检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Hui Wu, Xiao-Jun Kittler, Josef Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China The Center for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

In the image fusion field, the design of deep learning-based fusion methods is far from routine. It is invariably fusion-task specific and requires a careful consideration. The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand. Thus, devising learnable fusion strategy is a very challenging problem in the community of image fusion. To address this problem, a novel end-to-end fusion network architecture (RFN-Nest) is developed for infrared and visible image fusion. We propose a residual fusion network (RFN) which is based on a residual architecture to replace the traditional fusion approach. A novel detail-preserving loss function, and a feature enhancing loss function are proposed to train RFN. The fusion model learning is accomplished by a novel two-stage training strategy. In the first stage, we train an auto-encoder based on an innovative nest connection (Nest) concept. Next, the RFN is trained using the proposed loss functions. The experimental results on public domain data sets show that, compared with the existing methods, our end-to-end fusion network delivers a better performance than the state-of-the-art methods in both subjective and objective evaluation. The code of our fusion method is available at https://***/hli1221/imagefusion-rfn-nest. © 2021, CC BY-NC-ND.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

A correction method for aero-optics thermal radiation effects based on gradient distribution and dark channel

引用

Optoelectronics Letters 2019年第5期15卷 374-380页

作者： HONG Han-yu SHI Yu ZHANG Tian-xu LIU Zhao Hubei Key Laboratory of Optical Information and Pattern Recognition Hubei Research Centre of Video Image and High Definition Projection School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan 430074 China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing School of Automation Huazhong University of Science and Technology Wuhan 430074 China

In this paper, a new algorithm is proposed to remove the effects of aerodynamic optical thermal radiation from a single infrared image. In this method, the joint probability model of gradient distribution is introduced by studying the "global smoothing and local fluctuation" characteristics of the bias field. A prior L0 norm of dark channel is introduced to constrain the latent clear image. Finally, the split Bregman method is used to solve the optimization problem. The effectiveness of the proposed method is verified by a series of experiments, and the results are compared with the results of the existing methods for the correction of thermal radiation effects.

关键词： aero-optics thermal radiation effects gradient distribution dark channel

来源：评论

学校读者我要写书评

暂无评论

On the Target Area Tracking Method for Heart Rate Measurement Using Deep Learning Strategy

On the Target Area Tracking Method for Heart Rate Measuremen...

引用

2019第十一届数字图像处理国际会议

作者： Jiancheng Zou Sai Zhang Bailin Ge Institute of Image Processing and Pattern Recognition North China University of Technology

Heart rate monitoring is important for diagnosis and prevention of physiological *** method of measuring heart rate by infrared sequence image has high *** shaking is a factor to affect the measurement *** if a slight shaking will create a big measurement *** this paper,we propose an automatic capture algorithm of heart rate measurement through the real-time tracking and capturing of the face monitoring area,so the disturbance caused by human body shaking is *** with the traditional method1,the measurement accuracy of the tests with shaking is improved about 6% higher based on our algorithm.

关键词： Automatic capture algorithm face feature point detection heart rate measurement

来源：评论

学校读者我要写书评

暂无评论

Real-time Oxygen Saturation Measurement Based on Reflective Region Removal Technology

Real-time Oxygen Saturation Measurement Based on Reflective ...

引用

2019第十一届数字图像处理国际会议

作者： Jiancheng Zou Yupeng Chen Bailin Ge Institute of Image Processing and Pattern Recognition North China University of Technology

Blood oxygen saturation is an important physiological parameter to measure human *** oxygen saturation can be measured in real time through an optical lens with high ***,when there is the light reflection of the measured area,the accuracy of the measurement results will fluctuate,leading to the instability of the measurement *** this paper,we improved the original algorithm by detecting and removing the highlight *** experimental results show that the accuracy of the improved method is higher than that of the traditional method in the case of specular reflection and the stability of the measurement results is enhanced.

关键词： Detection of reflective area blood oxygen saturation imaging photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

A Dual-Camera Surveillance Video Summarization Generating Strategy for Multi-Target Capturing 19

A Dual-Camera Surveillance Video Summarization Generating St...

引用

Proceedings of the 3rd International Conference on Video and image processing

作者： Qingyun Shen Cihui Yang Shipin Wen Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Information Engineering Nanchang Hangkong University Nanchang China University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781450376822

Traditional surveillance video contains a large amount of information which is too jumbled. Real-time video summarization can solve this problem but also face much challenges. Different from file summarization, real-time video summarization requires higher efficiency. Meanwhile, the validity and quality of a summarization should be ensured. To tackle these problems, we propose a real-time video summarization strategy based on dual-camera. In our strategy, a static camera and a PTZ camera are necessary. The static camera is used to monitor the scene to detect and track moving targets, and the PTZ camera is used to capture the close-up information of moving targets as video summarization, and the collaboration of these two cameras is crucial. Specifically, in order to obtain multi-target summarization efficiently and effectively, the priority of target capturing is determined by its spatial information and historical representation in the scene. Extensive experiments are performed on real-time outdoor scene with our method. Experimental results show that our proposed method is robust enough to capture multiple targets in the same scene at the same time.

关键词： Multi-target priority judgment Dual-camera coordination Real-time video summarization

来源：评论

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM image processing

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Rui Hu Jiaming Cai Wangjie Zheng Yang Yang Hong-Bin Shen Shanghai Jiao Tong University and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools.

关键词： Three-dimensional displays Feature extraction image reconstruction Task analysis Solid modeling Electron microscopy Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Medicine-engineering interdisciplinary researches for addiction: Opportunities and challenges

Meta-Radiology

引用

Meta-Radiology 2023年第2期1卷

作者： Wen, Xinwen Du, Zhe Wang, Zhen Xu, Yu Wang, Kunhua Yu, Dahua Liu, Jun Yuan, Kai School of Life Science and Technology Xidian University Shaanxi Xi'an 710126 China Yunnan University Yunnan Kunming 650500 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information Engineering Inner Mongolia University of Science and Technology Inner Mongolia Baotou 014010 China Department of Radiology Second Xiangya Hospital Central South University Changsha 410011 China Engineering Research Center of Molecular and Neuro Imaging Ministry of Education Shaanxi Xi'an 710126 China Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information School of Life Science and Technology Xidian University Shaanxi Xi'an 710126 China

Advances in neuroscience have suggested that addiction is not only an ongoing dynamic transaction between the person, their behavior, and the environment, but a disturbance of neurotransmitters in neurons involved in reward, memory, and cognitive control. Although the neural mechanism of addiction is complex and heterogeneous, previous addiction recovery and treatment studies have proven that addiction is amenable to treatment and recovery. At present, addiction treatment faces great challenges as well as many opportunities. The field of biomedical engineering is and will be at the forefront of these accelerating disciplines based on advances in imaging, genomics, systems medicine, molecular and cellular engineering, and other biomedical sciences. Thus, we propose several perspectives to accelerate the development of advanced and scientific approaches for addiction treatment: early prevention is better than cure and addiction treatment should focus on individualized regulation, whole-body interaction and the translation of effective animal models to human. © 2023 The Authors

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse slow feature analysis for enhanced control monitoring and fault isolation 1

Sparse slow feature analysis for enhanced control monitoring...

引用

1st International Conference on Industrial Artificial Intelligence, IAI 2019

作者： Shang, Chao Huang, Xiaolin Yang, Fan Huang, Dexian Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200400 China

ISBN: (纸本)9781728135939

This paper presents sparse slow feature analysis (SFA) for efficient process monitoring and fault isolation, which is a new latent variable model for time series data. We first recast sparse SFA in terms of a novel regression-Type problem, and further incorporate l-{1}-norm penalty into the objective in order to promote sparsity. To solve the induced nonconvex optimization problem, a tailored iterative algorithm is developed. With the sparse representation, process variables with insignificant contributions can be completely omitted, and each latent variable relates only to a fraction of crucial process variables in comparison with the generic SFA. A new process monitoring and fault isolation approach is developed based on the sparse SFA, which results in improved monitoring performance, easy-To-interpret diagnostics, and meaningful process knowledge discovery. Case studies on the Tennessee Eastman process are carried out to address the applicability of the proposed approach. © 2019 IEEE.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

AMIL: Adversarial multi instance learning for human pose estimation

arXiv

引用

arXiv 2020年

作者： SHAMSOLMOALI, POURYA ZAREAPOOR, MASOUMEH ZHOU, HUIYU YANG, JIE Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Department of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

Human pose estimation has an important impact on a wide range of applications from human-computer interface to surveillance and content-based video retrieval. For human pose estimation, joint obstructions and overlapping upon human bodies result in departed pose estimation. To address these problems, by integrating priors of the structure of human bodies, we present a novel structure-aware network to discreetly consider such priors during the training of the network. Typically, learning such constraints is a challenging task. Instead, we propose generative adversarial networks as our learning model in which we design two residual multiple instance learning (MIL) models with the identical architecture, one is used as the generator and the other one is used as the discriminator. The discriminator task is to distinguish the actual poses from the fake ones. If the pose generator generates the results that the discriminator is not able to distinguish from the real ones, the model has successfully learnt the priors. In the proposed model, the discriminator differentiates the ground-truth heatmaps from the generated ones, and later the adversarial loss back-propagates to the generator. Such procedure assists the generator to learn reasonable body configurations and is proved to be advantageous to improve the pose estimation accuracy. Meanwhile, we propose a novel function for MIL. It is an adjustable structure for both instance selection and modeling to appropriately pass the information between instances in a single bag. In the proposed residual MIL neural network, the pooling action adequately updates the instance contribution to its bag. The proposed adversarial residual multi-instance neural network that is based on pooling has been validated on two datasets for the human pose estimation task and successfully outperforms the other state-of-arts models. The code will be made available on https://***/pshams55/AMIL. Copyright © 2020, The Authors. All rights reserve

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

arXiv

引用

arXiv 2021年

作者： Rao, Dongyu Wu, Xiao-Jun Li, Hui Kittler, Josef Xu, Tianyang Jiangnan University Jiangsu Provincial Engineerinig Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Lihu Avenue Wuxi214122 China University of Surrey Centre for Vision Speech and Signal Processing GuildfordGU2 7XH United Kingdom

In this paper, we propose a photorealistic style transfer network to emphasize the natural effect of photo realistic image stylization. In general, distortion of the image content and lacking of details are two typical issues in the style transfer field. To this end, we design a novel framework employing the U-Net structure to maintain the rich spatial clues, with a multi-layer feature aggregation (MFA) method to simultaneously provide the details obtained by the shallow layers in the stylization processing. In particular, an encoder based on the dense block and a decoder form a symmetrical structure of U-Net are jointly staked to realize an effective feature extraction and image reconstruc tion. Besides, a transfer module based on MFA and "adaptive instance normalization" (AdaIN) is inserted in the skip connection positions to achieve the stylization. Accordingly, the stylized image possesses the texture of a real photo and preserves rich content details without introducing any mask or post-processing steps. The experimental results on public datasets demonstrate that our method achieves a more faithful structural similarity with a lower style loss, reflecting the effectiveness and merit of our approach. © 2021, CC0.

关键词： Deep learning

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：