检索结果-内蒙古大学图书馆

作者： Qiu, Jingbang Zhang, Chongyang Zheng, Shibao Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai 200240 China Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9789810863227

Abnormality Detection (AD), being the core part of intelligent surveillance systems, is calling for growing research interest due to its importance in providing higher efficiency and labor saving. In this paper, we propose a novel Bayesian Network (BN) based AD method for smart surveillance in scenes containing large scale viewpoint changes without modelrelearning. In the proposed AD scheme, Reasoning Layer is introduced into BN to strengthen logical inferences, and a localized Genetic Algorithm (GA) is developed to optimize BN parameters and structure. With the expert knowledge aided BN structure modeling and GA based optimization, the proposed method can provide more robust detection experience with retained accuracy. Experiments on unlearned surveillance test sequences are shown to exhibit the validity of this method. ©Memetic Computing Society.

关键词： Bayesian networks

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

Real-time position estimation and tracking of a basketball

Real-time position estimation and tracking of a basketball

引用

2012 IEEE International Conference on Signal processing, Computing and Control, ISPCC 2012

作者： Chakraborty, Bodhisattwa Meher, Sukadev Digital Image and Speech Processing Lab National Institute of Technology Rourkela Odisha 769008 India Dept. of Electronics and Communication Engineering National Institute of Technology Rourkela Odisha 769008 India

ISBN: (纸本)9781467313179

In this paper, an algorithm to detect the position of a basketball in a real time outdoor video is proposed. The problem of ball detection in sports video arises due to the occlusion of the ball with the players, the presence of many moving objects like spectators, flags, twigs and branches of the tree etc. The ball image is also getting distorted due to the high speed of the ball. Thus the conventional direct detection and tracking algorithm fails in various occasions. It is much advantageous to study the trajectory information of a ball and estimate the ball location using the trajectory information. In this trajectory based algorithm, firstly the ball like objects are detected and a set of ball candidates are generated for each frame. Then the set of candidate trajectories are plotted. From these potential trajectories, the actual ball trajectory is estimated by studying the trajectory information. The missing ball location in any frame can also be predicted by trajectory interpolation technique. In this paper, we also propose an efficient background detection method using the approximate median value of the background pixels, thus achieving a high degree of segmentations of the moving objects in the foreground. This algorithm provides excellent result under a high degree of occlusion and works satisfactorily in the presence of many moving objects along with the ball in the scene. © 2012 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Object tracking in hyperspectral videos with convolutional features and kernelized correlation filter 1st

Object tracking in hyperspectral videos with convolutional f...

引用

1st International Conference on Smart Multimedia, ICSM 2018

作者： Qian, Kun Zhou, Jun Xiong, Fengchao Zhou, Huixin Du, Juan Lab of Optoelectronic Imaging and Image Processing Xidian University Xi’an China School of Information and Communication Technology Griffith University Brisbane Australia College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9783030043742

Target tracking in hyperspectral videos is a new research topic. In this paper, a novel method based on convolutional network and Kernelized Correlation Filter (KCF) framework is presented for tracking objects of interest in hyperspectral videos. We extract a set of normalized three-dimensional cubes from the target region as fixed convolution filters which contain spectral information surrounding a target. The feature maps generated by convolutional operations are combined to form a three-dimensional representation of an object, thereby providing effective encoding of local spectral-spatial information. We show that a simple two-layer convolutional networks is sufficient to learn robust representations without the need of offline training with a large dataset. In the tracking step, KCF is adopted to distinguish targets from neighboring environment. Experimental results demonstrate that the proposed method performs well on sample hyperspectral videos, and outperforms several state-of-the-art methods tested on grayscale and color videos in the same scene. © 2018, Springer Nature Switzerland AG.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

A new method in highway route design：joining circular arcs by a single C-Bezier curve with shape paramete

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2009年第4期10卷

作者： Hua-hui CAI Guo-jin WANG Institute of Computer Graphics and Image Processing State Key Lab of CAD & CG Zhejiang University

We constructed a single C-B zier curve with a shape parameter for G2 joining two circular arcs. It was shown that an S-shaped transition curve, which is able to manage a broader scope about two circle radii than the B zier curves, has no curvature extrema, while a C-shaped transition curve has a single curvature extremum. Regarding the two kinds of curves, specific algo- rithms were presented in detail, strict mathematical proofs were given, and the effectiveness of the method was shown by examples. This method has the following three advantages: (1) the pattern is unified; (2) the parameter able to adjust the shape of the tran- sition curve is available; (3) the transition curve is only a single segment, and the algorithm can be formulated as a low order equation to be solved for its positive root. These advantages make the method simple and easy to implement.

关键词： Transition curve Shape parameter C-Bezier curve Monotone curvature

来源：评论

学校读者我要写书评

暂无评论

A Novel Representation for Video-based Person Reidentification with Attribute-constraints

A Novel Representation for Video-based Person Reidentificati...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： Wanru Song Jieying Zheng Yahong Wu Qingqing Zhao Changhong Chen Feng Liu Jiangsu Key Lab of Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781538646748;9781538646731

Person re-identification is an important task in the field of intelligent video surveillance, which has become one of the research focus spots in the field of computer vision. Video-based person re-identification aims to verify a pedestrian identity of the video sequences which captured from non-overlapping cameras at different time. In this paper, we propose a novel feature extractor based on LSTM networks. These LSTM networks are used to extract the effective space-time feature representation named the attribute-constraints space-time feature (ASTF). Different from other methods, we manually annotate pedestrians in videos with three attributes. In the meantime, the attributes with the IDs of pedestrians are regarded as labels to train the feature extractor. The ASTF representation for a testing video is extracted by this feature extractor, which is an effective space-time feature representation for video-based re-identification. Extensive experiments on two public datasets demonstrate that our approach outperforms the state-of-the-art video-based re-identification methods.

关键词： Feature extraction Task analysis Training Cameras Testing Measurement Video sequences

来源：评论

学校读者我要写书评

暂无评论

Hotspots on modern medical imaging and image analysis

Hotspots on modern medical imaging and image analysis

引用

IEEE/EMBS International Summer School on Medical Devices and Biosensors

作者： Wu-fan Chen Key Lab for Medical Image Processing of Guangdong Province China

Vision information processing (VIP) is the important supports of image processing. Currently, VIP has become as a leader direction in remote sense image processing (which mostly serves the government and military) and in medical image processing (which widely serves a great numbers of patients). Medical imaging and medical image analysis techniques are the hotspots of the biomedical engineering. On one hand, different from optical imaging, modern medical imaging such as CT, MR and PET have the very complex imaging mechanisms with deep mathematic fundamental and are entirely different with each other. Advanced and novel precise techniques in medical imagine are also needed, such as design of various filters, calibration techniques for different artifacts, fast imaging methods and low dose CT reconstruction. New important applications of medical imaging are still in progress with high speed, which include special imaging technique to some diseases, multi-functional imaging equipments and special imaging devices for brain or hand. On the other hand, medical image analysis such as image segmentation and image registration as the basic medical image processing still require some novel techniques to make it more effectively. Fuzziness of physiology estimation, stochastic behavior of imaging process, and ill condition behavior of mathematic model may be the dispute problems for a long time. For more convenient, we are to quite our recent research results to illustrate above the hotspots.

关键词： Biomedical imaging image analysis Optical imaging image processing Biomedical image processing Computed tomography Mathematics Information processing Remote sensing Government

来源：评论

学校读者我要写书评

暂无评论

Review of the deep learning for food image processing

引用

International Journal of Agricultural and Biological Engineering 2024年第5期17卷 15-30页

作者： Chenrui Niu Xiayang Ying Gan Pei Menghan Hu Guangtao Zhai Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic EngineeringEast China Normal UniversityShanghai 200241China Department of General Surgery Pancreatic Disease CenterRuijin HospitalShanghai Jiaotong University School of MedicineShanghai 200025China Istitute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai 200240China

As deep learning techniques are increasingly applied with greater depth and sophistication in the food industry,the realm of food image processing has progressively emerged as a central focus of research *** work provides an overview of key practices in food image processing techniques,detailing common processing tasks including classification,recognition,detection,segmentation,and image retrieval,as well as outlining metrics for evaluating task performance and thoroughly examining existing food image datasets,along with specialized food-related *** terms of methodology,this work offers insight into the evolution of food image processing,tracing its development from traditional methods extracting low and intermediate-level features to advanced deep learning techniques for high-level feature extraction,along with some synergistic fusion of these *** is believed that these methods will play a significant role in practical application scenarios such as self-checkout systems,dietary health management,intelligent food service,disease etiology tracing,chronic disease management,and food safety ***,due to the complex content and various types of distortions in food images,further improvements in related methods are needed to meet the requirements of practical applications in the *** is believed that this study can help researchers to further understand the research in the field of food imaging and provide some contribution to the advancement of research in this field.

关键词： deep learning food image processing feature extraction dietary health

来源：评论

学校读者我要写书评

暂无评论

A New Demapping Technique for 16-APSK Modulation for Digital Video Broadcasting in AWGN Channel

A New Demapping Technique for 16-APSK Modulation for Digital...

引用

International Conference on Convergence Information Technology

作者： Pervaiz Ali Farhan Hussain Jechang Jeong Image Communication and Signal Processing Lab Hanyang University Seoul South Korea

In this paper, we propose new demapping scheme for the 16-APSK modulation, which reduces the computational complexity of demapping process. Compared to existing soft demapping methods, which calculate a decision metric for each constellation point, and hard demapping, which need a detailed look-up table, the new technique needs a short look-up table and no decision metric is needed to be calculated, thus reducing the complexity. The BER performance simulations reveal that this simplified demapping scheme does not cause any penalty on performance and retains same BER as those of existing techniques.

关键词： Digital modulation Digital video broadcasting AWGN channels Additive white noise Gaussian noise Satellite broadcasting Table lookup Bit error rate Phase modulation Peak to average power ratio

来源：评论

学校读者我要写书评

暂无评论

A new noise erosion operator for anisotropic diffusion

引用

Chinese Optics Letters 2004年第5期2卷 268-270页

作者：蔡超丁名跃周成平张天序 Institute for Pattern Recognition and Artificial Intelligence State Education Commission Key Lab for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074

A noise erosion operator based on partial differential equation (PDE) is introduced, which has an excellent ability of noise removal and edge preservation for two-dimensional (2D) gradient data. The operator is applied to estimate a new diffusion coefficient. Experimental results demonstrate that anisotropic diffusion based on this new erosion operator can efficiently reduce noise and sharpen object boundaries.

关键词： Anisotropic diffusion Diffusion

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：