检索结果-内蒙古大学图书馆

ParallelEye Pipeline: An Effective Method to Synthesize Images for Improving the Visual Intelligence of Intelligent Vehicles

引用

IEEE TRANSACTIONS ON systems MAN CYBERNETICS-systems 2023年第9期53卷 5545-5556页

作者： Li, Xuan Wang, Kunfeng Gu, Xianfeng Deng, Fang Wang, Fei-Yue Peng Cheng Lab Dept Math & Theories Shenzhen 518000 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Virtual simulated scenes are becoming a critical part of autonomous driving. In the context of knowledge automation and machine learning, simulated images are widely used for visual environmental perception. However, even the most inspirational applications have not fully exploited the potential of simulated images in solving real-world problems. In this article, we propose a novel framework "ParallelEye Pipeline", which uses image-to-image translation and simulated images to automatically generate realistic synthetic images with multiple ground-truth annotations. Specifically, this method has three steps: first, we use Unity3D software to simulate driving scenarios and generate simulated image pairs (including raw images and six ground-truth labels) from the simulated scenes;second, advanced image-to-image translation algorithms can generate realistic and high-resolution synthetic images from simulated image pairs;third, we exploit publicly datasets, simulated images, and synthetic images to conduct experiments for visual perception. The experimental results suggest: 1) synthetic images and simulated images can improve the performance of detectors in real autonomous driving scenarios and 2) image-to-image translation algorithms can be affected by occlusion condition.

关键词： Annotations Pipelines Autonomous vehicles Generative adversarial networks Task analysis Semantics Visualization Generative adversarial network (GAN) intelligent vehicles object detection simulated scene synthetic image

来源：评论

学校读者我要写书评

暂无评论

Generalized zeroing neural dynamics model for online solving time-varying cube roots problem with various external disturbances in different domains

引用

INFORMATION SCIENCES 2023年第1期623卷 648-670页

作者： Wang, Gang Liu, Yongbai Sun, Yingyi Yu, Junzhi Sun, Zhongbo Changchun Univ Technol Dept Mechatron Engn Changchun 130012 Peoples R China Jilin Agr Univ Coll Econ & Management Changchun 130118 Peoples R China Peking Univ Coll Engn Dept Mech & Engn Sci State Key Lab Turbulence & Complex SystBIC ESAT Beijing 100871 Peoples R China Changchun Univ Technol Dept Control Engn Changchun 130012 Peoples R China

As a basic problem of the nonlinear dynamic model, the online solution of time-varying cube root problem (TVCRP) is widely used in science and engineering. However, the prac-tical system is frequently disturbed by the external factors, which inevitably leads to unknown disturbances in the solution process. Therefore, addressing the TVCRP with high accuracy in non-ideal environment (unknown disturbances) is the basis of solving the non-linear dynamic model. In this work, a noise-suppression zeroing neural dynamics (NSZND) model is investigated and developed from the control perspective to resolve the time -varying or time-invariant cube root problem with the different disturbances (bounded and unbounded disturbances) in real/complex domain. Moreover, the generalized noise -suppression zeroing neural dynamics model with various activation functions is discussed and designed for eliminating the interference of different disturbances to improve the pre-cision and noise immunity of the NSZND model. The global/exponential convergence of the developed models with various disturbances are proved by theoretical analyses. With unbounded disturbance (linear noise), the solving accuracy of the NSZND model is about 101 and 103 times superior to the gradient neural dynamics model and the zeroing neural dynamics model. Finally, the proposed NSZND model is extended to the tensor cube root problem, and the feasibility of the proposed model is verified in this work. Beyong that, dif-ferent fractals are generated by using the proposed model to solve the cube root problem in the complex domain, which provides an interesting idea for advertising design and com-puter graphics.

关键词： Nonlinear dynamic model Time-varying cube root problem Non-ideal environment Global and exponential convergence Theoretical analyses

来源：评论

学校读者我要写书评

暂无评论

A novel robotic visual perception framework for underwater operation

引用

Frontiers of Information Technology & Electronic Engineering 2022年第11期23卷 1602-1619页

作者： Yue LU Xingyu CHEN Zhengxing WU Junzhi YU Li WEN State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Ytech Kuaishou TechnologyBeijing 100085China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China

Underwater robotic operation usually requires visual perception(e.g.,object detection and tracking),but underwater scenes have poor visual quality and represent a special domain which can affect the accuracy of visual *** addition,detection continuity and stability are important for robotic perception,but the commonly used static accuracy based evaluation(i.e.,average precision)is insufficient to reflect detector performance across *** response to these two problems,we present a design for a novel robotic visual perception ***,we generally investigate the relationship between a quality-diverse data domain and visual restoration in detection *** a result,although domain quality has an ignorable effect on within-domain detection accuracy,visual restoration is beneficial to detection in real sea scenarios by reducing the domain ***,non-reference assessments are proposed for detection continuity and stability based on object ***,online tracklet refinement is developed to improve the temporal performance of ***,combined with visual restoration,an accurate and stable underwater robotic visual perception framework is ***-overlap suppression is proposed to extend video object detection(VID)methods to a single-object tracking task,leading to the flexibility to switch between detection and *** experiments were conducted on the ImageNet VID dataset and real-world robotic tasks to verify the correctness of our analysis and the superiority of our proposed *** codes are available at https://***/yrqs/VisPerception.

关键词： Underwater operation Robotic perception Visual restoration Video object detection

来源：评论

学校读者我要写书评

暂无评论

Semantic-enhanced Graph Voxelization for Pillar-based 3D Detection from Point Clouds 25

Semantic-enhanced Graph Voxelization for Pillar-based 3D Det...

引用

IEEE 25th International Conference on Intelligent Transportation systems (ITSC)

作者： Tian, Yonglin Wang, Xiao Shen, Yu Liu, Yuhang Wang, Zilei Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Sci & Technol China Natl Engn Lab Brain Inspired Intelligence Technol Hefei 230027 Peoples R China

ISBN: (数字)9781665468800

ISBN: (纸本)9781665468800

Pillar-based 3D detection simplifies the processing pipelines of feature extraction for irregular point clouds. However, the rigid voxelization adopted by pillar-based methods, inevitably and irreversibly, cuts off the direct connection between plenty of point pairs, thus hindering the modeling of local structures. Besides, it is difficult to handle intractable situations in 3D detection using structural information alone. In this paper, we propose a semantic-enhanced graph voxelization method to improve pillar-based feature extraction from two aspects, i.e., the construction of pillars and the learning of pillar-level features. For pillar construction, a novel voxelization method is proposed to capture more sufficient local structures with graph-based modeling of the relationships between adjacent point pairs. To learn representative features for each pillar, semantic enhancement is adopted by learning context awareness and class awareness pixel by pixel with a front-view-based segmentation branch. Extensive experiments conducted on the KITTI dataset demonstrate the effectiveness of the proposed method. Compared with the baseline, our method achieves 2.81 points and 2.65 points higher performance in 3D detection on KITTI test set for cars and cyclists individually.

关键词： Point cloud compression Three-dimensional displays Image edge detection Semantics Pipelines Context awareness Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Deep Forest With Deep Contours Feature for Leaf Cultivar Classification

引用

IEEE TRANSACTIONS ON FUZZY systems 2022年第12期30卷 5431-5444页

作者： Zheng, Wenbo Yan, Lan Gou, Chao Wang, Fei-Yue Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China Sun Yat sen Univ Sch Intelligent Syst Engn Guangzhou 510275 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Natl Univ Def Technol Res Ctr Mil Computat Expt & Parallel Syst Technol Changsha 410073 Peoples R China

Deep learning is a compelling technique for feature extraction due to its adaptive capacity of processing and providing deeper image information. However, for the task of leaf cultivar classification, the deep learning-based classifier model is unable to extract contour features of leaf images deeply due to the lack of large specialized datasets and expert knowledge annotations. Also, the scale/size of the current leaf cultivar dataset does not meet the needs of deep neural networks (DNNs). In particular, the high model complexity of DNNs implies that deep-learning-based neural networks seem to must require a large dataset to achieve good performance, but facing the fact that the leaf cultivar dataset often is small, even some classes in this kind of datasets contain less than ten images/examples. To overcome these problems and inspired by the resounding success of fuzzy logic, we propose a novel fuzzy ensemble model for leaf cultivar classification. To extract the contours of leaves, we first propose generative adversarial networks-based methods. Second, to improve the ability of feature representation, we present a data augmentation method to transform our contour features. Third, to get the essential features of leaves, we design a novel generation of the fuzzy random forest. Finally, to achieve accurate classification, we design a novel deep learning strategy, namely deep fuzzy representation learning, integrating and cascading a lot of our fuzzy random forests. Experimental results show that our model outperforms other existing state-of-the-arts on three real-world datasets, and performs much better than the original deep forest and DNN-based algorithms particularly.

关键词： Contour feature learning data augmentation deep forest fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

BGL-Net: A Brain-Inspired Global-Local Information Fusion Network for Alzheimers Disease Based on sMRI

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systems 2023年第3期15卷 1161-1169页

作者： Fan, Chen-Chen Yang, Hongjun Peng, Liang Zhou, Xiao-Hu Ni, Zhen-Liang Zhou, Yan-Jie Chen, Sheng Hou, Zeng-Guang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn CASIA MUST Joint Lab Intelligence Sci & Technol Macau Peoples R China

Alzheimer's disease (AD) is an irreversible neurodegenerative disease, the most common form of dementia, affecting millions worldwide. Neuroimaging-based early AD diagnosis has become an effective approach, especially by using structural magnetic resonance imaging (sMRI). The convolutional neural network (CNN)-based method is challenging to learn dependencies between spatially distant positions in the various brain regions due to its local convolution operation. In contrast, the graph convolutional network (GCN)-based work can connect the brain regions to capture global information but is not sensitive to the local information in a single brain region. Unlike a separate CNN or GCN-based method, we proposed a brain-inspired global-local information fusion network (BGL-Net) to diagnose AD. It essentially inherits the advantages of both CNN and GCN. The experiments on three public data sets demonstrate the effectiveness and robustness of our BGL-Net. Our method achieved the best performance on three popular public data sets compared with the existing CNN and GCN-based methods. In addition, our visualization results of the learned brain connection on AD and normal people agree with many current AD clinical research.

关键词： Alzheimer's disease (AD) cognitive assessment convolutional neural networks (CNNs) graph neural networks structural magnetic resonance imaging (sMRI)

来源：评论

学校读者我要写书评

暂无评论

On the Gaussian Filtering for Nonlinear Dynamic systems Using Variational Inference 27

On the Gaussian Filtering for Nonlinear Dynamic Systems Usin...

引用

27th International Conference on Information Fusion, FUSION 2024

作者： Liu, Yi Li, Xi Yang, Le Mihaylova, Lyudmila Li, Ji University of Canterbury Department of Electrical and Computer Engineering Christchurch New Zealand National University of Defense Technology State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems Changsha China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Locaris Electronic Technology Co. Ltd Zhengzhou China

ISBN: (纸本)9781737749769

This paper introduces a new variational Gaussian filtering approach for estimating the state of a nonlinear dynamic system. We first assume that the predictive distribution of the state is Gaussian and derive an iterative method for updating the state posterior in the natural parameter space through KullbackLeibler divergence minimization. The obtained update rule is the same as that of the conjugate-computation variational inference technique in Bayesian learning. The derivation here is simpler and more insightful. We then impose a Wishart prior on the inverse of the state prediction covariance to take into account the impact of approximating the state predictive distribution using a Gaussian density on the state posterior estimation. The prediction covariance is identified jointly with the state using variational inference and the established state posterior update rule to achieve the desired Gaussian filtering. Simulation study examines the performance of the proposed filtering framework in target tracking based on bearing and range measurements. © 2024 ISIF.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Integrating Sustainability in Future Traffic Lighting: Designing Efficient Light systems for Vehicle, Road, and Traffic

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第1期9卷 65-68页

作者： Zhou, Shaodong Chen, Jicheng Teng, Siyu Zhang, Hui Wang, Fei-Yue Guangzhou Co Ltd Elect Facil Guangzhou 511447 Peoples R China Beihang Univ Sch Transportat Sci & Engn Beijing 100191 Peoples R China Hong Kong Baptist Univ Kowloon Hong Kong 999077 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Engn Macau 999078 Peoples R China

Lighting systems in intelligent transportation system (ITS) can play a crucial role in promoting sustainability through various measures, including enhanced driving safety, energy efficiency and environmental protection. This letter presents a framework for integrating sustainable development goals into ITS lighting systems. We first explore the necessity of headlights in future traffic systems, particularly in the context of autonomous vehicles (AVs). Moreover, we discuss active safety technologies, such as night perception enhancement and collaborative lighting in connected vehicles, which contribute to enhancing safety during nighttime driving. Next, the letter analyzes the impact of vehicle-to-infrastructure (V2I) communication on intelligent street light systems. We propose a novel street light perception enhancement framework based on V2I, along with an enhanced lighting scheme for faulty vehicles. Lastly, the letter addresses the importance of energy conservation in future networked street lighting system. Several energy-saving schemes, including demand-based lighting and time-of-day optimization, are discussed, emphasizing the need for efficient energy management and sustainable practices in lighting infrastructure. As a summary of a part of Distributed/Decentralized Hybrid Workshop on Sustainability for Transportation and Logistics (DHW-STL), the letter aims to contribute to the development of sustainable lighting systems.

关键词： Lighting Roads Autonomous vehicles Safety Pedestrians Sustainable development Intelligent sensors Sustainability lighting system autonomous vehicles (AVs) intelligent connected technologies

来源：评论

学校读者我要写书评

暂无评论

Heuristic rank selection with progressively searching tensor ring network

引用

complex & INTELLIGENT systems 2022年第2期8卷 771-785页

作者： Li, Nannan Pan, Yu Chen, Yaran Ding, Zixiang Zhao, Dongbin Xu, Zenglin Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China Harbin Inst Technol Shenzhen Shenzhen Peoples R China Pengcheng Lab Shenzhen Peoples R China

Recently, tensor ring networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named progressively searching tensor ring network search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100, UCF11 and HMDB51, achieving the state-of-the-art performance.

关键词： Tensor ring networks Rank selection Progressively search Image classification

来源：评论

学校读者我要写书评

暂无评论

Boundary vibration suppression for a flexible three-dimensional marine riser against unknown sensor and actuator faults

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR control 2021年第5期31卷 1438-1451页

作者： Ji, Ning Liu, Jinkun Yang, Hongjun Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China

In this article, boundary control strategy is adopted to suppress the vibration of a flexible three-dimensional (3D) marine riser simultaneously against both sensor and actuator faults. The flexible 3D marine riser is a distributed parameter system modeled as partial differential equations. During normal operation of the system, all the system components will behave optimally. However, if the sensor and actuator appear fault, the system will work abnormally. While the sensor is faulty, the output signal of the sensor will have errors, and this error signal will be the input signal of the actuator. In terms of actuator fault, once the actuator appears fault problem, the actuator should make up for the fault and continue working for the sake of safety. In this work, the fault degree of sensors and actuators are unknown and the boundary control schemes using Nassbaum function are developed for fault compensation. The system stability is proven by introducing an appropriate Lyapunov function. Finally, the simulation results verify the accuracy of the proposed control laws.

关键词： actuator fault boundary control flexible three‐ dimensional marine riser sensor fault vibration suppression

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：