检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhidan Ran Xiaobo Lu Wei Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

Video-based person re-identification (Re-ID) aims at matching the video snippets of the same person across multiple cameras. The ubiquitous appearance misalignment is a critical challenge in video person re-identification. Existing alignment-based methods rely on off-the-shelf human parsing models and cannot handle anomalous appearance information (e.g., obstacles and pedestrian interference) in video sequences. In this paper, we propose Anomaly-Aware Semantic Self-Alignment (ASSA), a novel video-based person Re-ID framework that seeks out body parts without prior human topology information and learns part-based feature representations against anomalous information. The proposed ASSA performs part classifier training and part-aligned representation learning alternately. For the classifier training, we design a Salient Region Extraction module to segment the entire foreground from the background in each input frame. Furthermore, a novel Anomaly-Aware Refinement module is proposed to suppress the influence of anomalous interference. Extensive experiments on three prevalent benchmarks demonstrate the effectiveness and superiority of the proposed framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Co-regularization Facial Emotion Recognition Based on Multi-Task Facial Action Unit Recognition 41

A Co-regularization Facial Emotion Recognition Based on Mult...

引用

第41届中国控制会议

作者： Chinonso Paschal Udeh Luefeng Chen Sheng Du Min Li Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Facial emotion recognition helps feed the growth of the future artificial intelligence with the development of emotion recognition,learning,and analysis of different angles of a human face and head *** worlds recent pandemic gave rise to the rapid installment of facial recognition for fewer applications,while emotion recognition is still within the experimental *** current challenges encountered with facial emotion recognition(FER) are the difference between background *** todays world shows us that humans soon need robotics in the most significant role of human perception,attention,memory,decision-making,and human-robot interaction(HRI) needs *** merging the head pose as a combination towards the FER to boost the robustness in understanding emotions using the convolutional neural networks(CNN).The stochastic gradient descent with a comprehensive model is adopted by applying multi-task learning capable of implicit parallelism,inherent and better global optimizer in finding better network *** executing a multi-task learning model using two independent datasets,the experiment with the FER and head pose learning multi-views co-regularization frameworks were subsequently merged with validation accuracy.

关键词： head pose facial expression convolution neural network deep learning emotion recognition

来源：评论

学校读者我要写书评

暂无评论

MoB-NetV2-RVFL: Diagnosis of Coronavirus (COVID-19) from CT images via a Deep Learning Architecture

MoB-NetV2-RVFL: Diagnosis of Coronavirus (COVID-19) from CT ...

引用

2024 Jiangsu Annual Conference on Automation, JACA 2024

作者： Tang, Xiaoyu Chai, Lin Song, Chengze School of Automation Southeast University Jiangsu Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Jiangsu Nanjing210096 China School of Sino-french Engineering Institute Nanjing University of Science and Technology Jiangsu Nanjing China

ISBN: (纸本)9781837242689

Computer-aided diagnosis has emerged as a crucial trend in modern medicine. Recently, CT-based automatic detection algorithms for lung infectious diseases suffer from issues of low accuracy and complex architecture. In this paper, three MoB-NetV2 models (MoB-NetV2-SNN, MoB-NetV2-ELM, and MoB-NetV2-RVFL) for the detection of COVID-19 in CTs are proposed. the MoB-NetV2 model is proposed by inserting batch normalization layers between bottlenecks in MobileNetV2 and substituting the fully connected layer with the Net-1 model (SNN, ELM, RVFL), i.e. MoB-NetV2-SNN, MoB-NetV2-ELM, and MoB-NetV2-RVFL. After comparison, it is found that the proposed MoB-NetV2-RVFL achieves an average accuracy of 93.42% on a private dataset comprising of 2392 images, while the precision is reached at 97.33%. Furthermore, it is demonstrated that our MoB-NetV2-RVFL outperforms other existing algorithms in the literature. High classification accuracy and precision and low computing amount are achieved, thereby enhancing the potential application of the model in the field of medical image-aided diagnosis of COVID-19 virus. © The Institution of Engineering & Technology 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

YOLO-MSP: Effective Cigarette Detection YOLO Network for Surveillance Scenario

YOLO-MSP: Effective Cigarette Detection YOLO Network for Sur...

引用

International Conference on systems and Informatics (ICSAI)

作者： Zhiwei Zhang Xiaobo Lu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

This paper presents an new approach to enhance the detection of smoking behavior using object detection neural networks, focusing on the challenge of small object detection, namely cigarettes in video frames. We introduce a Multi-Spatial Pooling (MSP) bottleneck mechanism integrated into a YOLOv8 backbone, which significantly improves the network's ability to discern smaller objects without compromising real-time inference capabilities. This enhancement facilitates the extraction of relevant features across various scales and efficiently handles the computational overhead, thereby boosting the detection accuracy and operational efficiency. Our results demonstrate a substantial improvement in performance metrics over traditional and existing neural network approaches, making this method highly suitable for real-time applications in diverse scenarios.

关键词： YOLO measurement Computational modeling Surveillance Neural networks Focusing Streaming media Feature extraction Real-time systems Informatics

来源：评论

学校读者我要写书评

暂无评论

Automatic Programming system of Painting Robots for Unstructured Workpieces Spraying 36

Automatic Programming System of Painting Robots for Unstruct...

引用

36th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2021

作者： Liu, Xinkai Xu, Yunhui Zhou, Bo Fang, Fang Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9781665437127

Spraying technology has been applied more and more widely in aeronautical manufacturing field. However, aeronautical test workpieces usually have unstructured and complex shapes, which makes the spraying inefficient and the quality of coating cannot be guaranteed. Therefore, this paper designs an automatic programming and simulation system for aeronautical workpiece spraying. And the kinematics and inverse kinematics modeling of NACHI robot, spraying parameters optimization and trajectory planning of the robot are studied in detail. This paper also designs the simulation experiments on typical aeronautical test workpieces, and the result shows that this system can improve the spraying efficiency and coating thickness effect, which has a certain universality and effectiveness. © 2021 IEEE.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Haptic-Aided Navigation Vehicle: Enhancing Obstacle Detection in Blind Spots and Transparent Object Scenarios

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Li, Mingwang Li, Xinde Zhang, Zhentong Zhang, Zeyu Zhao, Haoming School of Software Southeast University Suzhou Jiangsu215000 China School of Automation Southeast University Nanjing210018 China School of Cyber Science and Engineering Southeast University Nanjing211102 China Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education Nanjing214135 China Nanjing Center for Applied Mathematics Nanjing211135 China Southeast University Shenzhen Research Institute Shenzhen Guangdong518063 China

As autonomous mobile robots are increasingly deployed in complex environments, traditional vision sensors and LiDAR encounter considerable limitations, particularly in detecting obstacles in blind spots or transparent objects. To address the issue of blind spots, we design a specialized haptic sensing structure and develop the haptic-aided navigation vehicle (HANV). This system integrates haptic sensors and LiDAR to deliver comprehensive perception, significantly enhancing close-range obstacle detection in areas that are typically beyond the range of conventional sensors. To tackle the challenge of transparent obstacles, which are often undetected by both vision and LiDAR sensors, we employ a fusion of haptic sensors and LiDAR. The haptic system provides physical contact feedback, ensuring reliable detection of transparent obstacles such as glass, while LiDAR offers long-range sensing capabilities. This combination enables HANV to navigate effectively in environments with transparent obstacles, overcoming the limitations of traditional sensing systems. Experiment results indicate that the proposed haptic and LiDAR integration substantially improves obstacle detection in both blind spots and environments with transparent obstacles. HANV achieves high success rates, minimal collisions, and efficient obstacle avoidance, particularly excelling in complex, confined spaces where conventional systems prove inadequate. These findings emphasize the efficacy of our approach in enhancing navigation performance in dynamic and challenging environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A High-Quality View Synthesis system for Sparse Rgb-D Input

SSRN

引用

SSRN 2024年

作者： Zhao, Ziyu Lu, Xiaobo Zhou, Sifan Chiang, Patrick Y.I.N. School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Key Laboratory of ASIC and System Fudan University Shanghai China

Recent research in neural rendering has achieved impressive results in the field of novel view synthesis. However, high-quality view synthesis with sparse source views remains a challenging task, as the reduction in the number of source views significantly degrades the synthesis quality. In this paper, we present a novel view synthesis system that exploits RGB-D pairs from sparse source views. First, we introduce a two-branch feature extraction network to embed the geometric clues from depth maps into the texture information of color images and fuse it with regularized Fourier mapping features. Second, a distance-aware feature query method, which constructs multi-level feature maps, is proposed to ensure high-fidelity details across different distance views. Then, we apply an occupancy network to perform occupancy prediction on raw point cloud. By integrating occupancy probabilities and extracted features, we use a prediction network with geometric information as an additional input to obtain the color and density of sampled points, and synthesize the target view using neural volume rendering. To prevent model degradation and enhance efficiency, we design an efficient sampling strategy based on Gaussian Mixture Model. Moreover, we introduce pixel-wise local regularization and full-image global geometric regularization to optimize the model. Extensive experiments show that the proposed method can achieve the state-of-the-art results for novel view synthesis with sparse inputs, and the model performance has been significantly improved in different scenarios. © 2024, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Apollonius Partitions Based Pursuit-evasion Game Strategies by Q-Learning Approach 41

Apollonius Partitions Based Pursuit-evasion Game Strategies ...

引用

第41届中国控制会议

作者： Qing Wang KaiQi Wu JianFeng Ye YongBao Wu Lei Xue SEU-Monash Joint Graduate school Southeast University The College of Software Engineering Southeast University School of Automation Southeast UniversityKey Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper studies a classical single pursuer and single evader pursuit-evasion *** pursuer attempts to capture the slower evader who aims to extend its lifetime during the *** simplify this question,requiring the evader to take fixation strategy which is choosing the farthest point in its current dominant region as aimpoint and moving at a constant *** the pursuer is faster than the ***,the speed ratio is a *** instaneous state space will be partitioned into pursuer's dominant zone and evader's dominant zone by the generalized Apollonius *** pursuit strategy is based on minimizing the area of the evader's dominant ***,we propose a supermodular game for this ***,the existence of the Nash equilibrium is *** results based on Q-learning are presented to solve the problem,which shows the effectiveness of this method.

关键词： Pursuit-evasion game Nash equilibrium Q-learning

来源：评论

学校读者我要写书评

暂无评论

MFANet: Mixed Feature Attention Network for Port Lane Detection 42

MFANet: Mixed Feature Attention Network for Port Lane Detect...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhang, Jinwei Su, Jinya Yi, Dewei Yang, Jun Ministry of Education The School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing210096 China University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

ISBN: (纸本)9789887581543

With the advancement of industrial automation and artificial intelligence technology, unmanned port autonomy has gained increasing attention. Port automatic driving technology is a critical component of unmanned autonomous systems, enabling rubber tire gantry cranes (RTGs) to autonomously navigate by detecting port lanes and implementing control commands. In this study, a deep learning-based method is proposed for detecting port lanes in complex port scenes. The method employs the Inception module and attention mechanism to enhance lane feature extraction, and a structural loss is introduced to explicitly constrain the detection results and incorporate the prior characteristics of port lanes. A novel Mixed Feature Attention Network (MFANet) is proposed to implement the method for port lane detection. Experimental results demonstrate that MFANet effectively improves the accuracy of port lane detection while maintaining high computational efficiency. Furthermore, the performance of MFANet is evaluated in a real-world application scenario. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Multiple AMR Rigid Formation control With Collision Avoidance Based On MADDPG 41

Multiple AMR Rigid Formation Control With Collision Avoidanc...

引用

第41届中国控制会议

作者： Kaiqi Wu Qing Wang YongBao Wu Jian Liu Lei Xue The College of Software Engineering Southeast University SEU-Monash Joint Graduate school Southeast University School of Automation Southeast UniversityKey Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Recently,the formation control of multiple autonomous mobile robots(AMRs) have gained significant attention,and autonomous mobile robots(AMRs) have applied to all aspects of our ***-agent reinforcement learning is used to solve the autonomously sequential decision-making problem of agents in a common environment with competition or ***,we present a utility function and a reward function to achieve formation control with collision avoidance for a rigid AMRs system,and build a simulation environment to meet environmental requirements based on MPE.

关键词： Formation control Reinforcement learning Rigid system Collision avoidance

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：