检索结果-内蒙古大学图书馆

11th International Conference on Simulated Evolution and Learning, SEAL 2017

作者： Zou, Xumiao Liu, Jing Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi’an710071 China

ISBN: (纸本)9783319687582

Fuzzy cognitive maps (FCMs) are inference networks, which are the combination of fuzzy logic and neural networks. Various evolutionary-based learning algorithms have been proposed to learn FCMs. However, evolutionary algorithms have shortcomings, such as easy to become premature and the local search ability is weak where the search may trap into local optima. Decision-making trial and evaluation laboratory (DEMATEL) has been widely accepted as one of the best tools to analyze the causal and effect relationships between concepts. Therefore, we combine real-coded genetic algorithm (RCGA) with DEMATEL method, termed as RCGADEMATEL-FCM, to learn FCM models. In RCGADEMATEL-FCM, the DEMATEL method is used as a directed neighborhood search operator to steer the search to the right direction in the objective space, which can overcome the premature problem and make the search jump out of the local optimum. Experimental results on both synthetic and real life data demonstrate the efficiency of the proposed algorithm. The comparison with existing learning algorithms shows that RCGADEMATEL-FCM can learn FCMs with higher accuracy without expert knowledge. © Springer International Publishing AG 2017.

关键词： Fuzzy Cognitive Maps

来源：评论

学校读者我要写书评

暂无评论

Human detection based on second generation bandelet transform

Human detection based on second generation bandelet transfor...

引用

1st International Conference on Information Science and Engineering, ICISE2009

作者： Han, Hong Wu, Xing Jiao, Licheng Yue, Lichuan Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an 710071 China

ISBN: (纸本)9780769538877

Base on geometric flow of images and the second generation bandelet transform, a new feature extraction method was proposed, and it was used to detect human in still images. In the paper, bandelet coefficients and their statistical values were extracted as the feature of human images, combined with Adaboost classifier to classify and detect human in images. In the proposed algorithm, some general statistical values of the bandelet coefficients were computed to enhance the classification capacity. The results of human detection experiments indicate that the proposed method can describe human characteristics and improve the performance of classifier effectively. It is very suitable for human detection in still images. ©2009 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Blocking artifact reduction in DIBR using an overcomplete 3D dictionary

Blocking artifact reduction in DIBR using an overcomplete 3D...

引用

19th International Conference on Advances in Multimedia Modeling, MMM 2013

作者： Jung, Cheolkon Jiao, Licheng Qi, Hongtao Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an 710071 China

ISBN: (纸本)9783642357244

It has been reported that the image quality and depth perception rates are undesirably decreased by compression in DIBR. This is because highfrequency components are filtered by compression, and thus several compression artifacts occur. Blocking artifacts are the most representative ones which seriously degrade the picture quality, and are annoying to viewers. The fundamental cause of the coding artifacts is that the 3D contents are delivered to users over the existing 2D broadcast infrastructures which employ BDCT coding as image compression techniques. In this paper, we propose a new deblocking method in 3D images, i.e., video-plus-depth, using an overcomplete 3D dictionary. We generate the 3D dictionary from natural and depth images using the k-singular value decomposition (K-SVD) algorithm, and estimate an error threshold to utilize the 3D dictionary using a compression factor of the compressed images. Experimental results demonstrate that the proposed method is very effective in reducing undesirable blocking artifacts in 3D images. © Springer-Verlag 2013.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Unsupervised image segmentation based on watershed and kernel evolutionary clustering algorithm 11th

Unsupervised image segmentation based on watershed and kerne...

引用

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Lei, Chao Ma, Jingjing Jiang, Xiangming Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi’an710071 China

ISBN: (纸本)9789811036132

In this study, a novel image segmentation algorithm based on watershed and kernel evolutionary clustering algorithm (WKECA) is proposed. An improved watershed algorithm, marker driven watershed transform, is used to segment image into many small regions and the image features of every region are extracted. By using kernel functions, the image features in the original space are mapped to a high-dimensional feature space, in which we can perform clustering efficiently on the unsupervised segmentation task. The proposed algorithm can be used to cope with different types of images, such as natural image, texture image and remote sensing image. The experimental results show that WKECA is competent for segmenting most of the testing images with high quality. © Springer Nature Singapore Pte Ltd. 2016.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised sparse dimensionality reduction for hyperspectral image classification

Semi-supervised sparse dimensionality reduction for hyperspe...

引用

2016 IEEE Region 10 Conference, TENCON 2016

作者： Zhang, Xiangrong Huyan, Ning Zhou, Nan An, Jinliang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an710071 China

ISBN: (纸本)9781509025961

In this paper, a semi-supervised dimensionality reduction method based on sparse representation is proposed. The s-parse representation has the ability to distinguish samples, exactly, the sparse coefficient in sparse representation will be large when the represented samples and the entries of the dictionary are in the same class, but it will be small if they are not. So we use the sparse coefficient to construct our l1-graph in which the connection weight is defined as the contribution of each entries in the dictionary when construct this sample. Considering the goal that reduce the dimension of each pixel and preserve the discriminative information as much as possible we propose an regularization term incorporating the structures reflected by l1-graph. Although labeled samples are always insufficient in HSI processing, we make full use of them with abundant unlabeled samples to improve the performance after dimensionality reduction. So we then introduce LDA method and extend it as a semi-supervised method. Finally we evaluate our method in practical classification work and experimental results on real hyperspectral image show that the proposed method can achieve better and more stable results. © 2016 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Edge detection approach based on directionlet transform

Edge detection approach based on directionlet transform

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Bai, Jing Zhou, Huaji Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi'an China

ISBN: (纸本)9781612847740

Due to possessing the multi-direction anisotropic basis functions, directionlet transform can capture the inherent geometrical feature of the image. A directionlet transform -based edge detection approach is proposed in this paper. In the approach, we filter along any two directions with two slopes to capture abundant edge information. In addition, we use the multiscale characteristics of directionlet transform. Combine the advantage of small and large scales to get the desirable edge. The experiments indicate that the proposed approach outperforms wavelet and any other traditional approaches. © 2011 IEEE.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

IMPROVED SIAMRPN++ WITH CLUSTERING-BASED FRAME DIFFERENCING FOR OBJECT TRACKING OF REMOTE SENSING VIDEOS

IMPROVED SIAMRPN++ WITH CLUSTERING-BASED FRAME DIFFERENCING ...

引用

2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

作者： Feng, Jie Hui, Bingyu Liang, Yuping Yao, Quanhe Zhang, Xiangrong Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an710071 China

ISBN: (纸本)9781665403696

Deep learning (DL) based object tracking methods have achieved encouraging results on natural videos. However, directly applying these DL-based methods to the vehicle tracking of optical remote sensing videos (ORSV) still faces many challenges. Different with the vehicles in nature videos, most vehicles in ORSV are blurry, small in size, and highly similar to other vehicles. Furthermore, blurred vehicles easily blend into the background and are difficult to distinguish. To solve these problems, an improved Siamrpn++ with clustering-based frame differencing (CFD-SiamRPN++) is proposed. In CFD-SiamRPN++, a clustering method is used to divide the differencing map among adjacent frames into two clusters. By using the statistics of the clustering results, each cluster is judged to the target or not. According to the judgment of each cluster, the differencing map is refined by reducing the background noises and retaining moving information of vehicles. Then, the refined differencing map is fused with the original frame as the input of the tracking network to enhance the discriminative ability of small-sized and blurred vehicles. In the tracking phase, SiamRPN++ is selected as the tracking network due to its feature extraction capability with multi-scale feature fusion and efficient tracking performance. Experiment results based on Jilin-1 ORSV dataset show that the proposed method provides a competitive tracking performance over state-of art deep learning methods. © 2021 IEEE

关键词： Deep learning Target tracking Clustering methods Feature extraction Optical sensors Object tracking Background noise

来源：评论

学校读者我要写书评

暂无评论

Evolutionary game network reconstruction by memetic algorithm with l 1/2 regularization 11th

Evolutionary game network reconstruction by memetic algorith...

引用

11th International Conference on Simulated Evolution and Learning, SEAL 2017

作者： Wu, Kai Liu, Jing Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi’an710071 China

ISBN: (纸本)9783319687582

Evolutionary Game (EG) theory is effective approach to understand and analyze the widespread cooperative behaviors among individuals. Reconstructing EG networks is fundamental to understand and control its collective dynamics. Most existing approaches extend this problem to the l 1-regularization optimization problem, leading to suboptimal solutions. In this paper, a memetic algorithm (MA) is proposed to address this network reconstruction problem with l 1/2 regularization. The problem-specific initialization operator and local search operator are integrated into MA to accelerate the convergence. We apply the method to evolutionary games taking place in synthetic and real networks, finding that our approach has competitive performance to eight state-of-the-art methods in terms of effectiveness and efficiency. © Springer International Publishing AG 2017.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network-Based Electromagnetic Signal Classification: A Semi- Supervised Learning Framework

引用

China Communications 2020年第10期17卷 157-169页

作者： Huaji Zhou Licheng Jiao Shilian Zheng Lifeng Yang Weiguo Shen Xiaoniu Yang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial IntelligenceXidian UniversityXi'an 710071China Science and Technology on Communication Information Security Control Laboratory Jiaxing 314033China

Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic *** this paper,we introduce GAN into the field of electromagnetic signal classification(ESC).ESC plays an important role in both military and civilian ***,in many specific scenarios,we can’t obtain enough labeled data,which cause failure of deep learning methods because they are easy to fall into ***,semi-supervised learning(SSL)can leverage the large amount of unlabeled data to enhance the classification performance of classifiers,especially in scenarios with limited amount of labeled *** present an SSL framework by incorporating GAN,which can directly process the raw in-phase and quadrature(IQ)signal *** to the characteristics of the electromagnetic signal,we propose a weighted loss function,leading to an effective classifier to realize the end-to-end classification of the electromagnetic *** validate the proposed method on both public RML2016.04c dataset and real-world Aircraft Communications Addressing and Reporting System(ACARS)signal *** experimental results show that the proposed framework obtains a significant increase in classification accuracy compared with the state-of-the-art studies.

关键词： generative adversarial network semi-supervised learning electromagnetic signal classification end-to-end classification weighted loss function

来源：评论

学校读者我要写书评

暂无评论

Tracking Multi-objects with Anchor-Free Siamese Network 5th

Tracking Multi-objects with Anchor-Free Siamese Network

引用

5th IFIP TC 12 International Conference on Intelligence Science, ICIS 2022

作者： Hui, Bingyu Feng, Jie Yao, Quanhe Gu, Jing Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi’an710071 China

ISBN: (纸本)9783031149023

Single object tracker based on siamese neural network have become one of the most popular frameworks in this field for its strong discrimination ability and high efficiency. However, when the task switch to multi-object tracking, the development of siamese-network based tracking methods is limited by the huge calculation cost comes from repeatedly feature extract and excessive predefined anchors. To solve these problems, we propose a siamese box adaptive multi-object tracking (SiamBAN-MOT) method with parallel detector and siamese tracker branch, which implementation in an anchor-free manner. Firstly, ResNet-50 is constructed to extract shared features of the current frame. Then, we design a siamese specific feature pyramid networks (S-FPN) to fuse the multi-scale features, which improves detection and tracking performance with the anchor-free architecture. To alleviate the duplicate feature extraction, RoI align is operated to extract all trajectories’ template feature and search region feature in a single feature map at once. After that, anchor-free based Siamese tracking network outputs the tracking result of each trajectory according to its template and search region feature. Meanwhile, current frame’s detection results are obtained from the detector for the target association. Finally, a simple novel IOU-matching scheme is designed to map the tracking results to the detection results so as to refine the tracking results and suppress the drifts caused by siamese tracking network. Through experimental verification, our method achieves competitive results on MOT17. © 2022, IFIP International Federation for Information Processing.

关键词： Feature extraction

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：