conjugate multiplication to reduce the intra-pulse modulation and get a rough range of the signal. Then a novel intra-pulse correlation accumulation method is applied to achieve a precise estimation of rising and falling edge. Simulations are conducted to show the feasibility of the method and evaluate the performance of estimation. Compared with existing methods, this novel method can achieve a better estimation result.

关键词： TOA estimation unknown signal low SNR Monte Carlo simulation

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：