检索结果-内蒙古大学图书馆

12th International Conference on image and Graphics, ICIG 2023

作者： Ding, Xuan Gu, Shuo Yang, Jian PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783031463075

With the development of imaging technology, it becomes increasingly easy to obtain hyperspectral images (HSI) containing rich spectral information. The application of hyperspectral images in autonomous driving is expected to become a reality. Hyperspectral images have higher dimensions and more information than RGB images, which brings the challenge of training with limited samples. It is not easy to train satisfactory semantic segmentation models directly from hyperspectral images. In this paper, we propose a hyperspectral dual-fusion (hyperDF) network that can fully utilize the pre-training knowledge of the RGB modality to improve the performance of hyperspectral semantic segmentation. Specifically, we generate pseudo-color images from hyperspectral images to simulate RGB signals in order to make better use of the pre-trained RGB semantic segmentation models. The pseudo-color and hyperspectral images are processed in a dual encoder structure and then fused through a channel-wise attention fusion module. Finally, a multi-scale decoder injected with low-level features is used to predict the semantic segmentation results. Experimental results on the Hyperspectral City V2.0 dataset show that our method achieves state-of-the-art results, with a mIoU of 51.68%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation using regions in natural scenes

Semantic segmentation using regions in natural scenes

引用

2011 International Conference on Electronic and Mechanical Engineering and Information Technology, EMEIT 2011

作者： Wu, Shilin Zhu, Feng Hao, Yingming Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 China Graduate School Chinese Academy of Sciences Beijing 100049 China Key Laboratory of Optical-Electronics Information Processing Chinese Academy of Sciences Shenyang 110016 China Key Laboratory of Image Understanding and Computer Vision Liaoning Province 110016 China

ISBN: (纸本)9781612840857

By introducing an over-segmentation algorithm into the conditional model (CM), we propose a new region-based CM model (R-CM), and investigate its performance on semantic segmentation of images. In order to incorporate structure information of objects, we segment an image into regions by using an over-segmentation algorithm. Based on the results of CM model, we first consider assigning all pixels in one region with the same label, and then other feature potentials are included to counteract the influence of false over-segmentation. We compare our results to related work on the Olive & Torralba database and show that aside from improved accuracy of the whole database, our model obtains a perceptual improvement, with boundary of different objects correctly labeled. © 2011 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Multiple class segmentation using a scene-based framework

Multiple class segmentation using a scene-based framework

引用

2011 International Conference on Electronics and Optoelectronics, ICEOE 2011

作者： Wu, Shilin Zhu, Feng Miao, Xikui Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 China Graduate School of Chinese Academy of Sciences Beijing 100049 China Key Laboratory of Optical-Electronics Information Processing Chinese Academy of Sciences Shenyang 110016 China Key Laboratory of Image Understanding and Computer Vision Liaoning Province 110016 China

ISBN: (纸本)9781612842738

In this paper, we propose a new scene-based conditional model and investigate its performance on multiple class segmentation of images. By including the scene of an image, we also propose a new texture-environment potential to represent texture environment of a pixel. We compare our results to related work on the Olive & Torralba database and show that our model obtains greatly improved accuracy of the whole database. More significantly, a large perceptual improvement is gained, i.e. details of different objects are correctly labeled. © 2011 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Variable structure multiple model for articulated human motion tracking from monocular video sequences

引用

Science China(Information Sciences) 2012年第5期55卷 1138-1150页

作者： HAN Hong 1,TONG MingLei 2,CHEN ZhiChao 1 & FAN YouJian 1 1 key laboratory of Intelligent Perception and image understanding of Ministry of Education of China,Institute of Intelligent Information Processing,Xidian University,Xi'an 710071,China 2 School of computer and Information Engineering,Shanghai University of Electric Power,Shanghai 200090,China 1. Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China2. School of Computer and Information Engineering Shanghai University of Electric Power Shanghai 200090 China

A new model-based human body tracking framework with learning-based theory is introduced in this *** propose a variable structure multiple model (VSMM) framework to address challenging problems such as uncertainty of motion styles,imprecise detection of feature points,and ambiguity of joint *** human joint points are detected automatically and the undetected points are estimated with Kalman *** motion models are learned from motion capture data using a ridge regression *** model set that covers the total motion set is designed on the basis of topological and compatibility relationships,while the VSMM algorithm is used to estimate quaternion vectors of joint *** using real image sequences and simulation videos demonstrate the high efficiency of our proposed human tracking framework.

关键词： human motion tracking ridge regression model groups design variable structure multiple model (VSMM) motion model group adaptation

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial:Advances in Bio-inspired Heuristics for Computing

引用

CAAI Transactions on Intelligence Technology 2019年第3期4卷 127-128页

作者： XINCHAO ZHAO MAOGUO GONG XINGQUAN ZUO LINQIANG PAN School of Science Beijing University of Posts and TelecommunicationsBeijing 100876PR China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian UniversityXi’an 710071PR China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876PR China Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of AutomationHuazhong University of Science and TechnologyWuhan 430074PR China

Bio-inspired computing (BIC), short for biologically inspired computing, is a field of study that loosely knits together subfields related to the topics of connectionism, social behaviour and emergence. The field of bio-inspired computing brings together researchers from many disciplines, including biology, computer science, mathematics, physics and genetics.

关键词： Guest Editorial Advances Bio-inspired Heuristics Computing

来源：评论

学校读者我要写书评

暂无评论

Parallel Linear Genetic Programming for multi-class classification

Parallel Linear Genetic Programming for multi-class classifi...

引用

作者： Downey, Carlton Zhang, Mengjie Liu, Jing School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China Xidian University Xi'an China

Motivated by biological inspiration and the issue of instruction disruption, we develop a new form of Linear Genetic Programming (LGP) called Parallel LGP (PLGP) for classification problems. PLGP programs consist of multiple lists of instructions. These lists are executed in parallel after which the resulting vectors are combined to produce the classification result. PLGP limits the disruptive effects of crossover and mutation, which allows PLGP to significantly outperform regular LGP. Furthermore, PLGP programs are naturally suited to caching due to their parallel architecture. Although caching techniques have been used in tree based GP, to our knowledge, there are no caching techniques specifically developed for LGP. Thus, a novel caching technique is also developed with the intrinsic properties of PLGP in mind, which can decrease fitness evaluation time by almost an order of magnitude for the classification problems. © Springer Science+Business Media, LLC 2012.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

A Shape Retentive Filtering Algorithm for Post-processing of Instance Contour of Cervical Cell Based on Level Set Method

A Shape Retentive Filtering Algorithm for Post-processing of...

引用

International Conference on computer and Communications (ICCC)

作者： Guangqi Liu Qinghai Ding Moran Ju Haibo Luo Tianming Jin Miao He The Key Laboratory of Image Understanding and Computer Vision Shenyang China Space Star Technology Company Ltd. Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

A novel filtering algorithm is proposed based on level set method (LSM) and linear time Euclidean distance transform (LET) algorithm in this paper, which has the property of shape retention and thus is suitable for post-processing of the initial contours for contacting instances in digital Pap image. As one of our contributions, we propose two new metrics based on the pixel-level average false positive rate and false negative rate that used by baseline method. A significant decrease in pixel-level average false positive rate (FP) by 62% can obtain by our proposed method. The result of quantitative and qualitative evaluation shows that our proposed shape retentive filtering algorithm (SRFA) can effectively filter out the false positive fragments of the initial instance contour of cervical cells from the ISBI-2014 dataset.

关键词： Measurement Shape Level set Transforms Euclidean distance Filtering algorithms Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism 7

Graph Convolutional Neural Network with Inter-layer Cascade ...

引用

7th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2021

作者： Wei, Lu Liu, Yiting Feng, Kaiyuan Li, Jianzhao Sheng, Kai Wu, Yue Xidian University Key Laboratory of Big Data and Intelligent Vision School of Computer Science and Technology Xi'an710071 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xi'an710071 China Academy of Advanced Interdisciplinary Research Xidian University Xi'an710071 China

ISBN: (纸本)9781665441490

In recent years, graph data in the non-Euclidean space has been widely used, and the methods and techniques for learning graph data in many deep learning fields have been continuously developed, such as the Graph neural network (GNN). The structural characteristics of graph data, the aggregation mode and representation mode of node information, and the node neighbor information are the core issues of GNN. However, most of the existing graph convolutional neural networks have an excessive smoothing problem, which limits the learning ability of the model. Aiming at the over-smoothing problem of the current algorithm, this paper enhances the learning of graph data by improving the expression ability of local information and global features. This paper constructs a cascade structure between graph convolutional layers. This kind of network structure realizes the dense connection of convolutional layers, makes the local feature information is effectively used, and further enhances the graph representation ability. Introduce self-attention and TopK into the Readout module, selectively aggregate and express feature information, and use graph-level information more efficiently. Graph classification is a downstream task to verify the performance of the proposed model. Experimental results prove that this densely structured graph convolutional network can effectively aggregate local node information and global graph-level information. © 2021 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Fletcher-reeves conjugate gradient for sparse reconstruction: Application to image compressed sensing

Fletcher-reeves conjugate gradient for sparse reconstruction...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Liu, Fang Wang, Hu Hao, Hongxia School of Computer Science and Technology Xidian University Xi'an 710071 China Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China Xidian University Xi'an 710071 China

ISBN: (纸本)9781424427314

GPSR-BB ( Gradient Projection for Sparse Reconstruction) algorithm is a popular CS (compressed sensing) reconstruction *** performs well for questions which have sparse *** approach is originally developed in the context of unconstrained minimization of a smooth nonlinear function F,and it uses the search direction of the Quasi-Newton method, So its shortcomings is the same as the Quasi-Newton method. For some reasons,the Hessen matrix of F can't be computed directly,it leads to a performance loss of the *** on GPSR-BB approach,a new gradient projection methods called CGSR-FR (Conjugate Gradient for Sparse Reconstruction) is proposed in this *** experiments show that CGSR-FR approache perform better than GPSR-BB approache in image compression sampling. ©2009 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Unsupervised SAR image segmentation based on quantum-inspired evolutionary gaussian mixture model

Unsupervised SAR image segmentation based on quantum-inspire...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Liu, Fang Liu, Yingying Hao, Hongxia School of Computer Science and Technology Xidian University Xi'an 710071 China Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China Xidian University Xi'an 710071 China

ISBN: (纸本)9781424427314

In this paper, an unsupervised SAR image segmentation algorithm (QEAGMM) based on quantum-inspired evolutionary Gaussian Mixture Models (GMM) is proposed. The method first divides the original image into small blocks. Then, the heterogeneous and homogeneous blocks are obtained using FCM clustering. Finally, the parameters of gaussian mixture model are trained by expectation-maximization (EM) algorithm using a part of homogeneous samples. However, the EM algorithm is apt to fall into a local optimum and the result is sensitive to initialization. So we embed the EM algorithm in quantum evolutionary algorithm (QEA) and propose a quantum-inspired-based EM algorithm (QEA-EM) to train the gaussian mixture model. This method not only improves the accuracy of parameters estimation but also performs better than immune clonal selection EM algorithm (ICSEM) on computational complexity. The experimental results show that compared to gaussian mixture model clustering algorithm (GMMC), the proposed method is successfully applied to texture mosaic images and SAR images, and shows overall improvement in performance. ©2009 IEEE.

关键词： Synthetic aperture radar

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：