检索结果-内蒙古大学图书馆

2nd EAI International Conference on Robotic Sensor Networks, ROSENET 2018

作者： Xia, Xingyu Gao, Hao Hu, Haidong Lan, Rushi Pun, Chi-Man The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China Department of Computer and Information Science University of Macau China Beijing Institute of Control Engineering Beijing China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9783030177621

As a popular evolutionary algorithm, artificial bee colony (ABC) algorithm has been successfully applied into the threshold-based image segmentation problem. Based on our analysis, we find that the Otsu segmentation function is separable which means each variable is independent. Due to its one-dimensional search strategy and relative power global but poorer local search abilities, ABC could find an acceptable but not precise segmentation results. For making more precise search and further enhancing the achievements on image segmentation, we propose an Otsu segmentation method based on a new ABC algorithm with an improved scout bee strategy. Different from the traditional scout bee strategy, we use a local search strategy when a bee stagnates for a defined value. The experimental results on Berkeley segmentation database demonstrate the effectiveness of our algorithm. © 2020, Springer Science and Business Media Deutschland GmbH. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

CTCNet: A CNN-Transformer Cooperation Network for Face image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Gao, Guangwei Xu, Zixiang Li, Juncheng Yang, Jian Zeng, Tieyong Qi, Guo-Jun The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China The Center for Mathematical Artificial Intelligence Department of Mathematics The Chinese University of Hong Kong Hong Kong Research Center for Industries of the Future School of Engineering Westlake University OPPO Research Seattle United States

Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by joint training with facial priors. However, these methods have some obvious limitations. On the one hand, multi-task joint learning requires additional marking on the dataset, and the introduced prior network will significantly increase the computational cost of the model. On the other hand, the limited receptive field of CNN will reduce the fidelity and naturalness of the reconstructed facial images, resulting in suboptimal reconstructed images. In this work, we propose an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone. Specifically, we first devise a novel Local-Global Feature Cooperation Module (LGCM), which is composed of a Facial Structure Attention Unit (FSAU) and a Transformer block, to promote the consistency of local facial detail and global facial structure restoration simultaneously. Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features. Finally, to further improve the restoration of fine facial details, we present a Multi-scale Feature Fusion Unit (MFFU) to adaptively fuse the features from different stages in the encoder procedure. Extensive evaluations on various datasets have assessed that the proposed CTCNet can outperform other state-of-the-art methods significantly. Source code will be available at https://***/IVIPLab/CTCNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Reaching Non-Negative Edge Consensus of Networked Dynamical Systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2018年第9期48卷 2712-2722页

作者： Wang, Xiao Ling Su, Housheng Chen, Michael Z. Q. Wang, Xiao Fan Chen, Guanrong College of Automation Nanjing University of Posts and Telecommunications Nanjing China School of Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan China School of Automation Nanjing University of Science and Technology Nanjing China Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Department of Electronic Engineering City University of Hong Kong Hong Kong

In this paper, the problem of non-negative edge consensus of undirected networked linear time-invariant systems is addressed by associating each edge of the network with a state variable, for which a distributed algorithm is constructed. Sufficient conditions referring only to the number of edges are derived for non-negative edge consensus of the networked systems. Subsequently, the linear programming method and a low-gain feedback technique are introduced to simplify the design of the feedback gain matrix for achieving the non-negative edge consensus. It is found that the low-gain feedback technique has a good effect on the non-negative edge consensus of the networked systems subject to input saturation. Numerical simulations are presented to verify the effectiveness of the theoretical results.

关键词： Distributed algorithm line graph low-gain feedback networked system non-negative edge consensus

来源：评论

学校读者我要写书评

暂无评论

image Retrieval using CNN and Low-level Feature Fusion for Crime Scene Investigation image Database

Image Retrieval using CNN and Low-level Feature Fusion for C...

引用

Asia-Pacific Signal and information processing Association Annual Summit and Conference (APSIPA)

作者： Ying Liu Yanan Peng Dan Hu Daxiang Li Keng-Pang Lim Nam Ling Center for Image and Information Processing Xi'an University of Posts and Telecommunications Xi'an China Department of Computer Engineering Santa Clara University California USA

ISBN: (纸本)9781728102436;9789881476852

Crime scene investigation (CSI) image retrieval is used to search for crime evidences and is critical in helping in solving various crimes. In recent years, using Convolutional Neural Network (CNN) has demonstrated outstanding performances in large-scale image database retrieval. However, to prevent over-fitting in the training of CNN model due to limited number of CSI images, this paper proposes to cascade two CNN models obtained based on transfer learning and combine CNN features with low-level image feature to better describe CSI images. First, two pre-trained CNN models are fine-tuned using the target image set. CNN features are extracted from fully connected layer of each model and are concatenated as high-level features for the image. These concatenated CNN features are then fused with the low-level image features of the target image set. The final fused image features are used in the image retrieval. Experimental results on CSI image database proved the effectiveness of the proposed algorithm for limited number of training sets. In addition, experiments carried out on the GHIM-10K database proved the generalizability of the proposed algorithm.

关键词： Feature extraction image retrieval Discrete cosine transforms image color analysis Semantics Mathematical model

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2020 Challenge on image and Video Deblurring

arXiv

引用

arXiv 2020年

作者： Seungjun, Nah Sanghyun, Son Radu, Timofte Kyoung Mu, Lee Tseng, Yu Xu, Yu-Syuan Chiang, Cheng-Ming Tsai, Yi-Min Brehm, Stephan Scherer, Sebastian Xu, Dejia Chu, Yihao Sun, Qingyan Jiang, Jiaqin Duan, Lunhao Yao, Jian Purohit, Kuldeep Suin, Maitreya Rajagopalan, A.N. Ito, Yuichi Hrishikesh, P.S. Puthussery, Densen Akhil, K.A. Jiji, C.V. Kim, Guisik Deepa, P.L. Xiong, Zhiwei Huang, Jie Liu, Dong Kim, Sangmin Nam, Hyungjoon Kim, Jisu Jeong, Jechang Huang, Shihua Fan, Yuchen Yu, Jiahui Yu, Haichao Huang, Thomas S. Zhou, Ya Li, Xin Liu, Sen Chen, Zhibo Dutta, Saikat Das, Sourya Dipta Garg, Shivam Sprague, Daniel Patel, Bhrij Huck, Thomas Department of ECE ASRI SNU Korea Republic of Computer Vision Lab ETH Zurich Switzerland MediaTek Inc University of Augsburg Chair for Multimedia Computing and Computer Vision Lab Germany Peking University China Beijing University of Posts and Telecommunications China Beijing Jiaotong University China Wuhan University China Indian Institute of Technology Madras India Vermilion College of Engineering Trivandrum India CVML Chung-Ang University Korea Republic of APJ Abdul Kalam Technological University India University of Science and Technology of China China Image Communication Signal Processing Laboratory Hanyang University Korea Republic of Southern University of Science and Technology China University of Illinois at Urbana-Champaign United States CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China China IIT Madra Jadavpur University India University of Texas Austin United States Duke University Computer Science Department United States

Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on image and Video Deblurring. In this challenge, we present the evaluation results from 3 competition tracks as well as the proposed solutions. Track 1 aims to develop single-image deblurring methods focusing on restoration quality. On Track 2, the image deblurring methods are executed on a mobile platform to find the balance of the running speed and the restoration accuracy. Track 3 targets developing video deblurring methods that exploit the temporal relation between input frames. In each competition, there were 163, 135, and 102 registered participants and in the final testing phase, 9, 4, and 7 teams competed. The winning methods demonstrate the state-of-the-art performance on image and video deblurring tasks. Copyright © 2020, 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

Blind deconvolution combined with level set method for correcting cupping artifacts in cone beam CT

Blind deconvolution combined with level set method for corre...

引用

SPIE Medical Imaging 2017

作者： Xie, Shipeng Zhuang, Wenqin Li, Baosheng Bai, Peirui Shao, Wenze Tong, Yubing Nanjing University of Posts and Telecommunications College of Telecommunications and Information Engineering China Medical Image Processing Group Department of Radiology University of Pennsylvania United States Shandong Cancer Hospital and Institute Jinan China

Cone-beam CT (CBCT) is a promising modality for many clinical applications. But the X-ray scatter in CBCT may lead to cupping and blurring artifacts, which is one of the crucial problems for which a clinically reasonable solution remains elusive. Recently, the main correction methods developed to solve the problems can be briefly classified into four approaches: Monte Carlo (MC) simulation, scatter measurements, primary modulation, and the analytical modeling methods. The MC simulation algorithms, such as GPU-based method1, 2, 3 have been proposed in recent years. Some methods estimate the contribution of scatter in the measured projection data and then subtract it from the measured projection data as in the beam-stop array method4, and moving blocker method5. Using the primary beam modulator, the primary signals are separated from the scatter signals in the Fourier domain6,7,8. In analytical modeling methods, a scatter kernel is employed to estimate the scatter radiation distribution in measured data9. However, the heavy computation of MC scatter estimation hinders real-life applications of this approach. Scatter measurement and primary modulation methods add extra hardware to the CBCT system, which can add difficulty and complexity. The analytical modeling methods use the scatter kernel which may reduce the contrast resolution. Although there are many published papers, their approaches cannot simultaneously account for scatter artifacts and contrast resolution. We had observed that cupping artifacts, as the main scatter artifacts, can be corrected which can improve the contrast resolution by using the reconstructed image. © 2017 SPIE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Consistent ICP for the registration of sparse and inhomogeneous point clouds 6

Consistent ICP for the registration of sparse and inhomogene...

引用

6th IEEE International Conference on Communications and Electronics, IEEE ICCE 2016

作者： Luong, Hiep Quang Vlaminck, Michiel Goeman, Werner Philips, Wilfried Image Processing and Interpretation Research Group Department of Telecommunications and Information Processing Ghent University iMinds Ghent Belgium Grontmij Ghent Belgium

ISBN: (纸本)9781509019311

In this paper, we derive a novel iterative closest point (ICP) technique that performs point cloud alignment in a robust and consistent way. Traditional ICP techniques minimize the point-To-point distances, which are successful when point clouds contain no noise or clutter and moreover are dense and more or less uniformly sampled. In the other case, it is better to employ point-To-plane or other metrics to locally approximate the surface of the objects. However, the point-To-plane metric does not yield a symmetric solution, *** estimated transformation of point cloud p to point cloud q is not necessarily equal to the inverse transformation of point cloud q to point cloud p. In order to improve ICP, we will enforce such symmetry constraints as prior knowledge and make it also robust to noise and clutter. Experimental results show that our method is indeed much more consistent and accurate in presence of noise and clutter compared to existing ICP algorithms. © 2016 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

C-EFIC: Color and edge based foreground background segmentation with interior classification

Communications in Computer and Information Science

引用

Communications in Computer and information Science 2016年 598卷 433-454页

作者： Allebosch, Gianni Van Hamme, David Deboeverie, Francis Veelaert, Peter Philips, Wilfried Department of Telecommunications and Information Processing Image Processing and Interpretation Ghent University-iMinds Gent Belgium

The detection of foreground regions in video streams is an essential part of many computer vision algorithms. Considerable contributions were made to this field over the past years. However, varying illumination circumstances and changing camera viewpoints provide major challenges for all available algorithms. In this paper, a robust foreground background segmentation algorithm is proposed. Both Local Ternary Pattern based edge descriptors and RGB color information are used to classify individual pixels. Furthermore, camera viewpoints are detected and compensated for. We will show that this algorithm is able to handle challenging conditions and achieves state-of-the-art results on the comprehensive *** 2014 dataset. © Springer International Publishing Switzerland 2016.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Human gesture classification by brute-force machine learning for exergaming in physiotherapy

Human gesture classification by brute-force machine learning...

引用

IEEE Symposium on Computational Intelligence and Games, CIG

作者： Francis Deboeverie Sanne Roegiers Gianni Allebosch Peter Veelaert Wilfried Philips Department of Telecommunications and Information Processing Image Processing and Interpretation UGent/iMinds Ghent Belgium

ISBN: (纸本)9781509018840

In this paper, a novel approach for human gesture classification on skeletal data is proposed for the application of exergaming in physiotherapy. Unlike existing methods, we propose to use a general classifier like Random Forests to recognize dynamic gestures. The temporal dimension is handled afterwards by majority voting in a sliding window over the consecutive predictions of the classifier. The gestures can have partially similar postures, such that the classifier will decide on the dissimilar postures. This brute-force classification strategy is permitted, because dynamic human gestures show sufficient dissimilar postures. Online continuous human gesture recognition can classify dynamic gestures in an early stage, which is a crucial advantage when controlling a game by automatic gesture recognition. Also, ground truth can be easily obtained, since all postures in a gesture get the same label, without any discretization into consecutive postures. This way, new gestures can be easily added, which is advantageous in adaptive game development. We evaluate our strategy by a leave-one-subject-out cross-validation on a self-captured stealth game gesture dataset and the publicly available Microsoft Research Cambridge-12 Kinect (MSRC-12) dataset. On the first dataset we achieve an excellent accuracy rate of 96.72%. Furthermore, we show that Random Forests perform better than Support Vector Machines. On the second dataset we achieve an accuracy rate of 98.37%, which is on average 3.57% better then existing methods.

关键词： Radio frequency Games Decision trees Gesture recognition Training Skeleton Vegetation

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：