检索结果-内蒙古大学图书馆

Generative Adversarial Network for Image Deblurring Using Content Constraint Loss

学校读者我要写书评

暂无评论

Generative Adversarial Network for Image Deblurring Using Co...

第32届中国控制与决策会议

作者： Ye Ji Yaping Dai Junjie Ma Kaixin Zhao Yanyan Cheng School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

The research of image deblurring plays an important role in the digital image *** order to reduce image blurring problems,a content constraint loss（CCL） function in the generative adversarial network（GAN）is *** SSIM loss and the perceptual loss constitute the CCL function,which makes the trained generative model *** CCL function as the content constraint loss component and the adversarial loss component constitute the total *** total loss is optimized by the iterative training to further improve the stability of the network model,and the image blurring will be *** the test experiment of the open source image dataset MNIST,CIFAR10/100 and CELEBA,the CCL function is used as the content constraint loss component of the generative adversarial network,the effect of image deblurring has obvious promotion in the structural similarity measure and visual appearance.

关键词： Image deblurring Generative adversarial network Content constraint loss Adversarial loss

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Xie, Yuan Zou, Tao Chen, Ci Sun, Weijun Xie, Shengli School of Mechanical and Electrical Engineering Guangzhou University Guangdong-Hong Kong-Macao Key Laboratory of Multi-scale Information Fusion and Collaborative Optimization Control of Complex Manufacturing Process Guangzhou510006 China School of Automation Guangdong University of Technology Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education of the P.R.C. Guangzhou510006 China School of Automation Guangdong University of Technology Guangdong Key Laboratory of IoT Information Processing Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China School of Automation Guangdong University of Technology Key Laboratory of Intelligent Detection and the IoT in Manufacturing Ministry of Education 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Room reverberation and echoes have an important influence on acoustics quality, causing great difficulty in independent source separation. In the paper, an adaptive time-frequency blind source separation algorithm (ATF-BSS) is designed to deal with high reverberation and echoes, which can adaptively attenuate audible echoes and enhance the harmonic structure of real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components that have less energy than the dominant signal. ATF-BSS algorithm incorporates the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking for high reverberation and echoes scene, improving the performance of blind separation. Experimental results on public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

Crsanet: Class Representations Self-Attention Network for the Segmentation of Thyroid Nodules

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Sun, Shiyao Fu, Chong Xu, Sen Wen, Yingyou Ma, Tao School of Computer Science and Engineering Northeastern University Shenyang110819 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China General Hospital of Northern Theatre Command Shenyang110016 China Medical Imaging Research Department Neusoft Research of Intelligent Healthcare Technology Co. Ltd. Shenyang China Dopamine Group Ltd. Auckland1542 New Zealand

Segmenting accurate thyroid nodules in medical ultrasound images is always non-trivial due to the large variation in size, shape and texture of nodules, and also the presence of surrounding tissues and organs with similar intensity values. Existing algorithms solve this by designing multi-scale spatial context modeling modules and introducing the emerging self-attention based paradigm, while failing to learn the class-wise relational context around nodules. To this end, we propose a novel coarse-to-fine framework, namely, CRSANet, which leverages both class-wise relational context and spatial multi-scale context for comprehensive context perception. Specifically, we first introduce the concept of Class Representations, which describe the overall representation of thyroid nodules in ultrasound images from a categorical perspective. Secondly, we propose a backbone-free dual-branch Class Representation Self-Attention Module (CRSA) to refine the coarse segmentation results from segmentation backbones. Concretely, Fine Class Region (FCR) branch is proposed to impose consistency between pixels and their corresponding Class Representations to correct the wrongly classified pixels. Meanwhile, Class Contextual Representation (CCR) branch is introduced to enhance the ability of pixel representations with the corresponding Class Representations. We evaluate the effectiveness and generality of CRSANet using three types of backbone networks. In the experiments, our proposed U-CRSANet achieves a mIoU of 78.86% and 81.35%, an accuracy of 97.11% and 98.63%, a Dice value of 74.26% and 87.57%, respectively, which outperforms most state-of-the-art methods on the public DDTI and TN-SCUI datasets. © 2023, The Authors. All rights reserved.

关键词： Pixels

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Room reverberation and echoes have an important influence on acoustics quality, causing great difficulty in independent source separation. In the paper, an adaptive time-frequency blind source separation algorithm (ATF-BSS) is designed to deal with high reverberation and echoes, which can adaptively attenuate audible echoes and enhance the harmonic structure of real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components that have less energy than the dominant signal. To the best of our knowledge, this is the first attempt to incorporate the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking to solve blind separation with high reverberation and echoes. Experimental results on public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

The input pattern problem on deep learning applied to signal analysis and processing to achieve fault diagnosis

学校读者我要写书评

暂无评论

science China(Information sciences) 2019年第12期62卷 269-271页

作者： Hao REN Nan LI Yi CHAI Jianfeng QU Qiu TANG Lei HUANG School of Automation Chongqing University Key Laboratory of Complex System Safety and Control Ministry of Education School of Computer Science and Technology Huaiyin Normal University

Dear editor,Generally, one of the most prominent features of modern industrial systems is the massive amount of data collected from various sensors, which poses great challenges to traditional methods of captur-

关键词： The input pattern problem on deep learning applied to signal analysis and processing to achieve fault diagnosis

Tracking Performance of Networked systems with Limited Bandwidth and Colored Noise

学校读者我要写书评

暂无评论

Tracking Performance of Networked Systems with Limited Bandw...

Chinese Automation Congress (CAC)

作者： Bin Zhang Xiaowei Jiang Li Sun Xianhe Zhang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China School of Statistics and Mathematics Zhongnan University of Economics and Law Wuhan China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

This study investigated the optimal tracking performance (OTP) of multi-input multi-output (MIMO), discrete- time networked control systems (NCSs). The limits of tracking performance (TP) under the influences of bandwidth, encoding- decoding, and additive coloured Gaussian noise (ACGN) are derived using the techniques of coprime decomposition and all-pass decomposition. The results reveal the negative impact of non-minimum phase (NMP) zeros and unstable poles of the plant as well as network communication constraints on the TP of NCSs. Finally, a numerical simulation is discussed and verifies our conclusions.

关键词： Networked control systems Gaussian noise Bandwidth Numerical simulation Downlink Decoding Colored noise

Solarsam: Building-Scale Photovoltaic Potential Assessment Based on Segment Anything Model (Sam) and Remote Sensing for Emerging City

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Li, Guanglei Wang, Guohao Luo, Tengqi Hu, Yuxiao Wu, Shouyuan Gong, Guanghui Song, Chenchen Guo, Zhiling Liu, Zhengguang Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Shandong University Jinan250061 China Department of Power and Electrical Engineering Northwest A&F University Yangling712100 China The Hong Kong Polytechnic University Hong Kong Eastern Institute of Technology Ningbo315200 China Higher Information Industry Technology Research Institute Beijing Information Science and Technology University Beijing100192 China Department of Chemical Engineering The University of Manchester ManchesterM13 9PL United Kingdom

Driven by advancements in photovoltaic (PV) technology, solar energy has emerged as a promising renewable energy source, due to its ease of integration onto building rooftops, facades, and windows. For the emerging cities, the lack of detailed street-level data presents a challenge for effectively assessing the potential of building-integrated photovoltaic (BIPV). To address this, this study introduces SolarSAM, a novel BIPV evaluation method that leverages remote sensing imagery and deep learning techniques, and an emerging city in northern China is utilized to validate the model performance. During the process, SolarSAM segmented various building rooftops using text prompt guided semantic segmentation. Separate PV models were then developed for Rooftop PV, Facade-integrated PV, and PV windows systems, using this segmented data and local climate information. The potential for BIPV installation, solar power generation, and city-wide power self-sufficiency were assessed, revealing that the annual BIPV power generation potential surpassed the city’s total electricity consumption by a factor of 2.5. Economic and environmental analysis were also conducted, including levelized cost of electricity and carbon reduction calculations, comparing different BIPV systems across various building categories. These findings demonstrated the model’s performance and reveled the potential of BIPV power generation in the future. © 2024, The Authors. All rights reserved.

关键词： Solar power generation

Monocular Visual-Inertial Odometry Based on Point and Line Features

学校读者我要写书评

暂无评论

Monocular Visual-Inertial Odometry Based on Point and Line F...

International Conference on Computer and Communications (ICCC)

作者： Gongyan Chen Hai Zhang Wenxing Fu Yiqun Qiao School of Automation Science and Electrical Engineering Beihang University Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

In order to solve the problem that the point feature tracking is not robust enough to reduce the accuracy of the system in a low-texture environment, this paper proposes a visual inertial odometry system based on point-line features (PL-VINS). Firstly, the system improves the extraction and matching algorithm of line features to increase the speed and accuracy of the algorithm; then the line features are added to the front-end tracking and back-end optimization. Finally, the EuRoc public data set is used as the experimental object to prove the effectiveness of the algorithm.

关键词： Visualization Conferences Feature extraction Cameras Real-time systems Optimization Optical flow