检索结果-内蒙古大学图书馆

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Li, Wenzheng Tian, Lihua Sun, Zhigang Xiao, Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450399029

In industrial production processes, defect inspection plays an important role in reducing the occurrence of failures and improving production efficiency. Data-driven algorithms represented by deep learning have made great progress in recent years, but need to face the problems of small quantity and poor quality of datasets when applied to industrial defect inspection. This paper proposes a layer mask blending-based generative adversarial network (LMBGAN) and optimizes the training process to generate high-quality surface defect samples. LMBGAN generates defect images and layer masks using the defect image decoder and layer mask decoder with the Pixel Shuffle operation. Inspired by the layer mask in computer painting, LMBGAN adopts the input image as the base layer and blends the defect foreground through the layer mask, giving it the ability to focus more on generating upper-layer defect images and reducing unnecessary background changes. LMBGAN additionally introduces adaptive discriminator augmentation and non-saturating logistic loss to promote model convergence under small datasets, effectively alleviating the problem of GAN training difficulties with limited data. The experiment results show that the proposed method can generate high-quality and diverse defect image samples through easily accessible normal samples, thus reducing the difficulty of obtaining rare defect image samples. © 2023 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Underwater image Restoration Based on Improved SwinIR Model 13

Underwater Image Restoration Based on Improved SwinIR Model

引用

13th International Conference on intelligent control and Information processing, ICICIP 2025

作者： Lu, Yanke Li, Fang Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798331516147

image restoration is a classic foundational visual task, aimed at recovering damaged images, such as those affected by compression, blurring, or noise, to high-definition clarity. Although current image enhancement techniques largely rely on convolutional neural networks, the efficient capabilities of Transformers demonstrated in complex visual tasks have not yet been extensively applied in the field of image restoration. This paper presents an optimized image restoration strategy based on the SwinIR model, which is applied to the task of underwater image restoration. In the shallow feature extraction phase, deep separable convolution technology is employed;while in the deep feature extraction phase, a Spatial Gated Feedforward Network (SGFN) is utilized. The experimental data suggests that the novel approach surpasses conventional techniques in effectiveness and has effectively minimized both the model's parameter quantity and computational demands. © 2025 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Demand-Side Frequency control in Power Network Based on Multi-Agent Deep Reinforcement Learning 5

Demand-Side Frequency Control in Power Network Based on Mult...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Liu, Xianggang Liu, Zhi-Wei Chi, Ming Zhang, Yifan Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education College of Artificial Intelligence and Automation Wuhan China

ISBN: (纸本)9798350325294

The integration of renewable energy sources into the power grid has led to new challenges in maintaining the stability of the system frequency. This paper proposes a novel approach to address the Optimal Demand Side Frequency control (ODFC) problem using Multi-Agent Deep Deterministic Policy Gradient (MADDPG) method. The proposed method models the ODFC problem as a Markov game, with centralized training based on multi-agent cooperative self-learning and associative storage service. In the decentralized execution stage, each agent independently outputs control actions to the controlled plant using local observations. Numerical simulations show that the proposed method effectively addresses the ODFC problem with superior performance compared to traditional methods. © 2023 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Combined UAMP and MF Message Passing Algorithm for Multi-Target Wideband DOA Estimation with Dirichlet Process Prior

引用

Tsinghua Science and Technology 2024年第4期29卷 1069-1081页

作者： Shanwen Guan Xinhua Lu Ji Li Rushi Lan Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic TechnologyGuilin 541004China Guilin Huigu Institute of AI Industrial Technology Guilin 541004China School of Information Engineering Nanyang Institute of TechnologyNanyang 473000China

When estimating the direction of arrival (DOA) of wideband signals from multiple sources, the performance of sparse Bayesian methods is influenced by the frequency bands occupied by signals in different directions. This is particularly true when multiple signal frequency bands overlap. Message passing algorithms (MPA) with Dirichlet process (DP) prior can be employed in a sparse Bayesian learning (SBL) framework with high precision. However, existing methods suffer from either high complexity or low precision. To address this, we propose a low-complexity DOA estimation algorithm based on a factor graph. This approach introduces two strong constraints via a stretching transformation of the factor graph. The first constraint separates the observation from the DP prior, enabling the application of the unitary approximate message passing (UAMP) algorithm for simplified inference and mitigation of divergence issues. The second constraint compensates for the deviation in estimation angle caused by the grid mismatch problem. Compared to state-of-the-art algorithms, our proposed method offers higher estimation accuracy and lower complexity.

关键词： wideband direction of arrival(DOA)estimation sparse Bayesian learning(SBL) unitary approximate message passing(UAMP)algorithm Dirichlet process(DP)

来源：评论

学校读者我要写书评

暂无评论

HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation

引用

Chinese Journal of Electronics 2023年第1期32卷 189-198页

作者： GUAN Qi SHENG Zihao XUE Shibei Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management

Real-time six degrees-of-freedom(6D)object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and lightweight model, namely high-resolution 6D pose estimation network(HRPose). We adopt the efficient and small HRNetV2-W18 as a feature extractor to reduce computational burdens while generating accurate 6D poses. With only 33% of the model size and lower computational costs, our HRPose achieves comparable performance compared with state-of-the-art models. Moreover, by transferring knowledge from a large model to our proposed HRPose through output and feature-similarity distillations, the performance of our HRPose is improved in effectiveness and efficiency. Numerical experiments on the widely-used benchmark LINEMOD demonstrate the superiority of our proposed HRPose against state-of-the-art methods.

关键词： Knowledge engineering Computational modeling Pose estimation Grasping Benchmark testing Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Resilience of Microgrid-Integrated Power Systems in Disaster Events Using Reinforcement Learning 1

引用

Chinese intelligent Automation Conference, CIAC 2023

作者： Zha, Zhongyi Wang, Bo Liu, Lei Fan, Huijin Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Artificial Intelligence and Automation School Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9789819961870

ISBN: (纸本)9789819961863

Enhancing the resilience of power systems has become increasingly important to mitigate the negative impact of risk attacks. Integrating microgrids, which are small-scale power grids that can operate independently or in conjunction with the main grid, has emerged as an effective energy source for emergency situations and can avoid power outages. Typhoons, which are inevitable and relatively easy to predict risk attacks, have become one of the contexts to examine power system resilience. In this paper, we propose a reinforcement learning algorithm that combines graph theory knowledge to make decisions for optimizing power system resilience with microgrids under the Typhoon event. The algorithm effectively utilizes graph theory knowledge and reduces the number of decisions required in the optimization process. Numerical experimental results show that compared to traditional methods, the reinforcement learning algorithm can more effectively respond to typhoon changes, achieve flexible economic control, and enhance the resilience of power systems with microgrids. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Lightweight Human Pose Estimation Using Loss Weighted by Target Heatmap 26th

Lightweight Human Pose Estimation Using Loss Weighted by Ta...

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Li, Shiqi Xiang, Xiang Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031376597

Recent research on human pose estimation exploits complex structures to improve performance on benchmark datasets, ignoring the resource overhead and inference speed when the model is actually deployed. In this paper, we lighten the computation cost and parameters of the deconvolution head network in SimpleBaseline and introduce an attention mechanism that utilizes original, inter-level, and intra-level information to intensify the accuracy. Additionally, we propose a novel loss function called heatmap weighting loss, which generates weights for each pixel on the heatmap that makes the model more focused on keypoints. Experiments demonstrate our method achieves a balance between performance, resource volume, and inference speed. Specifically, our method can achieve 65.3 AP score on COCO test-dev, while the inference speed is 55 FPS and 18 FPS on the mobile GPU and CPU, respectively. © 2023, Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Task Allocation and Path Planning for Multiple Destinations Oriented Towards Task Updates 6

Task Allocation and Path Planning for Multiple Destinations ...

引用

6th International Conference on Industrial Artificial Intelligence, IAI 2024

作者： Yang, Yong He, Dingxin Mao, Huantao Chen, Hong Wu, Hongtao Liu, Zhi-Wei Huazhong University of Science and Technology School of Artificial Intelligence and Automation China Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China

ISBN: (纸本)9798350356618

This study addresses the complexities of orchestrating multi-target transportation tasks within multi-agent systems, constrained by load capacity. The primary objective is to engineer an advanced path planning framework that assures collision avoidance and optimal load distribution. Diverging from conventional single-path strategies, this research incorporates load factors and requires continuous dynamic multi-target point and path planning to ensure agents can efficiently navigate through a series of predetermined key points. To address this complex requirement, a two-stage multi-agent task allocation and path planning method is proposed. First, an initial solution is obtained using a suboptimal algorithm, followed by optimization iterations using the large neighborhood search algorithm to improve task allocation. In the second stage, an accelerated algorithm based on priority search is used to plan optimal paths for each agent in a predetermined order. The proposed algorithm's effectiveness is comprehensively evaluated through a series of experimental evaluations and comparisons with the commercial solver Gurobi within a limited time. The results show that the proposed method achieves optimality in both running time and minimum path cost while ensuring the load balance of agents. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Spatio-Temporal Scale Based Affective Neural Network for Emotion Detection in Conversation

A Spatio-Temporal Scale Based Affective Neural Network for E...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Jiang Wang, Xiaoping Lei, Shanglin Zeng, Zhigang Wuhan430074 China Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China Key Laboratory of Brain-inspired Intelligent Systems Hubei Province Wuhan430074 China

ISBN: (纸本)9798350303759

Emotion Detection in Conversation (EDC) has been implemented in numerous domains and is under increasing attention. The EDC task is highly challenging due to the need to incorporate both the context of the utterance and the identity of the participant. Some existing EDC approaches employ redundant network structures and inadequately model contextual utterances, resulting in limited performance gains. In this work, we devise a Spatio-Temporal scale based Affective neural Network (STANet) in a simplistic and efficacious manner. STANet consists of two main components, i.e., spatial scale network and temporal scale network, which are applied to extract spatial scale and temporal scale information in the conversation, respectively. Prior to spatio-temporal scale modeling, we encode the identity information of participants to examine its impact on the performance of emotion detection. We conduct substantial comparative experiments and ablation studies on three conversational emotion datasets, and the results demonstrate that our STANet realizes superior performance without taking advantage of external knowledge. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Memristive Spiking Neural Network Circuit for Bio-inspired Navigation Based on Spatial Cognitive Mechanisms

引用

IEEE Transactions on Biomedical Circuits and Systems 2024年第3期19卷 686-698页

作者： Chen, Zhanfei Wang, Xiaoping Wang, Zilu Yang, Chao Huang, Tingwen Lai, Jingang Zeng, Zhigang School of Mechanical Engineering and Automation Shenzhen518055 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation China Hubei Key Laboratory of Brain-inspired Intelligent Systems Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Guangxi University of Science and Technology School of Computer Science and Technology Liuzhou545006 China Shenzhen University of Advanced Technology School of Computer Science and Control Engineering Shenzhen518055 China

Cognitive navigation,a high-level and crucial function for organisms' survival in nature,enables autonomous exploration and navigation within the environment. However,most existing works for bio-inspired navigation are implemented with non-neuromorphic computing. This work proposes a bio-inspired memristive spiking neural network (SNN) circuit for goal-oriented navigation,capable of online decision-making through reward-based learning. The circuit comprises three primary modules. The place cell module encodes the agent's spatial position in real-time through Poisson spiking;the action cell module determines the direction of subsequent movement;and the reward-based learning module provides a bio-inspired learning method adaptive to delayed and sparse rewards. To facilitate practical application,the entire SNN is quantized and deployed on a real memristive hardware platform,achieving about a 21× reduction in energy consumption compared to a typical digital acceleration system in the forward computing phase. This work offers an implementation idea of neuromorphic solution for robotic navigation application in low-power scenarios. © 2007-2012 IEEE.

关键词： intelligent robots

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：