检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenzheng Zeng Yang Xiao Sicheng Wei Jinfang Gan Xintao Zhang Zhiguo Cao Zhiwen Fang Joey Tianyi Zhou Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Biomedical Engineering Southern Medical University Guangzhou China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou China Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from uncon-strainedfilms to reveal “in the wild“ characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counter-parts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

有向动态网络的自发恢复（英文）

引用

Engineering 2024年第6期 208-214页

作者：刘雪明闫贤 H.Eugene Stanley School of Artificial Intelligence and Automation & The MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems & the Key Laboratory of Image Processing Huazhong University of Science and Technology Center for Polymer Studies Department of Physics Boston University

Complex networked systems, which range from biological systems in the natural world to infrastructure systems in the human-made world, can exhibit spontaneous recovery after a failure; for example, a brain may spontaneously return to normal after a seizure, and traffic flow can become smooth again after a jam. Previous studies on the spontaneous recovery of dynamical networks have been limited to undirected networks. However, most real-world networks are directed. To fill this gap, we build a model in which nodes may alternately fail and recover, and we develop a theoretical tool to analyze the recovery properties of directed dynamical networks. We find that the tool can accurately predict the final fraction of active nodes, and the prediction accuracy decreases as the fraction of bidirectional links in the network increases, which emphasizes the importance of directionality in network dynamics. Due to different initial states, directed dynamical networks may show alternative stable states under the same control parameter, exhibiting hysteresis behavior. In addition, for networks with finite sizes, the fraction of active nodes may jump back and forth between high and low states, mimicking repetitive failure-recovery processes. These findings could help clarify the system recovery mechanism and enable better design of networked systems with high resilience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Fault Detection Observer Design using Excluding Degree

Optimal Fault Detection Observer Design using Excluding Degr...

引用

IEEE Conference on Decision and Control

作者： Feng Xu Yiming Wan Ye Wang Division of Information Science and Technology Shenzhen International Graduate School Tsinghua University Shenzhen P.R. China School of Artificial Intelligence and Automation Huazhong University of Science and Technology and Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan P.R. China Department of Electrical and Electronic Engineering The University of Melbourne Parkville VIC Australia

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper proposes a novel optimal gain design method for robust fault detection using set-valued observers. First, a new fault detection performance specification is proposed for set-valued observers based on a new notion named the excluding degree of the origin from a zonotope. Second, a fractional programming problem is formulated to describe fault detection optimality of set-valued observers. Third, optimal fault detection gains are obtained by solving the fractional programming problem. Finally, numerical examples are used to illustrate the effectiveness of the proposed method.

关键词： Fault detection Design methodology Observers Programming Computational complexity Optimization Numerical stability

来源：评论

学校读者我要写书评

暂无评论

V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results

arXiv

引用

arXiv 2024年

作者： Wang, Jiaqi Zang, Yuhang Zhang, Pan Chu, Tao Cao, Yuhang Sun, Zeyi Liu, Ziyu Dong, Xiaoyi Wu, Tong Lin, Dahua Chen, Zeming Wang, Zhi Meng, Lingchen Yao, Wenhao Yang, Jianwei Wu, Sihong Chen, Zhineng Wu, Zuxuan Jiang, Yu-Gang Wu, Peixi Chai, Bosong Nie, Xuan Yan, Longquan Wang, Zeyu Zhou, Qifan Wang, Boning Huang, Jiaqi Xu, Zunnan Li, Xiu Yuan, Kehong Zu, Yanyan Hao, Jiayao Gao, Qiong Jiao, Licheng Shanghai AI Laboratory China Chinese University of Hong Kong Hong Kong Shanghai Jiao Tong University China Wuhan University China Shenzhen International Graduate School Tsinghua University China Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft Research Redmond United States University of Science and Technology of China China Zhejiang University China Northwestern Polytechnical University China Northwest University China Tsinghua Shenzhen International Graduate School Tsinghua University China Intelligent Perception and Image Understanding Lab Xidian University China

Detecting objects in real-world scenes is a complex task due to various challenges, including the vast range of object categories, and potential encounters with previously unknown or unseen objects. The challenges necessitate the development of public benchmarks and challenges to advance the field of object detection. Inspired by the success of previous COCO [15] and LVIS [11] Challenges, we organize the V3Det Challenge 2024 in conjunction with the 4th Open World Vision Workshop: Visual Perception via Learning in an Open World (VPLOW) at CVPR 2024, Seattle, US. This challenge aims to push the boundaries of object detection research and encourage innovation in this field. The V3Det Challenge 2024 consists of two tracks: 1) Vast Vocabulary Object Detection: This track focuses on detecting objects from a large set of 13204 categories, testing the detection algorithm's ability to recognize and locate diverse objects. 2) Open Vocabulary Object Detection: This track goes a step further, requiring algorithms to detect objects from an open set of categories, including unknown objects. In the following sections, we will provide a comprehensive summary and analysis of the solutions submitted by participants. By analyzing the methods and solutions presented, we aim to inspire future research directions in vast vocabulary and open-vocabulary object detection, driving progress in this field. Challenge homepage: https://***/challenge. © 2024, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards Environmentally Adaptive Odor Source Localization: Fuzzy Lévy Taxis Algorithm and Its Validation in Dynamic Odor Plumes

Towards Environmentally Adaptive Odor Source Localization: F...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Xinxing Chen Jian Huang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

In this paper, we propose a bio-inspired Fuzzy Lévy Taxis algorithm to solve the robotic odor source localization problem in dynamic odor plumes. According to the proposed algorithm, the robot is programmed to move for a length with a turning angle at each step until reaching the odor source. The movement length and the turning angle follow two specific probability distribution, of which the parameters are adaptive through a fuzzy logic system. The proposed algorithm was compared with the Adaptive Lévy Taxis algorithm in simulated pseudo-Gaussian plumes. Our proposed algorithm shows a higher success rate and efficiency. The algorithm has also been systematically evaluated in simulated filament-based odor plumes under various environmental conditions. The results revealed that the performance of the proposed algorithm is consistently good in various environmental conditions in terms of success rate, number of steps and distance overhead to find the odor source.

关键词： Public transportation Heuristic algorithms Turning Robot sensing systems Adaptation models Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Battery Parameter Identification Using Recursive Least Squares with Variable Directional Forgetting

Battery Parameter Identification Using Recursive Least Squar...

引用

International Conference on Control and Automation (ICCA)

作者： Kun Zhu Yiming Wan Chenou Li Xin Luo Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728190938

ISBN: (纸本)9781728190945

An accurate battery model is important to perform various tasks of battery management. Battery model parameters change with working conditions, thus requiring continuous update for parameter estimation. The recursive least-squares algorithm with a forgetting strategy is widely used to estimate time-varying parameters online. However, the online data vary with battery operations, so the data may fail to contain sufficient excitation. When the online data is not persistently exciting, most existing forgetting strategies in battery literature suffer from covariance blowup, which means the algorithm cannot identify parameters reliably. In order to cope with non-persistent excitation, a recursive least-squares algorithm with variable direction forgetting is presented in this paper for battery parameter estimation. Instead of discounting all old information, it performs forgetting only in the direction of sufficient excitation. The forgetting factor can adaptively adjust based on excitation, which enhances trade-off between stability and tracking capability of the algorithm. A battery simulation model with time-varying parameters is used to illustrate the effectiveness of our proposed algorithm.

关键词： Batteries State of charge Electronic countermeasures Computational modeling Parameter estimation Load modeling Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Fault detection of lithium-ion batteries subject to probabilistic parametric uncertainties 11

Fault detection of lithium-ion batteries subject to probabil...

引用

11th CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2019

作者： Liu, Yuhao Wan, Yiming Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

ISBN: (纸本)9781728106816

The fault detection task in lithium-ion battery management system (BMS) is critical to the safety and reliability of rechargeable and hybrid electric vehicles. To explicitly account for inevitable errors of battery model parameters, a robust fault detection method is proposed in this paper. The residual generator is established by exploiting an equivalent circuit model. The effect of uncertainties on the residual is parametrized as polynomial dependence on probabilistic uncertain parameters and noises. Then Gaussian mixtures are adopted to derive the residual distribution. To account for residual uncertainties in the detection decision, the weighted sum of distances from the generated residual to each Gaussian component of the residual distribution is proposed. Simulation results illustrate that our proposed method outperforms the conventional approach that does not consider parametric uncertainties. © 2019 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

keypoint-Based Feature Matching For Partial Person Re-Identification

Keypoint-Based Feature Matching For Partial Person Re-Identi...

引用

IEEE International Conference on image processing

作者： Chuchu Han Changxin Gao Nong Sang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

As a derivative of person re-identification (re-ID), partial re- ID aims to retrieve a partial pedestrian across holistic person images captured by non-overlapping cameras. This task is more challenging and closer to real-world applications. Since we cannot locate the part of the partial image, the misaligned region compromises the performance greatly when directly (a) compare a partial pedestrian with a holistic one. To alleviate this issue, we propose a keypoint-Based Feature Matching (KBFM) network, which constructs a simple and effective framework for partial re-ID. Specifically, our architecture explicitly leverages the keypoints generated by pose estimation. Based on the visible keypoints, coordinates of the corresponding visible region can be computed. And the keypoint-based feature embeddings can be generated by bilinear sampling. When matching two images, we extract their features on the basis of shared visible keypoints, avoiding the misalignment and disturbance. Moreover, considering the triplet loss cannot be flexibly built in the partial re-ID pipeline, we improve the original sampling method and achieve significant performance. Extensive experimental results on two widely used benchmarks demonstrate significant performance improvements of our method over most state-of-the-art methods.

关键词： Feature extraction Cameras Task analysis Pose estimation Training Pipelines Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A New Control System Based on An Improved PID Neural Network Controller for Landslide System Control

A New Control System Based on An Improved PID Neural Network...

引用

Chinese Control Conference (CCC)

作者： Ying Zhang Shu Sun Cheng Lian Xiaoping Wang School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

In this paper, a new control system based on the improved PID neural network controller (PIDNNC) is designed to control the landslide displacement. In the control system, the fuzzy comprehensive judgement model of landslide system is established to judge whether the system needs to be controlled and give the expected displacement. To solve the problem of random initialization in PIDNNC, This paper proposed an improved PIDNNC based on fuzzy PID controller (F-PIDNNC). The fuzzy PID controller is used to obtain the proportional, integral and differential coefficients k p , k i and k d . Then the obtained parameters are taken as the initial weights of PIDNN. The effectiveness of the proposed control system is simulated on Baishuihe and Shiliushubao landslides. The results show that the proposed control system based on F-PIDNNC is much accurate and faster than the traditional one-dimensional fuzzy PID controller and PIDNNC.

关键词： Terrain factors Control systems Neural networks Neurons Predictive models Stability criteria

来源：评论

学校读者我要写书评

暂无评论

3D Virtual Sand Table Display System of Industrial Park Based on Augmented Reality

3D Virtual Sand Table Display System of Industrial Park Base...

引用

Industrial Application of Artificial Intelligence (IAAI), IEEE International Conference on

作者： Hongyan Lu Jie He Caichun Cen School of Big Data and Software Engineering Wuzhou University Wuzhou China Key Laboratory of Image Processing and Intelligent Information System at Guangxi University Wuzhou University Wuzhou China School of Electronic and Information Engineering Wuzhou University Wuzhou China

ISBN: (纸本)9781665465816

To improve the interactivity of 3D virtual sand table displays, an industrial park 3D virtual sand table display system based on augmented reality is designed. The system consists of multiple modules. The design of the animation browsing module is based on the roaming walking model environment. The walking and roaming module can enable participants to experience the real visual and tactile virtual space in the process of input browsing. In the surrounding environment and traffic condition module, the surrounding environment and traffic condition display are created by means of static pictures and picture buttons. The VRML scene space module is responsible for creating objects such as VRML viewpoints. Scenario module transformation completes event transmission through routing. The virtual sand table VRML optimization modeling module is responsible for constructing the virtual sand table VRML model. The function of the multiperson collaboration module is to provide collaboration capability for plotting and discussion functions. In the multiuser detection module, yolov2 is used for multiuser detection. The augmented reality hardware module is mainly composed of computers and hololens. Through the combination of hardware and software, a three-dimensional virtual sand table display of an industrial park is realized. The test results show that the performance of the designed system is good and can meet the design requirements.

关键词： Multiuser detection Legged locomotion Visualization Three-dimensional displays Computational modeling Display systems Collaboration

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：