检索结果-内蒙古大学图书馆

Multi-branch low-light enhancement algorithm based on spatial transformation

Multimedia Tools and Applications 2025年第18期84卷 19647-19667页

作者： Wang, Wenlu Sun, Ying Zou, Chunlong Tang, Dalai Fang, Zifan Tao, Bo Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot010051 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Hydroelectric Design & Maintenance China Three Gorges University Yichang443002 China

Many state-of-the-art low-light image enhancement techniques now suffer from issues like color distortion, detail blurring, and the halo effect, hindering their ability to produce visual effects. This paper presents a multi-branch low-light enhancement algorithm based on spatial transformation to significantly improve the visual impact of images under low-light settings, overcoming the limitations of existing approaches. The process involves dividing the initial low-light picture into three distinct layers. Bootstrap filtering and Contrast Limited Adaptive Histogram Equalization are used to process the main feature layer. Primary feature extraction is used to extract features for the compensation layer, which is then integrated with Contrast Limited Adaptive Histogram Equalization and MSRCR. The auxiliary layer utilizes spatial transformation to apply gamma correction to the V-channel and performs color space transformation and additional processing. Ultimately, these three layers are combined and refined to create the final improved image. Based on the experimental results, the proposed method outperforms the standard MSRCR algorithm by 52.47%, 71.58%, and 12.10%, respectively, on the assessment metrics AG, SD, and IE. LOE declines by 22.3%. The processed image presents a good visual quality, effectively enhancing the image brightness while retaining a large amount of information and improving the image details. This paper proposes an effective method to deal with the problem of low illumination image enhancement, which provides a strong reference for future research and application in related fields. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced control Applications

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 18-36页

作者： Ding Wang Ning Gao Derong Liu Jinna Li Frank L.Lewis IEEE the Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing Laboratory of Smart Environmental Protectionand Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China the School of System Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518055China the Department of Electrical and Computer Engineering University of Illinois at ChicagoChicago IL 60607 USA the School of Information and Control Engineering Liaoning Petrochemical UniversityFushun 113001China the UTA Research Institute the University of Texas at ArlingtonArlington TX 76118 USA

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, ***, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation ***, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

关键词： Adaptive dynamic programming(ADP) advanced control complex environment data-driven control event-triggered design intelligent control neural networks nonlinear systems optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

On a novel tracking differentiator design based on iterative learning in a moving window

引用

control Theory and Technology 2023年第1期21卷 46-55页

作者： Xiangyang Li Rafal Madonski Zhiqiang Gao Senping Tian Key Laboratory of Autonomous Systems and Network Control Ministry of EducationSchool of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510641China Energy and Electricity Research Center Jinan UniversityZhuhai 519070China Department of Electrical and Computer Science Cleveland State UniversityClevelandOH 44115USA

Differential signals are key in control engineering as they anticipate future behavior of process variables and therefore are critical in formulating control laws such as proportional-integral-derivative(PID).The practical challenge,however,is to extract such signals from noisy measurements and this difficulty is addressed first by *** in the form of linear and nonlinear tracking differentiator(TD).While improvements were made,TD did not completely resolve the conflict between the noise sensitivity and the accuracy and timeliness of the *** two approaches proposed in this paper start with the basic linear TD,but apply iterative learning mechanism to the historical data in a moving window(MW),to form two new iterative learning tracking differentiators(IL-TD):one is a parallel IL-TD using an iterative ladder network structure which is implementable in analog circuits;the other a serial IL-TD which is implementable digitally on any computer *** algorithms are validated in simulations which show that the proposed two IL-TDs have better tracking differentiation and de-noise performance compared to the existing linear TD.

关键词： Tracking differentiator(TD) Iterative learning Iterative learning tracking differentiator(IL-TD) Active disturbance rejection control(ADRC)-Two-dimensional system(2-D system)

来源：评论

学校读者我要写书评

暂无评论

Sequential-aware Unsupervised Image Enhancement for Visual Odometry

Sequential-aware Unsupervised Image Enhancement for Visual O...

引用

Chinese control and Decision Conference, CCDC

作者： Jiayan Wan Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China

Visual SLAM or visual odometry is essential for robot navigation and localization. The quality of the images that the robot captures dramatically influences the performance of visual SLAM or visual odometry. In some challenging conditions, such as low light or changing light, the images are of bad quality, with reduced contrast or photometric inconsistency. It is hard to extract enough information for tracking from these kinds of images. In this work, we solve this problem by applying image enhancement, a lightweight yet effective solution. Image enhancement methods could be combined with different visual odometry algorithms as an independent module without significant changes to the entire framework. Standard image enhancement methods focus on enhancing the visual effect of images and are not designed for camera localization. We introduce an unsupervised low-light image enhancement method, adopting 3D clues to form the temporal and scale restrictions. Additionally, we augment the training data with gamma transformation to mimic multiple lighting conditions, enabling the network to handle both low-light and changing-light situations. Extensive experiments are conducted on some illumination-related datasets for visual odometry, and the result verifies the effectiveness of our proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relaxed Stability Analysis and Event-Triggered controller Design for Discrete-Time Positive T-S Fuzzy Networked control Systems

Relaxed Stability Analysis and Event-Triggered Controller De...

引用

Annual Conference of industrial Electronics Society

作者： Xiaoxiao Wang Xiaomiao Li Zhiyong Bao Fucai Liu Yuehao Du Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China

This paper deals with the relaxation stability analysis and event-triggered controller design of discrete-time positive Takagi-Sugeno (T-S) fuzzy networked control systems (FNCSs). The constraints of positive conditions in NCSs bring significant challenges to stability analysis and controller design. A 1-norm event-triggered scheme is proposed for the positive system, which can effectively reduce the frequency of network communication. Since the event-triggered T-S fuzzy controller (ETTSFC) can only observe the latest transmission state after the triggering action, the ETTSFC selects the premise variables different from the T-S fuzzy model, improving design and implementation flexibility. Using the linear copositive Lyapunov function (LCLF), the design criteria of the event-triggered controller to ensure the positivity and stability of the closed-loop system are derived. To relax the sum-of-squares (SOS) based conservative condition, we adopt the Taylor series membership functions (TSMFs) and introduce TSMFs and their approximation error into the stability conditions. Finally, an example is given to illustrate the effectiveness of the design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Decomposition-based Encoder-Decoder Framework for Multi-step Prediction of Burn-Through Point in Sintering Process

A Decomposition-based Encoder-Decoder Framework for Multi-st...

引用

industrial Cyber-Physical Systems (ICPS)

作者： Yuhan Xie Bocun He Xinmin Zhang Zhihuan Song State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China

Sintering process is a critical step in the ironmaking process. Burn-through point (BTP), as a key performance index of sintering ore, has a great influence on the quality of the sintering product. The existing prediction methods attempt to use a single model to establish the relationship between variables. However, due to the strong volatility, uncertainty, and multivariable coupling of sintering process, the traditional prediction model cannot produce reliable predictions. In order to deal with the complex characteristics of sintering process, this paper proposes a decomposition-based encoder-decoder modeling framework, in which a sequence decomposition module is designed to decompose the input time series into different sub-sequences. Then, these sub-sequences are constructed by the encoder-decoder models separately. The effectiveness of the proposed multi-step ahead prediction modeling framework was evaluated in a real-world sintering process. Compared with the traditional prediction modeling framework, the proposed modeling framework has more accurate results in multi-step ahead prediction.

关键词： Couplings Uncertainty Time series analysis Sintering Predictive models Cyber-physical systems Data models

来源：评论

学校读者我要写书评

暂无评论

Research on Traceability Method of Gas Leak for Emergency Auxiliary Support

Research on Traceability Method of Gas Leak for Emergency Au...

引用

Chinese Automation Congress (CAC)

作者： Tingting Cui Huilin Dong Zhi Zhou Yuqi Cao Dibo Hou Guangxin Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China

In the field of environmental emergency, sudden gas leaks cause great harm to the economy and society. In recent years, gas leaks have occurred frequently, and the problem of locating the source of air pollution is mainly divided into two steps: dispersion and traceability. However, the application of mechanism modeling or data-driven modeling methods for dispersion prediction is difficult to meet computational efficiency and prediction accuracy. Conventional source estimation methods also have the disadvantage of local optima in tracing pollution sources. In this paper, we propose a gaussian-machine learning model for gas dispersion prediction using gaussian features as inputs, and the improved particle swarm optimization algorithm that takes into account globally search and optimization. Predicted concentration is utilized as the input of the traceability model. Results demonstrate that this method have better performance on estimating leak location and concentration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects of Combined Stress from Salt and Herbicide on Microbial Remediation of Soil Contaminated by n-Hexadecane and Phenanthrene

引用

China Petroleum Processing & Petrochemical Technology 2022年第2期24卷 126-137页

作者： Liu Bingkun Zuo Shuai Wang Ruirui Dong Kangning Zhang Xiuxia Li Ruyue Hao Boyu Li Jing Yin Linghao Bai Yuhao Song Jiayu Gu Yingying Sun Juan State Key Laboratory of Petroleum Pollution Control Beijing 102206 Department of Environment and Safety Engineering China University of PetroleumQingdao 266580 Department of Computer Science and Technology China University of PetroleumQingdao 266580

In this study,physicochemical,cluster,and high-throughput sequencing analyses were used to investigate the joint effects of salt and herbicide(glyphosate)stress factors on the microbial remediation of soil contaminated by n-hexadecane and *** on the soil’s physical and chemical properties,differences in microbial quantity and enzyme activities were analyzed among the samples,and how that influenced distribution of soil community structure was focused *** 120 days of indoor simulated remediation,the cumulative degradation rate of n-hexadecane decreased by 94.92%(blank control),96.96%(low concentration salt and glyphosate stress group),65.07%(high concentration salt and glyphosate stress group),while that of phenanthrene decreased by 87.33%(blank control),86.25%(low concentration salt and glyphosate stress group),58.45%(high concentration salt and glyphosate stress group).The combined stress of salt and herbicides was capable of lowering the reduction efficiency of organic matter,total nitrogen,and total phosphorus,and also restricting the growth of microorganisms and enzyme *** analysis results indicated that the non-stress group was similar to the low-concentration compound stress group during different remedial period,whereas both of those differed starkly from the high-concentration compound stress ***-throughput sequencing revealed that the dominant soil bacteria phyla shifted from Firmicutes to Actinobacteria within 120 days of remediation.

关键词： oil-contaminated soil cluster analysis common quantity sequencing microorganisms salt stress glyphosate stress

来源：评论

学校读者我要写书评

暂无评论

An Improved Seagull Optimization Algorithm for Flexible Job-shop Scheduling Problem

An Improved Seagull Optimization Algorithm for Flexible Job-...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent Systems

作者： Kai Ma Shijie Yao Shiliang Guo Bin Yang Shuai Li Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China

Job-shop scheduling problem is the core link and key technology to realize smart factory and develop smart manufacturing technology. Among them, the flexible job-shop scheduling problem (FJSP) which is more consistent with the actual production and processing mode has been focused. This paper proposes an improved seagull optimization algorithm(ISOA) for solving the FJSP. The ISOA uses chaos initialization and reverse learning to optimize initial population, and introduces Q-learning to change the fitting parameters to balance global search and local search. In addition, we propose a local search model that is adaptive iterative process to enhance the algorithm's optimization search capability. The results of the experiment proved that the algorithm is superior in terms of optimization speed and scheduling results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous Implicit Indoor Scene Reconstruction with Frontier Exploration

arXiv

引用

arXiv 2024年

作者： Zeng, Jing Li, Yanxu Sun, Jiahao Ye, Qi Ran, Yunlong Chen, Jiming College of Control Science and Engineering Zhejiang University Hangzhou310027 China College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University The Key Key Lab of CS&AUS of Zhejiang Province China

Implicit neural representations have demonstrated significant promise for 3D scene reconstruction. Recent works have extended their applications to autonomous implicit reconstruction through the Next Best View (NBV) based method. However, the NBV method cannot guarantee complete scene coverage and often necessitates extensive viewpoint sampling, particularly in complex scenes. In the paper, we propose to 1) incorporate frontier-based exploration tasks for global coverage with implicit surface uncertainty-based reconstruction tasks to achieve high-quality reconstruction. and 2) introduce a method to achieve implicit surface uncertainty using color uncertainty, which reduces the time needed for view selection. Further with these two tasks, we propose an adaptive strategy for switching modes in view path planning, to reduce time and maintain superior reconstruction quality. Our method exhibits the highest reconstruction quality among all planning methods and superior planning efficiency in methods involving reconstruction tasks. We deploy our method on a UAV and the results show that our method can plan multi-task views and reconstruct a scene with high quality. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

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：