检索结果-内蒙古大学图书馆

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Xinyi Zhao, Weiyue Liu, Tianqi Huang, Zihao Cao, Zhiguo Li, Xin 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

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods,DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS. Copyright © 2023, The Authors. All rights reserved.

关键词： Geometry

CSP-Net: Common Spatial Pattern Empowered Neural Networks for EEG-Based Motor imagery Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Xue Meng, Lubin Chen, Xinru Xu, Yifan Wu, Dongrui Key Laboratory of The Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

Electroencephalogram-based motor imagery (MI) classification is an important paradigm of non-invasive brain-computer interfaces. Common spatial pattern (CSP), which exploits different energy distributions on the scalp while performing different MI tasks, is very popular in MI classification. Convolutional neural networks (CNNs) have also achieved great success, due to their powerful learning capabilities. This paper proposes two CSP-empowered neural networks (CSP-Nets), which integrate knowledge-driven CSP filters with data-driven CNNs to enhance the performance in MI classification. CSP-Net-1 directly adds a CSP layer before a CNN to improve the input discriminability. CSP-Net-2 replaces a convolutional layer in CNN with a CSP layer. The CSP layer parameters in both CSP-Nets are initialized with CSP filters designed from the training data. During training, they can either be kept fixed or optimized using gradient descent. Experiments on four public MI datasets demonstrated that the two CSP-Nets consistently improved over their CNN backbones, in both within-subject and cross-subject classifications. They are particularly useful when the number of training samples is very small. Our work demonstrates the advantage of integrating knowledge-driven traditional machine learning with data-driven deep learning in EEG-based brain-computer interfaces. © 2024, CC BY.

关键词： Convolutional neural networks

Fully Circuit Implementation of a two-layer Memristive Neural Network for Pattern Recognition

学校读者我要写书评

暂无评论

Fully Circuit Implementation of a two-layer Memristive Neura...

International Conference on Information Science and Technology (ICIST)

作者： Mian Li Xiaoping Wang Zhanfei Chen 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

ISBN: (纸本)9781665412667;9781665429412

In this paper, a fully circuit implementation of Memristive Neural Network (MNN) is proposed. The forward calculation of the network is based on winner-take-all (WTA) mechanism. The weight updating is achieved through the difference of pre-spike and post-spike, which is more close to the biological weight adjustment mechanism. The network is implemented in a full circuit without additional control units. The designed circuit consists of four modules. The memristive crossbar array module with one-memristor (1M) unit structure can effectively calculate the vector-matrix multiplication with only one step. The switch S is replaced by the transistor in the designed leaky-integrate-and-fire (LIF) module, which can control the integration and leakage of the membrane voltage and realize the lateral inhibition between output neurons. Connecting the integrated monostable trigger and the difference circuit, the post-spike generating module can output the required post-spike. The signal switch module realizes the switching of signals connected to memristors by using voltage-controlled switches. The combination of two modules validly realizes weight updating. The functions of four modules are verified separately. We performed a simulation experiment of 5×3 pixels image classification based on the designed circuit in PSPICE. The circuit output results and the high classification accuracy prove the circuit can be effectively applied in pattern recognition. The noise experiment shows the robustness of the designed circuit.

关键词： Training Neurons Switches Robustness Pattern recognition Integrated circuit modeling Task analysis

Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression

学校读者我要写书评

暂无评论

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

Fast Full-frame Video Stabilization with Iterative Optimization

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

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：

MMTrans-MT: A Framework for Multimodal Emotion Recognition Using Multitask Learning

学校读者我要写书评

暂无评论

MMTrans-MT: A Framework for Multimodal Emotion Recognition U...

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Jinrui Shen Jiahao Zheng Xiaoping Wang the School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China the School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

With the development of deep learning, emotion recognition tasks are more inclined to use multimodal data and adequate supervised information to improve accuracy. In this work, MMTrans-MT (Multimodal Transformer-Multitask), the framework for multimodal emotion recognition using multitask learning is proposed. It has three modules: modalities representation module, multimodal fusion module, and multitask output module. Three modalities, i.e, words, audio and video, are comprehensively utilized to carry out emotion recognition by a simple but efficient fusion model based on Transformer. As for multitask learning, the two tasks are defined as categorical emotion classification and dimensional emotion regression. Considering a potential mapping relationship between two kinds of emotion model, multitask learning is adopted to make the two tasks promote each other and improve recognition accuracy. We conduct experiments on CMU-MOSEI and IEMOCAP datasets. Comprehensive experiments show that the accuracy of recognition using multimodal information is higher than that using unimodal information. Adopting multitask learning promotes the performance of emotion recognition.

关键词： Learning systems Deep learning Emotion recognition Correlation Computational modeling Task analysis Computational intelligence

Optimizing Binary Sequence Excitation Signals for Rapid Impedance Spectrum Measurement in Proton Exchange Membrane Fuel Cells

学校读者我要写书评

暂无评论

Optimizing Binary Sequence Excitation Signals for Rapid Impe...

第43届中国控制会议

作者： Jingzhi Lei Chuang Sheng Jingjing Wang Liansong Yu Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology State Grid Electric Power Research Institute Wuhan Nanrui Limited Liability Company Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

With the increasing demand for efficient and reliable renewable energy sources,Proton Exchange Membrane Fuel Cells(PEMFCs) have emerged as a promising *** experiments demonstrate that Electrochemical Impedance Spectroscopy(EIS) effectively differentiates various states of *** broadband signals as testing excitations significantly reduces EIS measurement time,facilitating real-time monitoring of PEMFCs' health under dynamic *** signal design requires maintaining adequate amplitude across frequency components for noise resistance while minimizing signal peak value to reduce operational *** paper introduces an EIS simulation environment,leveraging PEMFCs' impedance and electrochemical noise *** focuses on optimizing the excitation signal's amplitude-frequency distribution using discrete interval binary *** results indicate that our method achieves minimal perturbation amplitude while preserving measurement accuracy in amplitude-frequency signal design.

关键词： Proton exchange membrane fuel cell Electrochemical impedance spectroscopy Electrochemical noise Excitation signal optimization

Cooperative Target-Surrounding control of Unmanned Surface Vessels Based on MADDPG

学校读者我要写书评

暂无评论

Cooperative Target-Surrounding Control of Unmanned Surface V...

Annual Conference of Industrial Electronics Society

作者： Taoman Li Fei Zhu Zihan Gan Zexing Zhou Xiaotao Wang Renzhi Lu Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China China Ship Scientific Research Center Wuxi China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China

This article proposes a multi-agent deep reinforce-ment learning algorithm to control a fleet of unmanned surface vessels (USVs) that encircle and capture sea targets. First, a simulation environment for USVs is established based on a dynamic model; two-dimensional control variables are used to control movements in three directions. Second, the multi-agent deep deterministic policy gradient (MADDPG) algorithm is employed to achieve intelligent control of the USVs, using a reward function based on certain prior knowledge. Finally, centralized training and decentralized execution are used to complete the offline learning of multiple agents, and continuous action decisions are made based on the observations of the USV sensors. Simulations demonstrate that the method can capture stationary moving sea targets with any number of multi-agents under disturbances, and exhibits strong robustness and practicality.

关键词：