检索结果-内蒙古大学图书馆

Stereo matching algorithm based on the combination of matching costs 7

Stereo matching algorithm based on the combination of matchi...

7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017

作者： Ende, Wang Yalong, Zhu Liangyu, Peng Yijun, Li Tianyao, Wu Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Opto-Electronic Information Processing CAS Shenyang110016 China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China College of Electrical Engineering Yanshan University Qinhuangdao066004 China School of Metallurgy Northeastern University Shenyang110819 China

ISBN: (纸本)9781538604892

Aiming at solving the problem of low accuracy of weak texture region and disparity discontinuous region and sensitivity to illumination caused by existing local stereo matching algorithm, a new stereo matching algorithm based on the combination of Sum of Absolute Difference algorithm and Absolute Difference of Gradient algorithm is presented here. Using the average of the pixels in the disparity range to apply adaptive weight to the SAD part. The new algorithm can adaptively adjust each part of the cost function in the proportion of the total cost function according to the different texture, illumination characteristics of image. Moreover, we use the semiglobal matching algorithm to calculate the cost of 8 directions, to carry out optimized processing on disparity image, finally a dense disparity map is obtained. The experimental results shows that the proposed method not only improve accuracy of stereo matching, but also has well results in weak texture region and disparity discontinuous region. © 2017 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Video Emotion Recognition using Hand-Crafted and Deep Learning Features

Video Emotion Recognition using Hand-Crafted and Deep Learni...

引用

Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia)

作者： Xiaohan Xia Jiamu Liu Tao Yang Dongmei Jiang Wenjing Han Hichem Sahli NPU-VUB Joint AVSP Research Lab School of Computer Science Northwestern Polytechnical University (NPU) Shaanxi Key Lab on Speech and Image Information Processing 127 Youyi Xilu Xi’an China Samsum R&D Institute China-Beijing Floor 18 Sun Palace Building 12A Sun Palace Road Chaoyang District Beijing China Interuniversity Microelectronics Centre(IMEC) Kepeldreef 75 Heverlee Belgium

ISBN: (纸本)9781538653128

In this paper, we present our system designed for the video emotion recognition task of the Multimodal Emotion Challenge (MEC 2017). Histogram of Oriented Gradients (HOG), face shape (SHAPE), and geometric (GEO) features are extracted from the detected face images as hand-crafted video features. A pre-trained VGG-Face model is fine-tuned with the face images and emotion labels from the training set of CHEAVD 2.0, the outputs of the penultimate fully-connected layer (FC6) and the last fully-connected layer (FC7) are adopted as Deep Convolutional Neural Network (DCNN) based features. For each video clip, the hand-crafted features and DCNN based features are input into corresponding hidden Markov models (HMMs, one for each emotion class), respectively, for the initial emotion recognitions. The output logarithm likelihood probabilities from the HMMs are then ranked, and the orders constitute an eight-dimensional feature vector as inputs to a Naive Bayes classifier for decision fusion. Experimental results on the CHEAVD 2.0 database show that the combination of FC6, GEO, SHAPE and HOG features obtains the highest macro average precisions (MAPs) on both the validation set (46.61%) and test set (43.88%), which are 12.51% and 22.18% higher than the baseline results, respectively.

关键词： Face Emotion recognition Shape Feature extraction Hidden Markov models Task analysis

来源：评论

学校读者我要写书评

暂无评论

Derivatives and Inverse of Cascaded Linear+Nonlinear Neural Models

arXiv

引用

arXiv 2017年

作者： Martinez-Garcia, M. Cyriac, P. Batard, T. Bertalmío, M. Malo, J. Image Processing Lab. Univ. València Spain Instituto de Neurociencias CSIC Alicante Spain Information and Communication Technologies Dept. Univ. Pompeu Fabra Barcelona Spain

In vision science, cascades of Linear+Nonlinear transforms are very successful in modeling a number of perceptual experiences [1]. However, the conventional literature is usually too focused on only describing the forward input-output transform. Instead, in this work we present the mathematics of such cascades beyond the forward transform, namely the Jacobian matrices and the inverse. The fundamental reason for this analytical treatment is that it offers useful analytical insight into the psychophysics, the physiology, and the function of the visual system. For instance, we show how the trends of the sensitivity (volume of the discrimination regions) and the adaptation of the receptive fields can be identified in the expression of the Jacobian w.r.t. the stimulus. This matrix also tells us which regions of the stimulus space are encoded more efficiently in multi-information terms. The Jacobian w.r.t. the parameters shows which aspects of the model have bigger impact in the response, and hence their relative relevance. The analytic inverse implies conditions for the response and model parameters to ensure appropriate decoding. From the experimental and applied perspective, (a) the Jacobian w.r.t. the stimulus is necessary in new experimental methods based on the synthesis of visual stimuli with interesting geometrical properties, (b) the Jacobian matrices w.r.t. the parameters are convenient to learn the model from classical experiments or alternative goal optimization, and (c) the inverse is a promising model-based alternative to blind machine-learning methods for neural decoding that do not include meaningful biological information. The theory is checked by building and testing a vision model that actually follows the modular program suggested in [1]. Our illustrative derivable and invertible model consists of a cascade of modules that account for brightness, contrast, energy masking, and wavelet masking. To stress the generality of this modular setting we show exa

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

Experimental Combined Grouping Analysis Approach for Robust Battery pack design for Electric Vehicles with Higher Performance

引用

IOP Conference Series: Earth and Environmental Science 2019年第1期268卷

作者： Liu Yun Li Shui Liang Gao Zhun Fan C. Ruhatiya Chin-Tsan Wang Akhil Garg Intelligent Manufacturing Key Laboratory of Ministry of Education Shantou University Guangdong China State Key Lab of Digital Manufacturing Equipment & Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shantou 515063 China School of Engineering Sciences Mahindra École Centrale Hyderabad Telangana 500043 India Department of Mechanical and Electro-Mechanical Engineering National I Lan University ILan Taiwan

Battery consistency is an important factor for battery pack performance. Excellent battery consistency can make battery packs more energy efficient and electric vehicles can have longer mileage and higher safety. Thus, in this study a comprehensive intelligent clustering methodology for the design of Li-ion battery pack on the basis of uniformity and equalization criteria of the cell was proposed. Firstly, multiple parameters (capacity, voltage, temperature and resistance) test of single cell performance was performed. Secondly, a clustering method combine with self-organizing map neural network (SOM) was proposed. Furthermore, a validation experiment (pack level) was carried out to verify the accuracy of proposed clustering algorithm. It can be concluded that the battery pack formed from SOM sorting results perform better than the battery pack having random cells combination as well as the pack originally purchased from the manufacturer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Construction and application of Red5 cluster based on OpenStack

引用

AIP Conference Proceedings 2017年第1期1864卷

作者： Jiaqing Wang Jianxin Song Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210000 China

With the application and development of cloud computing technology in various fields, the resource utilization rate of the data center has been improved obviously, and the system based on cloud computing platform has also improved the expansibility and stability. In the traditional way, Red5 cluster resource utilization is low and the system stability is poor. This paper uses cloud computing to efficiently calculate the resource allocation ability, and builds a Red5 server cluster based on OpenStack. Multimedia applications can be published to the Red5 cloud server cluster. The system achieves the flexible construction of computing resources, but also greatly improves the stability of the cluster and service efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge directed single image super resolution through the learning based gradient regression estimation

引用

ICIC Express Letters, Part B: Applications 2016年第2期7卷 337-344页

作者： Wang, Guogang Gan, Zongliang Zhu, Xiuchang Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications No. 66 Xinmofan Road Nanjing China

Single image super resolution (SR) aims to estimate high resolution (HR) image from the low resolution (LR) one, and estimating accuracy of HR image gradient is very important for edge directed image SR methods. In this paper, we propose a novel edge directed image SR method by learning simple priors by mapping functions. Recognizing that the training samples of the given sub-set for regression should have similar local geometric structure based on clustering, we employ high frequency of LR image patches with removing the mean value to perform such clustering. Then we learn effective mapping functions of gradient of bicubic image patches and that of HR image patches for each cluster. Experimental results suggest that the proposed method can achieve better gradient estimation of HR image and competitive SR quality compared with other SR methods. © 2016 ICIC International.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

An openstack-based flexible video transcoding framework in live

引用

AIP Conference Proceedings 2017年第1期1864卷

作者： Qisen Shi Jianxin Song Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210000 China

With the rapid development of mobile live business, transcoding HD video is often a challenge for mobile devices due to their limited processing capability and bandwidth-constrained network connection. For live service providers, it’s wasteful for resources to delay lots of transcoding server because some of them are free to work sometimes. To deal with this issue, this paper proposed an Openstack-based flexible transcoding framework to achieve real-time video adaption for mobile device and make computing resources used efficiently. To this end, we introduced a special method of video stream splitting and VMs resource scheduling based on access pressure prediction,which is forecasted by an AR model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-label inductive matrix completion for joint MGMT and IDH1 status prediction for glioma patients 1

引用

20th International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2017

作者： Chen, Lei Zhang, Han Thung, Kim-Han Liu, Luyan Lu, Junfeng Wu, Jinsong Wang, Qian Shen, Dinggang Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China Department of Radiology and BRIC University of North Carolina Chapel Hill United States School of Biomedical Engineering Med-X Research Institute Shanghai Jiao Tong University Shanghai China Department of Neurosurgery Huashan Hospital Fudan University Shanghai China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai China

ISBN: (数字)9783319661858

ISBN: (纸本)9783319661841

MGMT promoter methylation and IDH1 mutation in high-grade gliomas (HGG) have proven to be the two important molecular indicators associated with better prognosis. Traditionally, the statuses of MGMT and IDH1 are obtained via surgical biopsy, which is laborious, invasive and time-consuming. Accurate presurgical prediction of their statuses based on preoperative imaging data is of great clinical value towards better treatment plan. In this paper, we propose a novel Multi-label Inductive Matrix Completion (MIMC) model, highlighted by the online inductive learning strategy, to jointly predict both MGMT and IDH1 statuses. Our MIMC model not only uses the training subjects with possibly missing MGMT/IDH1 labels, but also leverages the unlabeled testing subjects as a supplement to the limited training dataset. More importantly, we learn inductive labels, instead of directly using transductive labels, as the prediction results for the testing subjects, to alleviate the overfitting issue in small-sample-size studies. Furthermore, we design an optimization algorithm with guaranteed convergence based on the block coordinate descent method to solve the multivariate non-smooth MIMC model. Finally, by using a precious single-center multi-modality presurgical brain imaging and genetic dataset of primary HGG, we demonstrate that our method can produce accurate prediction results, outperforming the previous widely-used single- or multi-task machine learning methods. This study shows the promise of utilizing imaging-derived brain connectome phenotypes for prognosis of HGG in a non-invasive manner. © Springer International Publishing AG 2017.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Vehicle Type Classification via Adaptive Feature Clustering for Traffic Surveillance Video

Vehicle Type Classification via Adaptive Feature Clustering ...

引用

International Conference on Wireless communications and Signal processing

作者： Shu Wang Feng Liu Zongliang Gan Ziguan Cui Jiangsu Province Key Lab on Image Processing & Image Communications Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781509028610

Vehicle type classification has become an important part of intelligent traffic. However traditional methods can not deal with the varying situations in the reality. In this paper, a novel method is proposed to handle this task in the real road traffic surveillance video. In order to distinguish different vehicles, we categorize vehicles into three types: compact cars, mid-size cars, and heavy-duty vehicles. For a certain video, our method has four steps. First, a deep convolutional neural network is used to detect vehicles in the candidate region and a data set would be generated. Second, the main features of vehicles can be extracted using a fully-connected network. Also, for the sake of higher accuracy, weak labels given by pre-trained extreme learning machine (ELM) are fused into the final features, adding prior information proportionally. Third, K-means is implemented to learn three vehicle-type cluster centers adaptively. Finally, vehicle type will be recognized according to the closest distance principal. Experimental results show that the recognition rate outperforms other traditional methods, verifying the feasibility and effectiveness of the proposed method.

关键词： Vehicle type classification Adaptive clustering Feature learning Deep learning Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

PROSTATE SEGMENTATION IN MR imageS USING ENSEMBLE DEEP CONVOLUTIONAL NEURAL NETWORKS

PROSTATE SEGMENTATION IN MR IMAGES USING ENSEMBLE DEEP CONVO...

引用

International Symposium on Biomedical Imaging

作者： Haozhe Jia Yong Xia Weidong Cai Michael Fulham David Dagan Feng Shaanxi Key Lab of Speech & Image Information Processing (SAIIP) School of Computer Science Northwestern Polytechnical University Xi'an 710072 China Biomedical and Multimedia Information Technology (BMIT) Research Group School of Information Technologies University of Sydney NSW 2006 Australia

ISBN: (纸本)9781509011735

The automated segmentation of the prostate gland from MR images is increasingly used for clinical diagnosis. Since deep learning demonstrates superior performance in computer vision applications, we propose a coarse-to-fine segmentation strategy using ensemble deep convolutional neural networks (DCNNs) to address prostate segmentation in MR images. First, we use registration-based coarse segmentation on pre-processed prostate MR images to define the potential boundary region. We then train four DCNNs as voxel-based classifiers and classify the voxel in the potential region is a prostate voxel when at least three DCNNs made that decision. Finally, we use boundary refinement to eliminate the outliers and smooth the boundary. We evaluated our approach on the MICCAIPROMIS12 challenge dataset and our experimental results verify the effectiveness of the proposed algorithms.

关键词： MR prostate segmentation deep convolutional neural network voxel classification

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：