检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Pan, Zhiyu Chen, Yinpeng Zhang, Jiale Lu, Hao Cao, Zhiguo Zhong, Weicai Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Huawei CBG Consumer Cloud Service Search Product & Big Data Platform Department China

Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of composition from annotated cropping boxes. However, the bias of annotations leads to quasi-trivial recomposing results, which has an obvious tendency to the average location of training samples. The crux of this predicament is that the task is naively treated as a box regression problem, where rare samples might be dominated by normal samples, and the composition patterns of rare samples are not well exploited. Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, i.e., similar composition patterns. We propose a novel Contrastive Composition Clustering (C2C) to regularize the composition features by contrasting dynamically established similar and dissimilar pairs. In this way, common composition patterns of multiple images can be better summarized, which especially benefits the rare samples and endows our model with better generalizability to render nontrivial results. Extensive experimental results show the superiority of our model compared with prior arts. We also illustrate the philosophy of our design with an interesting analytical visualization. Copyright © 2023, The Authors. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Early Forest Fire Recognition Method Based on C-GhostNet Network 5

Early Forest Fire Recognition Method Based on C-GhostNet Net...

引用

5th International Symposium on Autonomous Systems, ISAS 2022

作者： Li, Mengna Zhang, Youmin Mu, Lingxia Xin, Jing Yu, Ziquan Jiao, Shangbin Liu, Han Xie, Guo Yi, Yingmin Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Shaanxi Xi'an710048 China Concordia University Industrial and Aerospace Engineering Department of Mechanical MontrealQCH3G 1M8 Canada Nanjing University of Aeronautics and Astronautics College of Automation Engineering Nanjing211106 China Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an Shaanxi 710048 China

ISBN: (纸本)9781665487085

Early forest fire image recognition plays an important role in timely fire fighting. This paper proposes an early forest fire recognition method based on C-GhostNet network. The C-GhostNet network is an improved version of GhostNet, which mainly consists of a series of c-ghost bottlenecks, each c-ghost bottleneck mainly consists of two c-ghost modules. Through the concat operation and channel shuffle, the c-ghost module establishes the relationship between the input data and the output features generated by the original ghost module, so that GhostNet network has the ability to capture contextual features. The experimental results show that the C-GhostNet network achieves better recognition performance than GhostNet without introducing additional computational load, and the running speed reaches about 20FPS, which basically realizes real-time recognition. In addition, like GhostN et, the C-GhostNet network is also a lightweight network. © 2022 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Whale optimisation algorithm with role labour division for multimodal optimisation

引用

International Journal of Innovative Computing and Applications 2024年第1期15卷 26-37页

作者： Wu, Bowen Xiao, Renbin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Hubei Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education of China Huazhong University of Science and Technology Hubei Wuhan430074 China

The multimodal optimisation problem challenges the balance between diversity and convergence, which poses a great degree of challenge to traditional population-based intelligence optimisers. The whale optimisation algorithm has the limitation of easily falling into local optimum when facing multimodal optimisation. To address this problem, this paper proposes a whale optimisation algorithm with role labour division (WOA-RDL). In WOA-RDL, a multi-stage role division of labour mechanism is designed to divide the optimisation process into two stages of group hunting. In the first stage, the task allocation in the hunting process is considered as two types of search tasks: exploration and exploitation. The external environmental stimulus of the task and the internal response threshold of the individual were designed to allow individuals to switch between exploration and exploitation tasks flexibly. In the second stage, the distribution mechanism of different roles was designed to simulate the 'strong to weak' distribution rule for the distribution of results after the hunt. The elite roles are selected to further strengthen their capabilities or remain robust, while the inferior roles are predicted and eliminated to improve the overall optimisation of the population and reduce the risk of falling into a local optimum. The results of the optimisation experiments using multimodal, unimodal, CEC2017 combined functions and CEC2009 dynamic functions to validate the effectiveness of the algorithm. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast Full-frame Video Stabilization with Iterative Optimization

arXiv

引用

arXiv 2023年

作者： Zhao, Weiyue Li, Xin Peng, Zhan Luo, Xianrui Ye, Xinyi Lu, Hao Cao, Zhiguo 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 Department of Computer Science University of Albany AlbanyNY12222 United States

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multiframe fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis

arXiv

引用

arXiv 2022年

作者： Li, Xingyi Hong, Chaoyi Wang, Yiran Cao, Zhiguo Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China S-Lab Nanyang Technological University Singapore

We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in self-occluded areas. This is because a single view only provides limited information. We observe that man-made objects usually exhibit symmetric appearances, which introduce additional prior knowledge. Motivated by this, we investigate the potential performance gains of explicitly embedding symmetry into the scene representation. In this paper, we propose SymmNeRF, a neural radiance field (NeRF) based framework that combines local and global conditioning under the introduction of symmetry priors. In particular, SymmNeRF takes the pixel-aligned image features and the corresponding symmetric features as extra inputs to the NeRF, whose parameters are generated by a hypernetwork. As the parameters are conditioned on the image-encoded latent codes, SymmNeRF is thus scene-independent and can generalize to new scenes. Experiments on synthetic and real-world datasets show that SymmNeRF synthesizes novel views with more details regardless of the pose transformation, and demonstrates good generalization when applied to unseen objects. Code is available at: https://***/xingyi-li/SymmNeRF. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Ship Power Sharing Strategy Based on Shapley Value Method and Cartel Mechanism

A Ship Power Sharing Strategy Based on Shapley Value Method ...

引用

Complex Systems and intelligent Science (CSIS-IAC), International Annual Conference on

作者： Zhengxu Zhang Jie Yang Kai Ma Shiliang Guo Hui Li School of Electrical Engineering Yanshan University Qinhuangdao China Key Laboratory of Power Electronics for Energy Conservation and Drive Control of Hebei Province Yanshan University Qinhuangdao China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China Key Laboratory of Intelligent Control and Neural Information Processing of the Ministry of Education Yanshan University Qinhuangdao China

ISBN: (数字)9798331504755

ISBN: (纸本)9798331504762

With the development of the maritime industry, the number and capacity of existing port cold-ironing (CI) equipment can no longer meet the power demand of ships during berthing, resulting in significant carbon emissions from ships within the port area. Therefore, a ship power sharing strategy based on Shapley value method and Cartel mechanism is proposed. Firstly, the rolling optimization model of ship power scheduling is established to adjust the ship power scheduling strategy according to the real-time information. Secondly, the cooperative game model of ship power sharing is established, and the cost sharing among cooperative ships is realized by Shapley value method. Finally, in order to reduce the situation that ships increase their own profits by deviating from cooperation and affect the overall profits, this paper introduces Cartel mechanism to punish the behavior of deviating from cooperation. The simulation results show that the power sharing strategy proposed in this paper can reduce the total ship cost and carbon emission by 5.28% and 3.78%, respectively. The introduction of Cartel mechanism can increase the cost of non-cooperative behavior, thus ensuring that all ships take cooperative behavior. The power sharing strategy based on Shapley method and Cartel mechanism proposed in this paper is helpful to the construction of green ports.

关键词： Costs Job shop scheduling Optimization models Simulation Carbon dioxide Microgrids Games Seaports Real-time systems Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

A Parallel Read-Write Circuit Design for Driving Memristor Crossbar Array

A Parallel Read-Write Circuit Design for Driving Memristor C...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Ningye Jiang Mingxuan Jiang Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

Memristor crossbar array is considered as a promising circuit module for accelerating neural networks. Because the memristor is tunable and multi-state, it is important to design applicable Read-Write (RW) circuit for driving memristor crossbar array. In this paper, a novel RW circuit based on analog circuits is proposed for tuning memristors in high-dimensional array parallelly, which is scalable and low-overhead. The standalone RW circuit schematic is presented for reading/writing single memristor and verified in circuit simulation. Then, we extend and apply this circuit into a two-dimensional memristor crossbar array. The performance of memristor crossbar array controlled by designed RW circuits is verified via the simulations under various machine learning datasets. The comparison with related works is presented, which demonstrates the advantages of the proposed RW circuit regarding overhead and anti-error.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity Beam Selection Method for MmWave Massive MIMO Systems

A Low Complexity Beam Selection Method for MmWave Massive MI...

引用

Ubiquitous Communication (Ucom), International Conference on

作者： Chunhua Zhu Qinwen Ji Xinying Guo The Key Laboratory of Grain Information Processing and Control The Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Zhengzhou China Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou China

The levels of inter-user interference (IUI) usually vary due to the different geographical locations of users, but, most existing beam selection methods apply the same beam selection criteria for all users, which is detrimental to maintain an attractive trade-off between complexity and system performance. Considering the discrepancy of IUI comprehensively, a low complexity beam selection method for millimeter-wave massive multiple-input multiple-output (MIMO) systems is proposed. Firstly, a candidate beam set (CBS) is constructed in light of the sparsity and power distribution of the beamspace channel, thereby all users are classified into non-interfering users (NIUs), low-interference users (LIUs) and high-interference users (HIUs). For NIUs, the beams with large power are selected from CBS under the magnitude maximization (MM) criterion; for LIUs, a novel MM criterion with a tabu list is designed, which can effectively tackle the drawback of assigning shared beams in traditional MM; for HIUs, the incremental algorithm based on the sum-rate maximization criterion is developed to find the optimal beams from CBS. Simulation results validate that the proposed method can achieve almost the same sum-rate performance as the existing methods with the lower computational complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Evasion Strategy of Aircraft Based on Deep Reinforcement Learning 14th

Research on Evasion Strategy of Aircraft Based on Deep Reinf...

引用

14th International Conference on Genetic and Evolutionary Computing, ICGEC 2021

作者： Li, Ye Zhang, Lin Wang, Kaixuan Zhang, Fuquan Fan, Yi China Academy of Launch Vehicle Technology Beijing100076 China Capital Aerospace Machinery Company Beijing100076 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9789811684296

In order to improve the autonomous penetration capability of aircraft, a method for generating aircraft maneuver avoidance strategies based on deep reinforcement learning is proposed. In order to solve the sparse reward problem of penetration reinforcement learning, the initialization process and sampling method of deep Q Network are improved, and the convergence efficiency of the learning algorithm is improved. Firstly, a penetration threat scene and an offensive and defensive confrontation motion model are established, and the relative motion state of the interceptor and the typical maneuver mode of the balanced flight section are selected as the state space and the action space. In the learning process, the aircraft is used as an agent to perform a reinforcement learning exploration process through confrontation simulations to train the maneuver value network so that it can finally make autonomous decisions based on the threat situation. Finally, the simulation experiment results show that the algorithm proposed in this paper can effectively generate maneuver penetration strategies and support the intelligent game of aircraft. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Resource Allocation via Accelerated Saddle Point Dynamics

引用

IEEE/CAA Journal of Automatica Sinica 2021年第9期8卷 1588-1599页

作者： Wen-Ting Lin Yan-Wu Wang Chaojie Li Xinghuo Yu School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074 Key Laboratory of Image Processing and Intelligent Control Ministry of EducationHuazhong University of Science and TechnologyWuhan 430074China School of Electrical Engineering and Telecommunications University of New South WalesSydney NSW 2052Australia School of Engineering Royal Melbourne Institute of Technology(RMIT University)Melbourne VIC 3000Australia

In this paper,accelerated saddle point dynamics is proposed for distributed resource allocation over a multi-agent network,which enables a hyper-exponential convergence ***,an inertial fast-slow dynamical system with vanishing damping is introduced,based on which the distributed saddle point algorithm is *** dual variables are updated in two time scales,i.e.,the fast manifold and the slow *** the fast manifold,the consensus of the Lagrangian multipliers and the tracking of the constraints are pursued by the consensus *** the slow manifold,the updating of the Lagrangian multipliers is accelerated by inertial ***-exponential stability is defined to characterize a faster convergence of our proposed algorithm in comparison with conventional primal-dual algorithms for distributed resource *** simulation of the application in the energy dispatch problem verifies the result,which demonstrates the fast convergence of the proposed saddle point dynamics.

关键词： Accelerated saddle point dynamic distributed resource allocation hyper-exponential stability power dispatch

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：