检索结果-内蒙古大学图书馆

Slimming Convolutional Neural Network Based on Attention Mechanism for Pavement Crack Detection 11

Slimming Convolutional Neural Network Based on Attention Mec...

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Huang, Wenning Zhu, Guijie Fan, Zhun Li, Wenji Rong, Yibiao Cai, Yuwei Key Lab of Digital Signal and Image Processing of Guangdong Province College of Engineering Shantou University Shantou515063 China

ISBN: (纸本)9781665425278

In recent years, convolutional neural networks (CNNs) have achieved excellent performance in pavement crack segmentation tasks. However, CNNs usually need high computational cost and large storage. As a result, CNN slimming is important for embedded systems with limited resources. Inspired by the channel attention techniques in CNNs, we propose an effective method to slim CNNs based on attention mechanism. The proposed method first removes the unimportant filters and their connecting feature maps according to their attention scales. The retraining process is then performed on the slimmed model to regain performance. The proposed pruning method is easily embedded in common convolutional layers without any dedicated software libraries. Comprehensive experiments show that the proposed method can prune over 40% parameters of CNNs applied on pavement crack segmentation tasks while the deterioration in performance is slight compared with the original UNet architecture. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Video smoke removal based on low-rank tensor completion via spatial-temporal continuity constraint

Video smoke removal based on low-rank tensor completion via ...

引用

作者： Zhu, Hu Xu, Guoxia Liu, Lu Deng, Lizhen Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunication Nanjing China Department of Computer Science Norwegian University of Science and Technology Gjovik Norway National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and Telecommunication Nanjing China

Smoke has a very bad effect on the outdoor vision system. Not only are the videos with poor visual effects obtained, but also the quality and structure of the videos are reduced. In this paper, we propose a video smoke removal method based on low-rank tensor completion via spatial-temporal continuity constraint. The proposed method is based on the smoke mixing model and consider the sparseness of smoke and the global and local consistency of clean video. Then, the optimal solution of the smoke removal algorithm model is quickly realized by the Alternating Direction Method of Multiplier. Finally, we evaluate the experiment results of real-world data and simulated data from the visual effects and objective indicators. And the experiment results show that our proposed algorithm can achieve better smoke removal results. © 2021 John Wiley & Sons, Ltd.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Homography matrix genetic consensus estimation algorithm

Homography matrix genetic consensus estimation algorithm

引用

2010 International Conference on Audio, Language and image processing, ICALIP 2010

作者： Yao, Da Zhou, Jun Xue, Zhi Institute of Image Communication and Information Processing Shanghai Jiao Tong Universit 200240 Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmissions 200240 Shanghai China

ISBN: (纸本)9781424458653

Homography matrix plays an important role in image stitching, camera calibration and other areas of computer vision. This paper presents a novel robust algorithm HM-GCE to estimate homography matrix with principles of genetic algorithm. Related experiments prove its superiority on the robustness, precision and time-consuming compared to the RANSAC algorithm. ©2010 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Study of the electrocardiogram's ST segment based on multiscale entropy

引用

Nanjing Youdian Daxue Xuebao (Ziran Kexue Ban)/Journal of Nanjing University of Posts and Telecommunications (Natural Science) 2008年第3期28卷 70-72+76页

作者： Wang, Jun Ma, Qian-Li Image Processing and Image Communications Key Lab. Nanjing University of Posts and Telecommunications Nanjing 210003 China

The ST segment of electrocardiogram (ECG) was studied using multiscale entropy (MSE) in the first time, and the MSE results of ST segments were compared with those of ECGs. It was found that the MSE values of electrocardiogram from healthy human and coronary heart disease (CHD) patients are close and both are larger than those from myocardial infarction (MI) patients. For the MSE values of ST segments, the least and the largest is those from the healthy people and from CHD patients respectively, and in the middle is those from MI patients. A reasonable explanation of the results is given. These characteristics of ECG complexity change have important clinical significance for early diagnosis.

关键词： Coronary heart disease Electrocardiogram Multiscale entropy ST segment

来源：评论

学校读者我要写书评

暂无评论

Real-time target tracking with particle filter in moving monocular camera

Real-time target tracking with particle filter in moving mon...

引用

5th International Symposium on Multispectral image processing and Pattern Recognition

作者： Liu, Guocheng Wang, Yongji Huazhong Univ Sci & Technol Key Lab Image Processing & Intelligent Control Chinese Educ Minist Wuhan 430072 Peoples R China

ISBN: (纸本)9780819469502

In this paper, we propose an improved particle filter algorithm for real-time tracking a randomly moving target in dynamic environment with a moving monocular camera. For making the tracking task robustly and effectively, color histogram based target model is integrated into particle filter algorithm. Bhattacharyya distance is used to weight samples by calculating each sample's histogram with a specified target model and it makes the measurement matching and samples' weight updating more reasonable. In order to reduce sample depletion, the improved algorithm will be able to take the latest observation into account. The experimental results confirm that the method is effective even when the monocular camera is moving and the target object is partially occluded in a clutter background.

关键词： visual tracking particle filter state-space model

来源：评论

学校读者我要写书评

暂无评论

A phase matching and region segmentation stereo depth mixed extraction algorithm

A phase matching and region segmentation stereo depth mixed ...

引用

2010 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2010

作者： Liu, Shengxia Zhou, Jun Wu, Meng Institute of Image Communication and Information Processing Shanghai Jiao Tong University 200240 Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmissions 200240 Shanghai China

ISBN: (纸本)9781424444625

This paper presents a novel dense disparity estimation method using phase matching and color segmentation. In the proposed method, the initial disparity map is firstly obtained by an improved phase-based stereo matching solution. The solution effectively restrains two tough problems of phase singularities and phase wrap, in a coarse-to-fine approach, by using Dual-Tree Complex Wavelet Transform (DT CWT) to extract the phase of the stereo images. The initial disparity is then refined by color segmentation and disparity plane fitting. Segmentation-based methods have an advantage of well representation of disparities on discontinuous region. Experimental results indicate that the proposed method is superior in generating disparity maps with high accuracy and clean edges.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Hybrid immune algorithm with Lamarckian local search for multi-objective optimization

引用

Memetic Computing 2010年第1期2卷 47-67页

作者： Gong, Maoguo Liu, Chao Jiao, Licheng Cheng, Gang Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University 710071 Xi'an China

Lamarckian learning has been introduced into evolutionary computation as local search mechanism. The relevant research topic, memetic computation, has received significant amount of interests. In this study, a novel Lamarckian learning strategy is designed for improving the Nondominated Neighbor Immune Algorithm, a novel hybrid multi-objective optimization algorithm, Multi-objective Lamarckian Immune Algorithm (MLIA), is proposed. The Lamarckian learning performs a greedy search which proceeds towards the goal along the direction obtained by Tchebycheff approach and generates the improved progenies or improved decision vectors, so single individual will be optimized locally and the newcomers yield an enhanced exploitation around the nondominated individuals in less-crowded regions of the current trade-off front. Simulation results based on twelve benchmark problems show that MLIA outperforms the original immune algorithm and NSGA-II in approximating Pareto-optimal front in most of the test problems. When compared with the state of the art algorithm MOEA/D, MLIA shows better performance in terms of the coverage of two sets metric, although it is laggard in the hypervolume metric. © 2009 Springer-Verlag.

关键词： Artificial immune system Lamarckian learning Memetic algorithm Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

A novel spatial information recovery algorithm based on fuzzy clustering in H.264

A novel spatial information recovery algorithm based on fuzz...

引用

IEEE International Symposium on Intelligent Signal processing and communication Systems (ISPACS)

作者： Han Shen Xiu-chang Zhu Jiangsu Province Key Lab on Image Processing & Image Communication Nanjing University of Posts and Telecommunications China

As no reference frame can be obtained in Intra-frame error concealment, reducing the degradation of spatial reconstructed image is one of the key techniques in error concealment. In this paper, a novel spatial error concealment algorithm based on fuzzy clustering for Intra-frame in H.264 is proposed. This proposed algorithm gives a new selection of eigenvectors and similarity measurement for fuzzy clustering. The experimental results show that the proposed algorithm can improve the edge details, achieve a better subjective quality of the recovered image and increase PSNR (Peak Signal-to-Noise Ratio) as well.

关键词： Clustering algorithms Signal processing algorithms image reconstruction Degradation PSNR Resilience Video sequences Frequency Discrete cosine transforms Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Spatial Error Concealment Based on Judgement on Edge Information

Spatial Error Concealment Based on Judgement on Edge Informa...

引用

2008 International Conference on Audio，Language and image processing(2008国际声音、语言、图像过程大会)

作者： XueFeng Zhan XiuChang Zhu Nanjing Univ.of Posts & Telecomm Image Processing and Image Communication Key Lab Nanjing 210003

An efficient spatial error concealment algorithm is proposed for corrupted image by transmission losses in this work. Firstly, information of edges in the neighboring blocks is extracted by judgements on which edges may traverse the loss block. Then, all detected edges are divided into relevant and irrelevant edge. Subsequently, one or more directions for interpolation can be selected from the relevant edge set by minimizing the boundary pixel difference for each direction. The method improves the capability of recovering more high-detailed contents of lost block with low complexity. Experimental results demonstrate the better performance of the proposed methods as compared to previous techniques.

关键词： image edge detection Pixel Interpolation image reconstruction PSNR image restoration Sun

来源：评论

学校读者我要写书评

暂无评论

Distributed Equally Surrounding Control for Multiple Unmanned Surface Vessels 41

Distributed Equally Surrounding Control for Multiple Unmanne...

引用

第41届中国控制会议

作者： Fu-Long Hu Chuan-Cong Tang Bin-Bin Hu Bowen Xu Hai-Tao Zhang School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Controland the State Key Lab of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper proposes a distributed controller to equally surround a static target with multiple unmanned surface vessels(USVs).By utilizing the mutually repulsive method,the proposed controller addresses the equally surrounding problem,taking into account the influence of time-varying topologies,and the total number USVs which is a 'global information is not used in the *** asymptotic convergence of the closed-loop multi-USV system is guaranteed with rigorous ***,the effectiveness of the controller is verified by numerical simulations.

关键词： Equally surrounding unmanned surface vessels(USVs) multi-agent system

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：