检索结果-内蒙古大学图书馆

2nd International Symposium on Electrical, Electronics and Information Engineering, ISEEIE 2022

作者： Pan, Chaolin Zhu, Xiaoyang Chu, Jun Nanchang Hangkong University Department of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang China

ISBN: (数字)9781665468749

ISBN: (纸本)9781665468749

Real-time object detection has been a critical component of onboard instrumentation for next-generation autonomous driving. To enable safety and reliability in autonomous driving systems, we must continue advancing its real-time object detection accuracy for future autonomous driving systems in complex environments. Existing works in real-time object detection cannot accurately detect objects with similar appearances and in complex environments. In particular, existing approaches missed many essential features because of the loss of multi-scale contextual features. Therefore, they cannot differentiate objects that have a similar appearance, a low-resolution, and a small size. To solve these issues, and to advance real-time object detection accuracy, we develop GFENet (Global Feature Enhancement Network), an end-to-end real-time object detection framework. First, we introduce a convolutional attention module that integrates spatial and channel-wise features and eliminates ineffective features to enable a strong feature representation of the network, followed by a lightweight residual module that further advances the feature representation by highlighting salient changes in features. Second, we build an adaptive feature fusion module to adaptively learn weights of multi-scale contextual features across layers, aiming to strengthen weights for small-size objects. We comprehensively evaluate GFENet on two leading object detection datasets-PASCAL VOC and MS COCO. The evaluation results (mAP of 82.9 and FPS of 31 on PASCAL VOC;mAP of 39.0 and FPS of 23 on MS COCO) show the outperformance of GFENet compared to competing baseline methods. © 2022 IEEE.

关键词： Instruments Object detection Detectors Feature extraction Real-time systems Safety Reliability

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

A WYNER-ZIV VIDEO CODING METHOD UTILIZING MIXTURE CORRELATION NOISE MODEL

引用

Journal of Electronics(China) 2012年第3期29卷 197-203页

作者： Hu Xiaofei Zhu Xiuchang Image Processing and Image Communication Key Laboratory Nanjing University of Posts and Telecommunications Nanjing 210003 China College of Geography and Biological Information Nanjing University of Posts and Telecommunications Nanjing 210003 China

In Wyner-Ziv (WZ) Distributed Video Coding (DVC), correlation noise model is often used to describe the error distribution between WZ frame and the side information. The accuracy of the model can influence the performance of the video coder directly. A mixture correlation noise model in Discrete Cosine Transform (DCT) domain for WZ video coding is established in this paper. Different correlation noise estimation method is used for direct current and alternating current coefficients. Parameter estimation method based on expectation maximization algorithm is used to estimate the Laplace distribution center of direct current frequency band and Mixture Laplace-Uniform Distribution Model (MLUDM) is established for alternating current coefficients. Experimental results suggest that the proposed mixture correlation noise model can describe the heavy tail and sudden change of the noise accurately at high rate and make significant improvement on the coding efficiency compared with the noise model presented by DIStributed COding for Video sERvices (DISCOVER).

关键词： Transform domain Wyner-Ziv (WZ) DIStributed COding for Video sERvices (DISCOVER) Video coding Correlation noise model Mixture Laplace-Uniform Distribution Model (MLUDM)

来源：评论

学校读者我要写书评

暂无评论

Edge Detection Using Matched Filter 27

Edge Detection Using Matched Filter

引用

第27届中国控制与决策会议

作者： LUO Hai-bo JIAO An-bo XU Ling-yun SHAO Chun-yan Shenyang Institute of Automation Chinese Academy of Sciences Key Laboratory of Optical-Electronics Information Processing Chinese Academy of Science Key Laboratory of Image Understanding and Computer Vision University of Chinese Academy of Sciences Key Laboratory of Image Understanding and Computer Vision Liaoning Province

ISBN: (纸本)9781479970186

For target tracking,automatic target recognition and detection applications,they value edge detection sensibility,precision and location accuracy rather than other *** at these three criterions,this paper presents an edge detection algorithm based on matched ***,a matched filter was designed by analyzing the edge model for natural image,then the edge response was computed using the designed matched filter;secondly,the lower and discontinuous filtered responses were further suppressed using a dedicated one-dimension filter;finally,the edge image was obtained by binarizing the edge response with a local adaptive *** results illustrate that the proposed algorithm has more improvement than the Sobel and Canny operators in detection sensibility,precision and location ***,the algorithm can be implemented with parallel pipeline using FPGA,so it is also rather suitable for real-time applications.

关键词： edge detection,matched filter,local adaptive threshold,real-time application,noise suppression

来源：评论

学校读者我要写书评

暂无评论

Multi-view synthesis using the relative affine structure from video sequences

Multi-view synthesis using the relative affine structure fro...

引用

International Conference on Multimedia and Signal processing (CMSP)

作者： Huo, Zhiyong Liu, Tianliang Zhu, Xiuchang Jiangsu Key Laboratory of Image Processing and Communication Nanjing Univ. of Posts and Telecommun. Nanjing China

ISBN: (纸本)9780769543567

This paper proposes an approach for Multi-view synthesis, the process of view synthesis based on the relative affine structure. We specifying the virtual camera position in an uncalibrated setting, based on the interpolation of the motion among the reference views. Novel images can be rendered from virtual cameras moving on parametric trajectories. Synthetic and real experiments illustrate the approach. © 2011 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Survey on Negative Transfer

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 305-329页

作者： Wen Zhang Lingfei Deng Lei Zhang Dongrui Wu the Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China IEEE the School of Microelectronics and Communication Engineering Chongqing UniversityChongqing 400044China

Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation expense,privacy concerns,***,the effectiveness of TL is not always *** transfer(NT),i.e.,leveraging source domain data/knowledge undesirably reduces learning performance in the target domain,and has been a long-standing and challenging problem in *** approaches have been proposed in the literature to address this ***,there does not exist a systematic *** paper fills this gap,by first introducing the definition of NT and its causes,and reviewing over fifty representative approaches for overcoming NT,which fall into three categories:domain similarity estimation,safe transfer,and NT *** areas,including computer vision,bioinformatics,natural language processing,recommender systems,and robotics,that use NT mitigation strategies to facilitate positive transfers,are also ***,we give guidelines on NT task construction and baseline algorithms,benchmark existing TL and NT mitigation approaches on three NT-specific datasets,and point out challenges and future research *** ensure reproducibility,our code is publicized at https://***/chamwen/NT-Benchmark.

关键词： Domain adaptation domain similarity negative transfer positive transfer transfer learning

来源：评论

学校读者我要写书评

暂无评论

image retrieval based on character-matching technology

Image retrieval based on character-matching technology

引用

5th International Conference on Information Assurance and Security, IAS 2009

作者： Shan, Zhao Jing, Liu School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Jiangsu Province Key Lab. on Image Processing and Image Communication Nanjing University of Posts and Communication Nanjing 210003 China

ISBN: (纸本)9780769537443

In order to introduce effective text-retrieval technologies into content-based image retrieval, a novel method based on string-matching technology was presented incorporating the different sensitivity along variant directions of human visual system. The image is firstly divided into non-overlapped blocks and sub-feature is extracted according to the human visual feature. Then, a novel descriptor is defined. Based on which, the sub-features is mapping into characters and the image into the text. Finally, the technology of the character string matching is adopted as the similarity measurement. Meantime, the situation information of character is considered, an adjusted method is proposed. Experimental results show that the proposed method has sound and robust retrieval performance. © 2009 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

A NOVEL METHOD TO REALIZE COMPRESSED VIDEO SUPER-RESOLUTION RECONSTRUCTION

引用

Journal of Electronics(China) 2006年第2期23卷 310-313页

作者： Zhou Liang Liu Feng Zhu Xiuchang Information Industry Ministry and Jiangsu Province Key Lab of lmage Processing and Image Communication Nanjing University of Posts and Communications Nanjing 210003 China

This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject to Poisson-Markov distribution, then constructing the projecting convex based on MAP. According to the characteristics of compressed video, two different convexes are constructed based on integrating the inter-frame and intra-frame information in the wavelet-domain. The results of the experiment demonstrate that the new method not only outperforms the traditional algorithms on the aspects of PSNR (Peak Signal-to-Noise Ratio), MSE (Mean Square Error) and reconstruction vision effect, but also has the advantages of rapid convergence and easy extension.

关键词： Super-resolution Compressed video image reconstruction MAP-POCS

来源：评论

学校读者我要写书评

暂无评论

Epileptogenic Region Detection Based on Deep CNN with Transfer Learning 11

Epileptogenic Region Detection Based on Deep CNN with Transf...

引用

11th IEEE International Conference on Advanced Infocomm Technology, ICAIT 2019

作者： Qu, Guiguo Yuan, Qi Shandong Normal University Shandong Province Key Laboratory of Medical Physics and Image Processing Technology Jinan250358 China

ISBN: (纸本)9781728147789

The Epileptic seizure can be detected using Electroencephalogram (EEG) signals. It is important for the detection of Epilepsy disease that the detection of epileptogenic region in brain. The focal signal is the signals which from epileptogenic region in brain and the non-focal signal is the signals which from normal regions in brain. Hence, It is important for Epilepsy to detect the focal signal. This paper proposes an automatic detection and diagnosis of EEG signals for Epilepsy disease based on deep learning structure and transfer learning. However, the EEG datasets are usually too small to train the entire deep learning structure. It is easy to be trapped into overfitting during training. Therefore, the transfer learning was introduced to train the deep neural network. Firstly, we obtained the pre-trained AlexNet structure. Then, the parameters of the last three layers were replaced with random weights and the rest parameters served as the initial values. Finally, we used the EEG dataset to train the modified model. Experimental results show that the method attained accuracy of 95.00%, which outperformed state-of-the-art approaches. © 2019 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A hierarchical diffusion algorithm for community detection in social networks

A hierarchical diffusion algorithm for community detection i...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery

作者： Shen, keyi Song, Li Yang, Xiaokang Zhang, Wenjun Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University China

ISBN: (纸本)9780769542355

Community discovery is one of the most important steps to understand the social networks. We propose a hierarchical diffusion method to detect the community structure. Our algorithm is based on the idea that people in different communities usually share less common friends. We also make use of the fact that people usually make decisions based others' choices, especially their friends'. Our algorithm can distinguish between pseudo-communities and meaningful ones. Tests on both classical and synthetic benchmarks show that our algorithm is comparable to state-of-the-art community detection algorithms in both computational complexity and accuracy measured by the so-called normalized mutual information. © 2010 IEEE.

关键词： 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：