检索结果-内蒙古大学图书馆

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Xu, Hao Bai, Jing North Minzu University Ningxia Yinchuan750021 China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission Ningxia Yinchuan750021 China

ISBN: (纸本)9783030930455

In this paper, we propose a novel method of reconstructing 3D shapes from single-view images based on an adversarial refiner. Generative Adversarial mechanism is adopted between the coarse-volumes generation stage and the refinement stage. In the coarse-volumes generation stage, a Context Aware Channel Attention Module (CA-CAM) and a VoxFocal Loss are designed to reconstruct the coarse-volume shapes as complete as possible. Furthermore, an adversarial refiner is proposed to adaptively optimize the coarse-volume shapes and remove redundant voxels by adding the discriminator into refiner. On the challenging large synthesis-image dataset ShapeNet and the real-world dataset Pix3D, ARShape-Net demonstrated significant quantitative and qualitative improvements compared with the state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Multi-view Moving Objects Classification via Transfer Learning

Multi-view Moving Objects Classification via Transfer Learni...

引用

第一届亚洲模式识别会议

作者： Jianyun Liu Zhaoxiang Zhang Yunhong Wang Yi Mo Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media

ISBN: (纸本)9781457701221

Moving objects classification in traffic scene videos is a hot topic in recent years. It has significant meaning to intelligent traffic system by classifying moving traffic objects into pedestrians, motor vehicles, non-motor vehicles etc.. Traditional machine learning approaches make the assumption that source scene objects and target scene objects share same distributions, which does not hold for most occasions. Under this circumstance, large amount of manual labeling for target scene data is needed, which is time and labor consuming. In this paper, we introduce TrAdaBoost, a transfer learning algorithm, to bridge the gap between source and target scene. During training procedure, TrAdaBoost makes full use of the source scene data that is most similar to the target scene data so that only small number of labeled target scene data could help improve the performance significantly. The features used for classification are Histogram of Oriented Gradient features of the appearance based instances. The experiment results show the outstanding performance of the transfer learning method comparing with traditional machine learning algorithm.

关键词： Feature extraction Training image edge detection Training data Accuracy Videos Support vector machines

来源：评论

学校读者我要写书评

暂无评论

image denoising based on nonsubsampled contourlet transform and bivariate model

引用

Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology 2009年第3期31卷 561-565页

作者： Bian, Ce Zhong, Hua Jiao, Li-Cheng Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

This paper proposes a new image denoising method based on the NonsubSampled Contourlet Transform (NSCT) and the bivariate model under the framework of Bayesian MAP estimation theory. The proposed algorithm uses the NSCT's advantages of translation-invariant and multidirection-selectivity, exploits the intra-scale and inter-scale correlations of NSCT coefficients, and elaborates the method of noise estimation. Compared with some current outstanding denoising methods, the simulation results and analysis show that the proposed algorithm obviously outperforms in both Peak Signal-to-Noise Ratio (PSNR) and visual quality, and effectively preserves detail and texture information of original images.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Real Time Object Tracking Approach for Mobile Robot Visual Servo Control

A Real Time Object Tracking Approach for Mobile Robot Visual...

引用

第一届亚洲模式识别会议

作者： Zhaoxiang Zhang Yunhong Wang Ruhan Sa Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media

ISBN: (纸本)9781457701221

A key problem of image Based Visual Servo (IBVS) System is to track objects in image sequences. Thus, the tracking algorithm plays an important role in improving the efficiency of IBVS systems. In this paper, a novel tracking algorithm called Modified CamShift Guided Particle Filter (MCAMSGPF) is proposed, which interpolated Speeded-Up Robust Features (SURF) into the framework of conventional CamShift Guided Particle Filter (CAMSGPF) tracking method. This new algorithm outperforms conventional CAMSGPF and other baseline trackers with respect to tracking robustness in the clutter background of similar colors and occlusions. We also proposed a new system model to implement and test the new algorithm in a real time moving IBVS system, which is applied in a mobile robot with an on-board camera.

关键词： Robustness image color analysis Robots Target tracking Cameras Clutter

来源：评论

学校读者我要写书评

暂无评论

View-invariant Action Recognition in Surveillance Videos

View-invariant Action Recognition in Surveillance Videos

引用

第一届亚洲模式识别会议

作者： Fang Zhang Zhaoxiang Zhang Yunhong Wang Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media

ISBN: (纸本)9781457701221

Recently, human action recognition has been a popular and important topic in computer vision. However, except some conventional problems such as noise, low resolution etc., viewinvariant recognition is one of the most challenging problems. In this paper, we focus on solve multi-view action recognition from surveillance video. To detect moving objects from complicated backgrounds, this paper employs improved Gaussian mixed model, which uses K-means clustering to initialize the model and it gets better motion detection results for surveillance videos. We demonstrate the silhouette representation ”Envelope Shape” can solve the viewpoint problem in surveillance videos. The experiment results demonstrate that our human action recognition system is fast and efficient on CASIA activity analysis database.

关键词： Videos Gaussian distribution Surveillance Shape Humans Hidden Markov models Databases

来源：评论

学校读者我要写书评

暂无评论

Research on fuzzy enhancement in the diagnosis of liver tumor from B-mode ultrasound images

Research on fuzzy enhancement in the diagnosis of liver tumo...

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Qiu, Wu Wang, Rui Xiao, Feng Ding, Mingyue School of Life Science and Technololgy Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (纸本)9780769546230

Fuzzy enhancement is applied in computer aided diagnosis of liver cancer from B mode ultrasound images as a pre-processing procedure in this paper. It was evaluated with three classifiers including K means, back propagation neural network and support vector machine using 25 features from first order statistic (FOS), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), Grey level dependant matrix (GLDM) and LAWS. In the analysis of 166 normal liver tissue, 30 hemangioma and 60 malignant tumor, our method improved the classification accuracy of three classifiers (K means, BP neural network and support machine vector) in distinguishing liver cancer, hemangioma and normal liver cancer from B mode ultrasound images. It is proved that fuzzy enhancement as an efficient preprocessing procedure could be used in the computer aided diagnosis system of liver cancer. © 2011 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

The assessment of EEG in patients with spinal cord injury to movements

The assessment of EEG in patients with spinal cord injury to...

引用

3rd International Symposium on intelligent Information Technology Application Workshops, IITAW 2009

作者： Li, Wei Huang, Yue Xu, Jiang Chen, Xi Wang, Xiaojun Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780769538600

Electroencephalography (EEG) is widely used in the field of neural engineering. EEG signals can describe the brain activities while the subjects with para/tetraplegia perform movement with their limbs. This paper reviews the research on the design of experiment, the different frequency bands of EEG signals and the data processing methods of EEG. According to the analysis of the previous studies, it has been concluded that EEG signal of alpha and beta frequency bands is of special significance for analyzing the brain activity of subjects with SCI during movements. And EEG signals also can be used for BCI with application in rehabilitation engineering. © 2009 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Memory Analysis for Memristors and Memristive Recurrent Neural Networks

引用

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 96-105页

作者： Gang Bao Yide Zhang Zhigang Zeng Key Laboratory of Cascaded Hydropower Stations Operation and Control Electrical Engineering and New EnergyChina Three Gorges UniversityYichang 443002and Hubei Key Laboratory of Applied Mathematics(Hubei University)Wuhan 430074China Department of Medical Engineering California Institute of TechnologyPasadenaCalifornia 91125 USA School of Artificial Intelligence and Automation Huazhong University of Science and Technologyand also with the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of ChinaWuhan 430074China

Traditional recurrent neural networks are composed of capacitors, inductors, resistors, and operational *** neural networks are constructed by replacing resistors with memristors. This paper focuses on the memory analysis,i.e. the initial value computation, of memristors. Firstly, we present the memory analysis for a single memristor based on memristors’ mathematical models with linear and nonlinear ***, we present the memory analysis for two memristors in series and parallel. Thirdly, we point out the difference between traditional neural networks and those that are memristive. Based on the current and voltage relationship of memristors, we use mathematical analysis and SPICE simulations to demonstrate the validity of our methods.

关键词： Dopant drift memory memristive neural networks memristor

来源：评论

学校读者我要写书评

暂无评论

Improvement and invariance analysis of Zernike moments 1

Improvement and invariance analysis of Zernike moments

引用

1st International Conference on Communications, Circuits and Systems, ICCCAS 2002

作者： Bin, Ye Xiong, Peng Jia State Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology WuhanHubei430074 China

ISBN: (纸本)0780375475

An improved Zernike moment using a region-based shape descriptor is presented. The improved Zernike moment not only has rotation invariance, but also has scale invariance that the unimproved Zernike moment does not have. The experimental results show that the improved Zernike moment has better invariant properties than the unimproved Zernike moment using a region-based shape descriptor. © 2002 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Semisupervised Transfer Boosting (SS-TrBoosting)

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3431-3444页

作者： Deng, Lingfei Zhao, Changming Du, Zhenbang Xia, Kun Wu, Dongrui Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China and also with Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen 518063 China

Semisupervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA mainly focused on learning transferable representations across domains. However, it is difficult to find a feature space where the source and target domains share the same conditional probability distribution. Additionally, there is no flexible and effective strategy extending existing unsupervised domain adaptation (UDA) approaches to SSDA settings. In order to solve the above two challenges, we propose a novel fine-tuning framework, semisupervised transfer boosting (SS-TrBoosting). Given a well-trained deep learning-based UDA or SSDA model, we use it as the initial model, generate additional base learners by boosting, and then use all of them as an ensemble. More specifically, half of the base learners are generated by supervised domain adaptation, and half by semisupervised learning. Furthermore, for more efficient data transmission and better data privacy protection, we propose a source data generation approach to extend SS-TrBoosting to semisupervised source-free domain adaptation (SS-SFDA). Extensive experiments showed that SS-TrBoosting can be applied to a variety of existing UDA, SSDA, and SFDA approaches to further improve their performance. © 2020 IEEE.

关键词： Supervised learning

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：