检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Huang, Yi-Hua He, Yue Yuan, Yu-Jie Lai, Yu-Kun Gao, Lin Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences China School of Computer and Control Engineering University of Chinese Academy of Sciences China School of Computer Science & Informatics Cardiff University United Kingdom

3D scene stylization aims at generating stylized images of the scene from arbitrary novel views following a given set of style examples, while ensuring consistency when rendered from different views. Directly applying methods for image or video stylization to 3D scenes cannot achieve such consistency. Thanks to recently proposed neural radiance fields (NeRF), we are able to represent a 3D scene in a consistent way. Consistent 3D scene stylization can be effectively achieved by stylizing the corresponding NeRF. However, there is a significant domain gap between style examples which are 2D images and NeRF which is an implicit volumetric representation. To address this problem, we propose a novel mutual learning framework for 3D scene stylization that combines a 2D image stylization network and NeRF to fuse the stylization ability of 2D stylization network with the 3D consistency of NeRF. We first pre-train a standard NeRF of the 3D scene to be stylized and replace its color prediction module with a style network to obtain a stylized NeRF. It is followed by distilling the prior knowledge of spatial consistency from NeRF to the 2D stylization network through an introduced consistency loss. We also introduce a mimic loss to supervise the mutual learning of the NeRF style module and fine-tune the 2D stylization decoder. In order to further make our model handle ambiguities of 2D stylization results, we introduce learnable latent codes that obey the probability distributions conditioned on the style. They are attached to training samples as conditional inputs to better learn the style module in our novel stylized NeRF. Experimental results demonstrate that our method is superior to existing approaches in both visual quality and long-range consistency. Copyright © 2022, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking Performance of Networked control Systems Under DoS and its Applications

Optimal Tracking Performance of Networked Control Systems Un...

引用

Chinese Automation Congress (CAC)

作者： Xinyu Ren Bo Li Feng Zhao Xiangyong Chen Xianhe Zhang Xiaowei Jiang Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China School of Finance Anhui University of Finance and Economics Bengbu China Key Laboratory of Complex systems and Intelligent Computing Universities of Shandong Linyi University Linyi China Key Laboratory of Complex systems and Intelligent Computing School of Automation and Electrical Engineering Universities of Shandong Linyi University Linyi China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This paper investigates the optimal tracking performance (OTP) of multiple-input multiple-output (MIMO) discrete networked control systems (NCSs) under the influence of Denial of Service (DoS) attack, channel noise, and bandwidth constraints. The channel noise is assumed to be additive Gaussian white noise (AWGN). Due to the randomness of DoS attack, a Bernoulli distribution is used for DoS modeling. Utilizing frequency domain analysis methods, coprime factorization, all-pass decomposition, and Youla parameterization, an explicit expression for the optimal tracking performance (OTP) of the system under the two-degree-of-freedom (TDOF) controller is derived. The analysis indicates that non-minimum phase (NMP) zeros, unstable poles (UPs), DoS attack, and network constraints affect the OTP of NCSs. Finally, the theoretical results are validated through simulations of MIMO NCS and vehicle control system.

关键词： Automation Networked control systems Frequency-domain analysis Bandwidth Interference White noise Cyber-physical systems Poles and zeros MIMO communication Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Channel and space-based joint rate allocation algorithm

Channel and space-based joint rate allocation algorithm

引用

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

作者： Dayong Wang Chao Yuan Yu Sun Xin Lu Hui Guo Frederic Dufaux Ce Zhu Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications China Department of Computer Science University of Central Arkansas Faculty of Computing Engineering and Media (CEM) De Montfort University UK Université Paris-Saclay CNRS CentraleSupélec Laboratoire Des Signaux et Systèmes France School of Information and Communication Engineering University of Electronic Science and Technology of China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Rate control is a critical component for image and video compression Particularly under limited network bandwidth conditions, bitrate control is essential to ensure efficient image transmission by effectively allocation channel resources. In this research, since both Channel and Spatial have relationship with rate allocation, we first propose a joint Channel-wise and Spatial-wise Quantization scheme to determine optimal quantization parameters. Subsequently, we develop a quantization step estimation network to obtain parameters to efficiently allocate rate according to target rate. Experiments demonstrate that our algorithm significantly improve compressed image quality with minimal bitrate distortion and achieve accurate rate control with nearly 3% average bitrate error.

关键词： Image quality Quantization (signal) Image coding Bit rate Signal processing algorithms Estimation Rate-distortion Video compression Resource management Speech processing

来源：评论

学校读者我要写书评

暂无评论

Efficient Spiking Neural Networks Incorporating Temporal Attention Mechanisms and Surrogate Gradient

Efficient Spiking Neural Networks Incorporating Temporal Att...

引用

Advanced Algorithms and control engineering (ICAACE), International Conference on

作者： Zhonglang Li Xingming Tang Qian Cheng Shukai Duan Lidan Wang College of Artificial Intelligence Southwest University Chongqing China National & Local Joint Engineering Research Center of Intelligent Transmission and Control Technology Chongqing China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing China State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

In recent years, Spiking Neural Networks (SNNs) have received much attention for their efficient bio-inspired properties, especially in processing time-series data. However, conventional SNNs face the challenges of information loss and insufficient temporal dependence in the encoding layer. To address these issues, this study proposes a SNN coding layer that integrates a temporal attention mechanism and introduces a new surrogate gradient function to improve the model's learning ability and performance. This study proposes a novel temporal attention mechanism designed to enhance the performance of the coding layer of SNNS. Traditional SNNs often face the problems of information loss and lack of temporal dependence when dealing with temporal data. To address these problems, we introduce a temporal attention mechanism, which enables the network to capture important temporal features more efficiently by dynamically adjusting the weights of the input information. In addition, we design a new gradient substitution function to accommodate the discrete nature of the impulse signal. This substitution function can improve the learning ability of the network by avoiding the common gradient vanishing problem in traditional backpropagation while maintaining the gradient flow. The experimental results show that the SNN combining the temporal attention mechanism and the new surrogate gradient function performs superiorly on several benchmark datasets, displaying stronger temporal information processing ability and higher classification accuracy.

关键词： Attention mechanisms Accuracy Systematics Spiking neural networks Feature extraction Encoding Robustness Faces Tuning Optimization

来源：评论

学校读者我要写书评

暂无评论

Robust correlation filter tracking based on response map analysis network

引用

Signal Processing: Image Communication 2022年第0期108卷

作者： Yang, Xin Song, Yong Zhang, Zishuo Zhao, Yufei Li, Liansheng Li, Wang Beijing Institute of Technology Beijing100081 China Department of Precision Instrument Center for Brain Inspired Computing Research Tsinghua University Beijing100084 China Beijing Institute of Control Engineering Beijing100190 China

Conventional discriminative-correlation-filter-based (DCF-based) visual tracking methods always update model at a fixed frequency and learning rate. Without evaluating the tracking confidence scores, the response map generated by filter is the only evidence for locating. Thus, most of the existing DCF-based methods suffer from the model contamination caused by drastic appearance variations, which leads to tracking drift even failure. And excessively frequent update will increase the computational redundancy and risk of over-fitting. In addition, these methods cannot recover target from heavy occlusion neither. Based on the observation that the shape of response maps reflects the matching degree between filter and target, we design and train a small-scale binary network named as response map analysis network (RAN) to evaluate the confidence scores of filters. Further, we propose to learn multiple filters to exploit different kinds of features, and adaptively adjust the update parameters according to the corresponding confidence scores. Moreover, we build a simple occlusion event model to detect heavy occlusion and recover target. Extensive experimental results validate the effectiveness of RAN and demonstrate that the proposed tracker performs favorably against other state-of-the-art (SOTA) DCF-based trackers in terms of precision, overlap rate and efficiency. © 2022 Elsevier B.V.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

引用

Chinese Automation Congress (CAC)

作者： Yumin Lang Jiande Wu Xun Lang Wanke Yu Chuanyan Yang Hongye Su Department of Electronic Engineering Information School Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Automation China University of Geosciences Wuhan China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Oscillation is a significant indication of the deterioration of control system performance and needs to be carefully monitored to ensure safe and stable process operations. However, industrial processes are often prone to noisy artifacts and nonstationary trends, resulting in low signal-to-noise ratios. In order to tackle this problem, this study introduces a novel framework for enhanced trend removal and noise reduction, which is featured by the following steps:(i) The circulant singular spectrum analysis (CiSSA) is used to decompose oscillation data into several reconstructed components (RCs). (ii) The estimated power spectral density (PSD) of these RCs is then smoothed using the Savitzky-Golay filter (SGF) to eliminate noise and identify the RCs corresponding to oscillatory components. (iii) These identified RCs are subsequently reconstructed to produce purified oscillatory data. The effectiveness of the suggested approach is validated using simulations and real-world industrial case studies. The findings indicate that the method notably enhances the quality of oscillatory data.

关键词： Power filters Noise reduction Process control Market research Information filters Noise measurement Oscillators Spectral analysis Monitoring Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Improved Action Recognition Algorithm for Video Surveillance Based on PoseC3D

Improved Action Recognition Algorithm for Video Surveillance...

引用

International Conference on Computer and Communications (ICCC)

作者： Ruifeng Guo Chao Yang Changyi Deng Ying Bai Xiaoxing Zhang Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on DigitTwin Shenyang China Institute of Software China Industrial Control Systems Cyber Emergency Response Team Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

The precise recognition of human action is of great significance for intelligent monitoring and video analysis. Previous researchers have utilized many methods to detect human action, but the accuracy and robustness of these methods remain to be improved. Skeleton-based action recognition methods have reported high accuracy and robustness, but these methods have not fully utilized multiple modalities for feature fusion. In order to solve the above problems, a multi-modality feature fusion based video surveillance personnel action recognition method is proposed by combining the two methods. The SlowOnly network is used to extract RGB modality features. The Faster R-CNN and Lite-HRNet networks are used to obtain skeleton modality data. The PoseC3D network is used to extract skeleton modality features. The early and late fusion of RGB modality features and skeleton modality features are performed. Then the action recognition results of video surveillance personnel are obtained. The experimental results on the NTU RGB+D public dataset under the X-Sub standard show the following points. In the action recognition model based on a single skeleton modality, PoseC3D has a higher recognition accuracy than GCN methods, reaching 92.8%. In the action recognition model based on RGB modality, recognition accuracy has reached 95.4%. The action recognition model based on multi-modality feature fusion has a higher recognition accuracy than the recognition model based on a single modality, reaching 96.1%.

关键词： Accuracy Computational modeling Feature extraction Video surveillance Skeleton Robustness Personnel Standards Monitoring

来源：评论

学校读者我要写书评

暂无评论

Quantification of Valve Stiction in control Loops Using Adaptive Differential Evolution Algorithm

Quantification of Valve Stiction in Control Loops Using Adap...

引用

Chinese Automation Congress (CAC)

作者： Dong Yang Xun Lang Jiande Wu Wanke Yu Songhua Liu Lei Xie Department of Electronic Engineering Information School Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Automation China University of Geosciences Wuhan China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurately and promptly quantifying stiction is crucial for valve maintenance in industrial settings and ensuring the stability of control loop performance. However, current Hammerstein-based stiction quantification methods overlook valve dynamics, potentially leading to inaccurate quantification. Therefore, this paper proposes a novel stiction quantification method based on an adaptive differential evolution algorithm. In addition to considering the impact of valve dynamics on stiction, the proposed method demonstrates a certain level of robustness against the interference of unknown noise. Finally, the effectiveness of the proposed method is demonstrated through a series of simulations and industrial case studies.

关键词： Adaptation models Heuristic algorithms Noise Interference Valves Stability analysis Robustness Data models Maintenance Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

LCFNet: Loss Compensation Fusion Network for Real-Time Semantic Segmentation of Urban Road Scenes

LCFNet: Loss Compensation Fusion Network for Real-Time Seman...

引用

International Conference on Intelligent Transportation

作者： Lu Yang Yiwen Bai Fenglei Ren Shiyu Zhang Chongke Bi Tianjin Key Laboratory for Advanced Mechanical System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin China College of Intelligence and Computing Tianjin University Tianjin China

Semantic segmentation is used by intelligent transportation systems to understand and sense the traffic environment. However, achieving semantic segmentation in real-time is a challenge due to the necessity of both high accuracy and fast processing. This is especially valuable for applications such as autonomous driving and industrial robotics. In this paper, we propose a real-time semantic segmentation network, called LCFNet, which makes use of three-branch structure. The LCFNet consists of Lightweight Detail Guidance Fusion (L-DGF) and Lightweight Semantic Guidance Fusion (L-SGF) modules. Both modules aggregate information from various network layers. In the termination of network, a Total Guidance Fusion (TGF) module is proposed for processing information from all three branches. Depth-wise Convolution Pyramid Pooling (DCPP) module is also included to optimize accuracy and simplify computation. The effectiveness of LCFNet is demonstrated on two typical semantic segmentation datasets, Cityscapes and CamVid. On a single NVIDIA GeForce GTX 2080 Ti GPU, LCFNet reaches 77.02% mIoU at 95.97 FPS and 81.17% mIoU at 204.82 FPS, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Altitude Balloons No-Fly Zone Avoidance Based Reinforcement Learning

High-Altitude Balloons No-Fly Zone Avoidance Based Reinforce...

引用

IEEE International Conference on Real-time computing and Robotics (RCAR)

作者： Jinkua Liu Xiaotao Li Yu Hu Bo Zhang College of Computing Georgia Institute of Technology Atlanta GA USA College of Mechatronics and Control Engineering Shenzhen University Shenzhen China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Shenzhen City Joint Laboratory of Autonomous Unmanned Systems and Intelligent Manipulation Shenzhen China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

High-altitude balloons are commonly used in scientific research but have challenges in operation due to underactuation and non-linear dynamics affected by atmospheric factors, resulting in traditional model-based control impractical. In response, reinforcement learning (RL) has been utilized as a promising approach for balloon control, achieving breakthroughs in station-keeping and navigation. Nonetheless, the No-Fly Zone (NFZ) avoidance of high-altitude balloons remains a largely uncharted territory. This study adopts a reinforcement learning-based methodology to address this particular problem. Quantile Regression DQN and DQN methods are utilized to guarantee the efficiency evaluated through simulating diverse NFZ configurations and missions. Results demonstrate that this approach effectively avoids NFZs, underscoring RL’s potential to enhance the safety and efficiency of high-altitude balloon operations.

关键词： Navigation Atmospheric modeling Reinforcement learning Numerical simulation Real-time systems Safety 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：