检索结果-内蒙古大学图书馆

Structured Computational Modeling of Human Visual System for No-reference image Quality Assessment

International Journal of Automation and computing 2021年第2期18卷 204-218页

作者： Wen-Han Zhu Wei Sun Xiong-Kuo Min Guang-Tao Zhai Xiao-Kang Yang MoE Key Lab of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China Institute of Image Communication and Information Processing Shanghai Jiao Tong UniversityShanghai 200240China

Objective image quality assessment(IQA)plays an important role in various visual communication systems,which can automatically and efficiently predict the perceived quality of *** human eye is the ultimate evaluator for visual experience,thus the modeling of human visual system(HVS)is a core issue for objective IQA and visual experience *** traditional model based on black box fitting has low interpretability and it is difficult to guide the experience optimization effectively,while the model based on physiological simulation is hard to integrate into practical visual communication services due to its high computational *** bridging the gap between signal distortion and visual experience,in this paper,we propose a novel perceptual no-reference(NR)IQA algorithm based on structural computational modeling of *** to the mechanism of the human brain,we divide the visual signal processing into a low-level visual layer,a middle-level visual layer and a high-level visual layer,which conduct pixel information processing,primitive information processing and global image information processing,*** natural scene statistics(NSS)based features,deep features and free-energy based features are extracted from these three *** support vector regression(SVR)is employed to aggregate features to the final quality *** experimental comparisons on three widely used benchmark IQA databases(LIVE,CSIQ and TID2013)demonstrate that our proposed metric is highly competitive with or outperforms the state-of-the-art NR IQA measures.

关键词： image quality assessment(IQA) no-reference(NR) structural computational modeling human visual system visual feature extraction

来源：评论

学校读者我要写书评

暂无评论

Approaches to image retrieval using fuzzy set theory

Approaches to image retrieval using fuzzy set theory

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Li, Yang Xuelong, Hu Jun, Pan School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

This paper mainly presents two approaches for image retrieval. There is some faintness in color locating in quantification boundary when image color is quantized. The membership function in fuzzy set theory can describe the fuzzy transition preferably. In this paper, the membership function in HSI color space is adopted to solve the problem above. At the same time, spatial information is integrated with color feature to describe the image content more truly. Due to the importance of texture feature, gray concurrence matrix is extracted. In the second part of this paper, retrieval scheme combining four image feature descriptors is presented, and then follows Fuzzy Hamming Distance (FHD) which is used as a fuzzy similarity measure. We have performed an experiment on a 1000 images database and our results show higher retrieval accuracy. © 2008 IEEE.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

A camera self-calibration method based on dual constraints of multi-view images

A camera self-calibration method based on dual constraints o...

引用

2011 International Conference on Wireless communications and Signal processing, WCSP 2011

作者： Liu, Feng Han, Weiwei Xu, Qiong Lin, Qiongjie Fan, Jingjing Image Processing and Image Communication Jiangsu Key Laboratory Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781457710100

Camera calibration is the essential step of obtaining 3D information from 2D views in the field of computer vision, which is widely used in the area of 3D reconstruction, navigation, visual supervision, etc. A camera self-calibration method based on dual constraints of multi-view images is proposed to make calibration possible when there is no reference calibration block or the movement of camera is arbitrary. In this method, multi-view images are preprocessed first to select three images which are most suitable for camera self-calibration, then we use the method based on the genetic algorithm, the camera parameters are finally estimated by using epipolar geometry matching error and reprojection error as fitness functions as two steps. Experimental results show that the proposed camera self-calibration method is correct and effective. © 2011 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Video object matching based on sift algorithm

Video object matching based on sift algorithm

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Yingcheng, Tang Zhenghua, Zhang School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Prov. Key Lab for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

SIFT (Scale Invariant Feature Transform) is used to solve visual tracking problem, where the appearances of the tracked object and scene background change during tracking. The implementation of this algorithm has five major stages: scale-space extrema detection;keypoint localization;orientation assignment;keypoint descriptor;keypoint matching. From the beginning frame, object is selected as the template, its SIFT features are computed. Then in the following frames, the SIFT features are computed. Euclidean distance between the object's SIFT features and the frames' SIFT features can be used to compute the accurate position of the matched object. The experimental results on real video sequences demonstrate the effectiveness of this approach and show this algorithm is of higher robustness and real-time performance. It can solve the matching problem with translation, rotation and affine distortion between images. It plays an important role in video object tracking and video object retrieval. © 2008 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Pipeline Leak Detection, Location and Repair 11

Pipeline Leak Detection, Location and Repair

引用

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

作者： Lin, Peihan Li, Xiaoming Long, Zhoubin Ma, Peili Zhu, Guijie Wei, Jiahong Fan, Zhun Engineering College Shantou University Department of Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou China

ISBN: (纸本)9781665425278

Pipeline leak-sealing under the high pressure and temperature condition is the way to repair a pipeline while the equipment is in continuous work in a power plant or chemical plant. At present, most of this work is carried out by operators with carrying heavy pipeline repairing tools. However, the medium transported by the pipeline is high temperature and high pressure, even acidic or corrosive, which is dangerous to the operators. In order to solve this issue, a pipeline leak-sealing robot is designed to replace the operators to perform pipeline leak-sealing tasks. Furthermore, we design and develop a caulking actuator for the pipeline leak-sealing task and applied a deep learning method to locate the leak points on the pipeline. The experimental results demonstrate that the caulking actuator achieves good performance to repair pipeline leaks, and the accuracy of the method for locating pipeline leaks meets the demand for leak location. © 2021 IEEE.

关键词： Chemical plants

来源：评论

学校读者我要写书评

暂无评论

A general end-to-end diagnosis framework for manufacturing systems

引用

National Science Review 2020年第2期7卷 418-429页

作者： Ye Yuan Guijun Ma Cheng Cheng Beitong Zhou Huan Zhao Hai-Tao Zhang Han Ding School of Artificial Intelligence and Automation MOE Key Lab of Intelligent Control and Image Processing Huazhong University of Science and Technology State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology

The manufacturing sector is envisioned to be heavily influenced by artificial-intelligence-based technologies with the extraordinary increases in computational power and data volumes. A central challenge in the manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications. Here, we propose a general data-driven,end-to-end framework for the monitoring of manufacturing systems. This framework, derived from deep-learning techniques, evaluates fused sensory measurements to detect and even predict faults and wearing conditions. This work exploits the predictive power of deep learning to automatically extract hidden degradation features from noisy, time-course data. We have experimented the proposed framework on 10 representative data sets drawn from a wide variety of manufacturing applications. Results reveal that the framework performs well in examined benchmark applications and can be applied in diverse contexts,indicating its potential use as a critical cornerstone in smart manufacturing.

关键词： manufacturing systems deep learning diagnosis and monitoring

来源：评论

学校读者我要写书评

暂无评论

Prediction of tourists flow distribution based on transition probability matrix

Prediction of tourists flow distribution based on transition...

引用

8th International Conference on Information Science and Digital Content Technology, ICIDT 2012

作者： Hu, Yuting Xie, Rong Zhang, Wenjun Xu, Yi Institute of Image Communication and Information Processing Shanghai Digital Media Processing and Transmission Key Lab. Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9788988678695

A new prediction algorithm of tourists flow distribution based on transition probability matrix (TPM) is proposed in this paper. In order to analyze the visitor transition-behavior and the tourists distribution model, the tourists flow distribution of 5 zones at Shanghai Expo site is predicted based on the TPM, which is estimated by use of multivariate linear regression in optimization. The extensive experimental results verify the efficiency and the correctness of the proposed algorithm over the wavelet neural network prediction method. © 2012 AICIT.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Retinex based low-light image enhancement using guided filtering and variational framework

引用

Optoelectronics Letters 2018年第2期14卷 156-160页

作者：张诗唐贵进刘小花罗苏淮王大东 Jiangsu Key Lab on Image Processing & Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China School of Electrical Engineering and Computing The University of Newcastle NSW 2308 Australia CSIRO Data61 PO Box 76 Epping NSW 1710 Australia

A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV color space to get the V channel. Next, the illuminations are respectively estimated by the guided filtering and the variational framework on the V channel and combined into a new illumination by average gradient. The new reflectance is calculated using V channel and the new illumination. Then a new V channel obtained by multiplying the new illumination and reflectance is processed with contrast limited adaptive histogram equalization(CLAHE). Finally, the new image in HSV space is converted back to RGB space to obtain the enhanced image. Experimental results show that the proposed method has better subjective quality and objective quality than existing methods.

关键词： RGB CLAHE Retinex based low-light image enhancement using guided filtering and variational framework HSV

来源：评论

学校读者我要写书评

暂无评论

An Efficient H.264 Rate Control Scheme with Accurate \theta Estimation

An Efficient H.264 Rate Control Scheme with Accurate \theta ...

引用

International Conference on image and Graphics (ICIG)

作者： Qingde Chen Dong Hu The provincial key lab of image processing and image communications Nanjing University of Posts and Telecom Nanjing PRC

An efficient rate control scheme for H.264 encoding has been proposed, where p domain source modeling, which was first used in block-based DCT coding system such as H.263, MPEG-2 and MPEG-4, is introduced. For accurate rate control, parameter thetas, the slope of the linear function of bit rate R vs. p, should be estimated in advance for each frame. Least-Mean-Square (LMS) algorithm is adopted for the estimation of thetas, which is further refined by a new factor thetas-ratio for each frame. Simulation results for standard test sequences show that, compared with JVT-H017, the new algorithm achieves better coding performance, while the output bit rates are more accurate.

关键词： Bit rate image coding Discrete cosine transforms Least squares approximation Quantization Communication system control Telecommunication control MPEG 4 Standard Equations Predictive models

来源：评论

学校读者我要写书评

暂无评论

Indoor localization with incomplete observation using set-membership filter

Indoor localization with incomplete observation using set-me...

引用

International Symposium on Micro-NanoMechatronics and Human Science, MHS 2015

作者： Wang, Yuan Huang, Jian Key Lab of Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781479966783

Indoor localization is a popular topic because of the poor performance of GPS in the indoor environment. This paper has provided a new method to achieve the goal of indoor localization. Combining the usage of posture sensors with the Radio Frequency Identification (RFID) technology, we solved the problem of plentiful tags in the traditional RFID indoor localization. The relative localization subsystem is based on posture sensors and the absolute localization subsystem is based on RFID. A set-membership theory based data fusion algorithm is proposed to fuse the data of relative localization and absolute localization. Experimental results show that the proposed data fusion algorithm could significantly reduce the accumulated error of our indoor localization system. © 2015 IEEE.

关键词： Indoor positioning systems

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：