检索结果-内蒙古大学图书馆

SAR image classification based on correlation of directional features in frequency domain

SAR image classification based on correlation of directional...

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhong, Hua Yang, Xiaoming Jiao, Licheng Institution of Intelligent Information Processing Key Laboratory of Intelligent Perception and Image Understanding Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478078

A new SAR image classification method is proposed based on the remarkable correlation of feature channels, which are obtained by dividing the Fourier plane into sectors according to the frequency and direction. Compared with other feature correlation based methods in wavelet and Contourlet domain, our method operates directly in the Fourier plane, which is more robust with regard to images size and more flexible in the capture of frequency and directional information. Moreover, the use of FFT transform is computationally more attractive. Experimental results on the Brodatz textures and SAR images demonstrate the effectiveness and efficiency of the proposed method. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Low-complexity bandelet for SAR image compression

Low-complexity bandelet for SAR image compression

引用

MIPPR 2009 - Multispectral image Acquisition and processing: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Yang, Shuyuan Wang, Zhaoxia Qi, Weidong Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478054

Synthetic aperture radar (SAR) images compression is very important in reducing the burden of data storage and transmission. Finding efficient geometric representations of images is a central issue in improving the efficiency of image compression. Bandelet provides an efficient way for image representation based on geometric regularity. In the second generation Bandelet, the multiscale decomposition of image is completed by 2D wavelet transform (WT) and the obtained subbands images are squared partitioned. Then a bottom to top CART algorithm is used to prune the quadtree, and finally an exhaustive searching algorithm is used to obtain the optimal direction in each square. This process is of high complexity in time and space though it can provide an efficient representation of images than WT. Considering this, we proposed a rapid implementation of Bandelet transform based on fixed size image partition, and then applied it to SAR image compression. Experiments results show that in relative to the second generation Bandelets, our proposed method has rapid implementation and comparable performance with chinalake and abq-apt in 0.5-2.0bpp. An improvement of PSNR(Peak Signal to Noise Ratio) and the preservation of edges and texture over JPEG2000 are obtained. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Demand-Side Frequency control in Power Network Based on Multi-Agent Deep Reinforcement Learning 5

Demand-Side Frequency Control in Power Network Based on Mult...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Liu, Xianggang Liu, Zhi-Wei Chi, Ming Zhang, Yifan Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education College of Artificial Intelligence and Automation Wuhan China

ISBN: (纸本)9798350325294

The integration of renewable energy sources into the power grid has led to new challenges in maintaining the stability of the system frequency. This paper proposes a novel approach to address the Optimal Demand Side Frequency control (ODFC) problem using Multi-Agent Deep Deterministic Policy Gradient (MADDPG) method. The proposed method models the ODFC problem as a Markov game, with centralized training based on multi-agent cooperative self-learning and associative storage service. In the decentralized execution stage, each agent independently outputs control actions to the controlled plant using local observations. Numerical simulations show that the proposed method effectively addresses the ODFC problem with superior performance compared to traditional methods. © 2023 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEEP NEURAL NETWORKS 8

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEE...

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Zhang, Xiao Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Graph-based scale-aware network for human parsing 1

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Yang, Beibei Yu, Changqian Liu, Jiahui Gao, Changxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Recent work has made considerable progress in exploring contextual information for human parsing with the Fully Convolutional Network framework. However, there still exist two challenges: (1) inherent relative relationships between parts;(2) scale variation of human parts. To tackle both problems, we propose a Graph-Based Scale-Aware Network for human parsing. First, we embed a Graph-Based Part Reasoning Layer into the backbone network to reason the relative relationship between human parts. Then we construct a Scale-Aware Context Embedding Layer, which consists of two branches to capture scale-specific contextual information, with different receptive fields and scale-specific supervisions. In addition, we adopt an edge supervision to further improve the performance. Extensive experimental evaluations demonstrate that the proposed model performs favorably against the state-of-the-art human parsing methods. More specifically, our algorithm achieves 53.32% (mIoU) on the LIP dataset. © Springer Nature Switzerland AG 2019.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Active learning for transferrable object classification in cross-view traffic scene surveillance

Active learning for transferrable object classification in c...

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Zhang, Zhaoxiang Tang, Jun Zhao, Yuhang Wang, Yunhong Liu, Jianyun Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9783642347771

We discuss the problem of object classification in cross-view traffic scene surveillance videos in this paper. To classify moving objects in traffic scene videos into pedestrian, bicycle and variety of vehicles, an effective intelligent classification framework has been proposed which takes advantage of a transfer machine learning method to bridge the gap between source scene data and target scene data. The transfer learning algorithm makes one classifier adaptive to perspective changes instead of training two different classifiers for corresponding perspectives. The samples transferred from source scene database have saved much manual labeling work on target scene database. In this paper, we propose an active transfer learning method to decrease manual labeling work further for target scene traffic object classification. Redundant experiments are conducted and experimental results demonstrate the effectiveness and convenience of our approach. © 2012 Springer-Verlag.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

image denoising with non-local means in the shearlet domain

Image denoising with non-local means in the shearlet domain

引用

International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping

作者： Zhang, Xiaohua Zhang, Qiang Jiao, L.C. Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424494040

In this paper, a novel method for image denoising is proposed which adopts multiscale geometry tool. Firstly the image is decomposed by discrete shearlet transform. The shearlet coefficients of each direction approach the generalized Gaussian distribution. We use the principal component analysis (PCA) for every similarity window of shearlet coefficients. Then we use Generalized Gaussian model of non-local means method to handle the shearlet coefficients. Finally, we reconstruct image with the new shearlet coefficients to obtain the result. Numerical results show that our algorithm competes favorably with nonlocal means algorithms in the case of high noise. ©2011 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Recent Patents Review in Three Dimensional Ultrasound Imaging

引用

Recent Patents on Biomedical Engineering 2011年第1期4卷 41-48页

作者： Chen, Yimin Li, He Zheng, Yaowu Yuchi, Ming Zhang, Xuming Ding, Mingyue College of Life Science and Technology Image Processing and Intelligence Control Key Laboratory of EducationMinistry of China Huazhong University of Science and Technology Wuhan 430074 China

Ultrasound is an inexpensive and widely used imaging modality for the diagnosis and staging of many *** the past several decades, it has benefited from major advances in technology and has become an indispensable imaging modality, due to its flexibility and non-invasive character. In the last decade, research investigators and commercial companieshave further advanced ultrasound imaging with the development of 3D ultrasound. Compared with two dimensional ultrasound imaging, it can provide a 3D image of the anatomy directly and localize the image plane much easier. This review focuses on three dimensional ultrasonic medical imaging patents filed in recent years between 2006 and 2010. The patents are classified into three classes: the hardware, software and applications. This paper will attempt to provide an appreciation of the recent advances in 3D ultrasound imaging research while glimpse the future development trend of 3D ultrasound imaging. © 2011 Bentham Science Publishers Ltd.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Bimodal Feature Propagation and Fusion for Real-time Semantic Segmentation on RGB-D images 7

Bimodal Feature Propagation and Fusion for Real-time Semanti...

引用

7th International Conference on intelligent Computing and Signal processing, ICSP 2022

作者： He, Ying Xiao, Li Sun, Zhigang Wang, Zhuo Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Wuhan China

ISBN: (纸本)9781665478571

Semantic Segmentation is the foundation of scene understanding and automatic driving tasks. One of the challenges of semantic segmentation is the reduction of feature resolution as the network goes deep. In this paper, the low-resolution features are integrated into high-resolution features progressively, enabling high-resolution prediction. Currently, incorporating the auxiliary depth information into a semantic segmentation framework has proven to be helpful to improve accuracy. However, additional process of depth data immensely increases computational complexity, resulting in limitation for practical application. Here, a real-time bimodal semantic segmentation network that effectively extracts and fuses complementary information is investigated. Our network extends a light-weight architecture which can seamlessly take advantage of various prevalent backbone networks. Our model extracts RGB and depth features from two branches in parallel and integrates multi-level features of two modalities through bimodal feature fusion blocks. To reduce computation complexity, we employ depth-wise separable convolution while keep performance intact. Meanwhile, an attention mechanism is exploited to recalibrate the fusion modality features adaptively. Refinement components are retained to refine multi-resolution feature maps. We conduct ablative study to demonstrate the availability of our bimodal fusion blocks. Comprehensive experiments validate that the proposed network outperforms the state-of-the-arts and achieves 18 FPS on the challenging RGB-D dataset, NYUDv2. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A hybrid local feature for face recognition

A hybrid local feature for face recognition

引用

12th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2012

作者： Gou, Gaopeng Huang, Di Wang, Yunhong Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9783642326943

Efficient face encoding is an important issue in the area of face recognition. Compared to holistic features, local features have received increasing attention due to their good robustness to pose and illumination changes. In this paper, based on the histogram-based interest points and the speeded up robust features, we propose a hybrid local face feature, which provides a proper balance between the computational speed and discriminative power. Experiments on three databases demonstrate the effectiveness of the proposed method as well as its robustness to the main challenges of face recognition and even in practical environment. © 2012 Springer-Verlag.

关键词： Face recognition

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：