检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code available at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Biased feature learning for occlusion invariant face recognition 29

Biased feature learning for occlusion invariant face recogni...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Shao, Changbin Huo, Jing Qi, Lei Feng, Zhen-Hua Li, Wenbin Dong, Chuanqi Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Jiangsu University of Science and Technology Zhenjiang China Department of Computer Science Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom

ISBN: (纸本)9780999241165

To address the challenges posed by unknown occlusions, we propose a Biased Feature Learning (BFL) framework for occlusion-invariant face recognition. We first construct an extended dataset using a multi-scale data augmentation method. For model training, we modify the label loss to adjust the impact of normal and occluded samples. Further, we propose a biased guidance strategy to manipulate the optimization of a network so that the feature embedding space is dominated by non-occluded faces. BFL not only enhances the robustness of a network to unknown occlusions but also maintains or even improves its performance for normal faces. Experimental results demonstrate its superiority as well as the generalization capability with different network architectures and loss functions. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Tor Anonymity Attack Experiment Platform Driven by Raspberry Pi

A Tor Anonymity Attack Experiment Platform Driven by Raspber...

引用

Prognostics and System Health Management (PHM-Jinan), International Conference on

作者： Qi Wang Weiquan Cao National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728151816

ISBN: (纸本)9781728151823

Private Tor network is essential for analyzing security issues both for Tor project as well as for numerous researchers. However, current research work mainly focus on improving scalability and efficiency by simulating traffic discretely with single node and restoration level by deploying a complete private network with high cost. In this paper, we propose a novel methodology constructing real private tor network by editing and controlling Raspberry Pis, called Tor anonymity attack experiment platform. Compared with other platforms of the same type, the platform has the advantages of low cost, easy to scale, high quality of real-time data transmission, high degree of network protocol restoration as well as convenient configuration. In order to demonstrate the platform can be used as a private and complete Tor anonymous network experiment environment, we conduct a source tracing attack as a study case. Experimental results and theoretical analysis both show that the platform can support researchers to carry out numerous Tor network security research with high degree of restoration efficiently and cheaply.

关键词： Servers Economic indicators Protocols Software Emulation Operating systems Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Research on Improvement of Code Phase Synchronization Accuracy in GPS Spoofing

Research on Improvement of Code Phase Synchronization Accura...

引用

IEEE Information technology and Mechatronics Engineering Conference (ITOEC)

作者： Shuming Yi Xian Li Ling You National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728143231

ISBN: (纸本)9781728143248

GPS (global positioning system) signals are direct-sequence spread-spectrum signals. The receiver relies on locally reproduced pseudo-random codes to keep tracking and dispreading the navigation signals. Due to the correlation characteristics of pseudo-random codes, scholars generally believe that only two identical signals that are separated by half a chip error have correlation, which brings high time synchronization accuracy requirements to GPS spoofing technology. In this paper, the research and analysis of the principle of the GPS receiver are carried out. It is found that the GPS spoofing technology can achieve a signal time synchronization error of 1.5 chips and proposed that the correlation peak loss due to chip error can be compensated by the transmit power in the meantime. The detailed theoretical derivation proof is given in the article. Finally, simulation experiments are performed to obtain the minimum spoofing power. The results show that under this error condition, GPS spoofing can be effectively implemented.

关键词： Correlation Tracking loops Receivers Global Positioning System Synchronization Low pass filters Generators

来源：评论

学校读者我要写书评

暂无评论

Three-lane Car-flowing Model Accounting for Variable Lane Change and Driving Behavior

Three-lane Car-flowing Model Accounting for Variable Lane Ch...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xiaotong Yan Jia Lee Lingqiu Zeng Yunni Xia College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Software Theory and Technology Chongqing University Chongqing China Laboratory of Signal and Information Processing Chongqing University Chongqing China

ISBN: (纸本)9781665442084

This paper aims to analyze the influence of different driving behavior on multilane traffic flows, via extending the well-studied single-lane car-following model into a three-lane model. To this end, we classify all drivers’ characteristics into three types: calm, moderate and aggressive, in accordance with their differences in response coefficient, expectation safe distance, maximum speed and lane-changing intention. Based on Kerner’s three-phase traffic theory, our model can reproduce the empirical features of spontaneous traffic breakdown phenomena, revealing the mechanism of congestion formation and state transitions. In addition, we examine how the traffic accident, honking and fast-slow lanes could affect the heterogeneous traffic flows. Numerical experiments show that the drivers’ characteristics play an essential role in stabilizing the traffic flow on multilane roads. The results may contribute to traffic planning and control on the urban roadways.

关键词： Analytical models Electric breakdown Roads Conferences Numerical models Planning Automobiles

来源：评论

学校读者我要写书评

暂无评论

Joint Detection and Tracking Scheme for Target Tracking in Moving Platform

Joint Detection and Tracking Scheme for Target Tracking in M...

引用

IEEE National Conference on radar

作者： Yongsheng Guan Yingping Wang Information Science Academy of China Electronics Technology Group Corporation Beijing China National Laboratory of Radar Signal Processing Xidian University Xi'an Shaanxi China

ISBN: (数字)9781728189420

ISBN: (纸本)9781728189437

In this paper, a joint detection and tracking (JDT) scheme is presented for single target tracking in clutter using a moving radar platform. The core of the JDT scheme is to adaptively modify the detection threshold according to the feedback information from the tracker to the detector, while guaranteeing the averaged false alarm rate in the validation gate is a constant. The feedback information we utilized is the target's predicted location distribution, which can be achieved through jointly estimating the state of platform and target. Simulation results suggest that the JDT scheme can provide improved detection and tracking performance significantly, when compared with the standard probabilistic data association method.

关键词： Target tracking radar tracking radar detection Detectors Clutter signal to noise ratio Technological innovation

来源：评论

学校读者我要写书评

暂无评论

Directional Source Localization Based on RSS-AOA Combined Measurements

引用

China Communications 2020年第11期17卷 181-193页

作者： Peiliang Zuo Tao Peng Hao Wu Kangyong You Hanbo Jing Wenbin Guo Wenbo Wang Wireless Signal Processing and Network Laboratory Key Laboratory of Universal Wireless CommunicationMinistry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China Department of Electronic and Communication Engineering Beijing Electronic Science&Technology InstituteBeijing 100070China th Research Institute of China Electronics Technology Group Corporation(CETC) Guangzhou 510310China Beijing Institute of Remote Sensing Equipment Beijing 100854China

Source localization plays an indispensable role in many *** paper addresses the directional source localization problem in a three-dimensional(3D)wireless sensor network using hybrid received-signal-strength(RSS)and angle-of-arrival(AOA)*** the position and transmission orientation of the source are to be *** the considered positioning scenario,the angle and range measurements are respectively corresponding to the AOA model and RSS model that integrates the Gaussian-shaped radiation *** that the localization problem is non-convex and the unknown parameters therein are coupled together,this paper adopts the second-order cone relaxation and alternating optimization techniques in the proposed estimation ***,to provide a performance benchmark for any localization method,the corresponding Cramer-Rao lower bounds(CRLB)of estimating the unknown position and transmission orientation of the source are *** and simulation results demonstrate that the presented algorithm effectively resolves the problem,and its estimation performance is close to the CRLB for the localization with the hybrid measurements.

关键词： localization directional source CRLB RSS AOA wireless sensor network(WSN) second-order cone programming(SOCP)

来源：评论

学校读者我要写书评

暂无评论

RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning

arXiv

引用

arXiv 2023年

作者： Zhu, Yabin Li, Chenglong Wang, Xiao Tang, Jin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes School of Electronic and Information Engineering Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant appearance gap between modalities limits the feature representation ability of certain modalities during the fusion process. To address this problem, we propose a novel Progressive Fusion Transformer called ProFormer, which progressively integrates single-modality information into the multimodal representation for robust RGBT tracking. In particular, ProFormer first uses a self-attention module to collaboratively extract the multimodal representation, and then uses two cross-attention modules to interact it with the features of the dual modalities respectively. In this way, the modality-specific information can well be activated in the multimodal representation. Finally, a feed-forward network is used to fuse two interacted multimodal representations for the further enhancement of the final multimodal representation. In addition, existing learning methods of RGBT trackers either fuse multimodal features into one for final classification, or exploit the relationship between unimodal branches and fused branch through a competitive learning strategy. However, they either ignore the learning of single-modality branches or result in one branch failing to be well optimized. To solve these problems, we propose a dynamically guided learning algorithm that adaptively uses well-performing branches to guide the learning of other branches, for enhancing the representation ability of each branch. Extensive experiments demonstrate that our proposed ProFormer sets a new state-of-the-art performance on RGBT210, RGBT234, LasHeR, and VTUAV datasets. In particular, the improvements of ProFormer on the LasHeR dataset are up to +6.2%/+ 4.1% in PR/SR compared with existing best RGBT tracker. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Tiny Object Tracking: A Large-scale Dataset and A Baseline

arXiv

引用

arXiv 2022年

作者： Zhu, Yabin Li, Chenglong Liu, Yao Wang, Xiao Tang, Jin Luo, Bin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Anhui Higher Education Institutes Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Hefei230601 China Peng Cheng Laboratory Shenzhen China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Anhui Higher Education Institutes Anhui University Hefei230601 China

Tiny objects, frequently appearing in practical applications, have weak appearance and features, and receive increasing interests in meany vision tasks, such as object detection and segmentation. To promote the research and development of tiny object tracking, we create a large-scale video dataset, which contains 434 sequences with a total of more than 217K frames. Each frame is carefully annotated with a high-quality bounding box. In data creation, we take 12 challenge attributes into account to cover a broad range of viewpoints and scene complexities, and annotate these attributes for facilitating the attribute-based performance analysis. To provide a strong baseline in tiny object tracking, we propose a novel Multilevel Knowledge Distillation Network (MKDNet), which pursues three-level knowledge distillations in a unified framework to effectively enhance the feature representation, discrimination and localization abilities in tracking tiny objects. Extensive experiments are performed on the proposed dataset, and the results prove the superiority and effectiveness of MKDNet compared with state-of-the-art methods. The dataset, the algorithm code, and the evaluation code are available at https://***/mmic-lcl/Datasets-andbenchmark-code. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Ekblom Promoting Adaptive Algorithm for System Identification

TechRxiv

引用

TechRxiv 2022年

作者： Huang, Xinqi Li, Yingsong Han, Xiao Tu, Huawei College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China College of Computer Science and Technology Harbin Engineering University Harbin150001 China Department of Computer Science and Information Technology La Trobe University MelbourneVIC3086 Australia

We propose an Ekblom promoting adaptive algorithm (EPAA) which uses Ekblom norm to construct a data reusing scheme to achieve better performance under impulsive noise (IN) environments. By exerting Ekblom-norm constraint on the a posterior error vector, a sliding window cost function is created to realize the EPAA that is derived to reduce IN effects. The derivation and theoretical convergence analysis of the EPAA are presented in detail. The simulation examples are setup to illustrate the superior performance of the EPAA compared to popular data reusing algorithms for system identification under IN environments. © 2022, CC BY.

关键词： Adaptive filtering

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：