检索结果-内蒙古大学图书馆

Two-Stage Fusion Model for Heavy Rain Removal on Single Image

Journal of Physics: Conference Series 2021年第1期2035卷

作者： Xiaomiao Pan Yueting Yang Chuansheng Yang Chao Wang Anhui Tan School of Information Engineering Zhejiang Ocean University Zhoushan Zhejiang 316022 China School of Mathematics and Statistics Beihua University Jilin Jilin 132013 P.R. China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhoushan Zhejiang 316022 China

Current single image derain methods cannot solve the heavy rain situation well. In this paper, based on the physical model of a rainy image, we build a two-stage network, TSF-Net, which combines model-driven and data-driven methods. The first stage gets the rain streaks, atmospheric light, and transmission map to obtain the coarse rain-free image by the physical model. The second stage is a fully convolutional neural network with the structure of U-Net. The proposed Multi-Scale Projection Fusion Block (MSPFB) module, which can perceive the spatial information across the scale of images, is employed to remove the residual rain and fuzzy parts in the first stage and obtain a refined clean image. Extensive experiments show that our TSF-Net achieves better accuracy and visual improvements against state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust features for leg detection in 2D laser range data

Robust features for leg detection in 2D laser range data

引用

ISPRS TC IV Mid-Term Symposium on 3D Spatial Information Science - The Engine of Change

作者： Li, Dalin Li, Lin Zhou, Mengjie Zuo, Xinkai School of Resource and Environment Sciences Wuhan University 129 Luoyu Road Wuhan430079 China Collaborative Innovation Centre of Geospatial Technology Wuhan University 129 Luoyu Road Wuhan430079 China College of Resources and Environmental Sciences Hunan Normal University Changsha410081 China Key Laboratory of Geospatial Big Data Mining and Application Hunan Province Changsha410081 China

People detection in 2D laser range data is widely used in many application, such as robotics, smart cities or regions, and intelligent driving. For most current methods on people detection based on a single laser range finder are actually leg detectors as the sensor are always established below the knee height. Current state-of-the-art methods share similar steps including segmentation, feature extraction and a machine learning-based classification, but use different features which have good performance on their own experimental data. For researchers, it is important and desirable to know which features are more robust. In this paper, taking advantage of the fact that effective features can be selected by AdaBoost and assembled into a strong classifier, a set of features presented in state-of-the-art methods is combined with a set of features presented by us to train a leg detector by the AdaBoost algorithm. This detector is assembling by effective features and can classify segments into leg and non-leg. Three open source data sets including simple and complex scenarios are used for the experiments to test the features and extracted the important ones. To reduce the effect of segmentation on the final results, three segmentation methods are simultaneously used for experiments and analysis to ensure the reliability and credibility of our conclusion. Finally, 10 robust features for leg detection in 2D laser range data are presented based on the results. © Authors 2018.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Enhanced Rain Image Restoration Network

引用

Journal of Physics: Conference Series 2021年第1期2035卷

作者： Quanqing Wang Yuanshun Cheng Yueting Yang Chao Wang Chuansheng Yang School of Information Engineering Zhejiang Ocean University Zhoushan Zhejiang 316022 China Tianfu College of SWUFE Mianyang Sichuan 621000 China School of Mathematics and Statistics Beihua University Jilin Jilin 132013 P.R. China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhoushan Zhejiang 316022 China

The restoration task of rain images is beneficial to the further development of computer vision tasks. However, recent rain removal methods have difficulty coping with dense rain streaks. In this paper, we propose a Multi-stage Enhanced Rain Image Restoration Network (MERNet) for the task of rain removal. Our main idea is to design a three-stage network architecture, which makes full use of the enhanced information of the previous stage and complements the information of the next stage through transmission step by step. We give consideration to information enhancement at the same time of information transmission, fully improve the information utilization rate and the overall network effect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention-based Feature Enhanced Dehazing Network

引用

Journal of Physics: Conference Series 2021年第1期2035卷

作者： Yuanshun Cheng Anhui Tan Chuansheng Yang Yueting Yang Chao Wang Tianfu College of SWUFE Mianyang Sichuan 621000 China School of Information Engineering Zhejiang Ocean University Zhoushan Zhejiang 316022 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhoushan Zhejiang 316022 China School of Mathematics and Statistics Beihua University Jilin Jilin 132013 P.R. China

Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing algorithm should enhance the feature information of the background while weakening the feature information of haze. In this paper, we propose an end-to-end attention-based feature enhanced dehazing network (AEDNet), which integrates enhancement strategy and attention mechanism, to achieve haze removal. The network is based on U-Net, which has the advantages of retaining information, obtaining multi-scale features and so on. In the training of the network, pixel loss and perceptual loss are used to preserve feature information and improve the overall quality of results. The extensive evaluation shows that the proposed model performs significantly better than previous dehazing methods on various benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incremental multivariate Markov chain model

Incremental multivariate Markov chain model

引用

作者： Yang, Chuan-Sheng Zheng, Yu-Jia Wang, Chao School of Mathematics Physics and Information Science Zhejiang Ocean University Zhoushan Zhejiang316000 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Ocean University Zhoushan Zhejiang316022 China

In this study, the authors present an incremental multivariate Markov (IMM) chain model. Moreover, the estimation method of the parameters in IMM is proposed. Numerical experiments illustrate the effectiveness of IMM.... 详细信息

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Control and Stabilization of High-Order KdV Equation Posed on the Periodic Domain

引用

Journal of Partial Differential Equations 2018年第1期31卷 29-46页

作者： ZHAO Xiangqing BAI Meng Department of Mathematics Zhejiang Ocean University Zhoushan 316000 China. Key Laboratory of Oceanographic Big Data Mining-& Application of Zhejiang Province Zhoushan 316000 China. School of Mathematics and Statistics Sciences Zhaoqing UniversityZhaoqing 526061 China.

In this paper, we study exact controllability and feedback stabilization forthe distributed parameter control system described by high-order KdV equation posedon a periodic domain T with an internal control acting on an arbitrary small nonemptysubdomain w of T. On one hand, we show that the distributed parameter controlsystem is locally exactly controllable with the help of Bourgain smoothing effect; onthe other hand, we prove that the feedback system is locally exponentially stable withan arbitrarily large decay rate when Slemrod＇s feedback input is chosen.

关键词： High-order KdV equation Bourgain smoothing property exact controllability Slem-rod＇s feedback law exponential stabilizability.

来源：评论

学校读者我要写书评

暂无评论

Ship Detection Using the Surface Scattering Similarity and Scattering Power

Ship Detection Using the Surface Scattering Similarity and S...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Tao Zhang Zhen Y ang Bo Mao Jian Y ang Yifang Ban Huilin Xiong Shanghai Key Lab. of Intelligent Sensing and Recognition Shanghai Jiao Tong University Shanghai China Jiangxi Science and Technology Normal University Nanchang China Jiangsu Key Laboratory of Grain Big Data Mining and Application Nanjing University of Finance & Economics Nanjing China Department of Electronic Engineering Tsinghua University Beijing China Division of Geoinformatics KTH Royal Institute of Technology Stockholm Sweden

Sea surface and ship have different backscattering mechanisms, in which surface scattering is predominant for sea surface in the low sea state case. Based on this fact, many ship detectors have been developed by suppressing the surface scattering resulted from sea surface. Actually, small ship may also have strong surface scattering sometimes. In such a case, the methods of avoiding using surface scattering features may easily miss the detection of small ships. To verify this point, in this paper, we first analyze the shortcomings of An's method which is based on surface scattering similarity and the power maximization synthesis detector (PMS), and then improve it for detecting small ships more effectively. In order to demonstrate the performance of the proposed method, AIRSAR L-Band Polarimetric SAR dataset is exploited. Comparing to other methods, the new method shows a better ship detection performance.

关键词： Marine vehicles Scattering Sea surface Covariance matrices Detectors Synthetic aperture radar Backscatter

来源：评论

学校读者我要写书评

暂无评论

Investigation on Influence of Reflectivity of the Film on Interference Fringes and its Optimization with Theoretical Analysis

Investigation on Influence of Reflectivity of the Film on In...

引用

2018 2nd International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2018)

作者： Sheng-wen QI Xue-ping CHENG Peng LI Xiao-ping Qin Qing-wei WANG Hong-guang LU School of Mathematics Physics and Information ScienceZhejiang Ocean University Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Affiliated Hospital Guiyang Medical University

In view of the problem that the low visibility of interference fringes of interferometer affects the accuracy of measurement,the intensity distribution of the interference of thin film is investigated with theoretical *** influences of the reflectivity of the film on the intensity distribution and the visibility of the fringes are discussed and the relation between the reflectivity and the visibility is *** results show that the optimal numerical range of the reflectivity with high clarity of the fringe is in the vicinity of 0.5.

关键词： Interference Fringe visibility Measurement

来源：评论

学校读者我要写书评

暂无评论

Leaf area index estimation of winter pepper based on canopy spectral data and simulated bands of satellite 4th

Leaf area index estimation of winter pepper based on canopy ...

引用

4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016

作者： Li, Dan Jiang, Hao Chen, Shuisen Wang, Chongyang Huang, Siyu Liu, Wei Guangdong Open Laboratory of Geospatial Information Technology and Application Guangdong Key Laboratory of Remote Sensing & GIS Application & Engineer Technology Research Center for Remote Sensing Big Data Application of Guangdong Province Guangzhou Institute of Geography Guangzhou510070 China

ISBN: (纸本)9789811039652

Leaf area index (LAI) is an important indicator of crop growth status. In this paper, the relationships between canopy reflectance at 400–2500 nm and leaf area index (LAI) in pepper crop were studied. 102 pair of canopy reflectance and LAI of pepper were collected in 2014–2015. Reflectance of canopy were measured in the field over a spectral range of 400–2500 nm. Simultaneously, the LAI were collected by the LAI-2000. Estimation models of LAI were developed based on the whole spectrum range by partial least squares regression (PLSR) and support vector regression (SVR), respectively. Then the field canopy spectra were resampled according to the band response functions of seven satellite sensors. They were the Vegetation and environment monitoring on a new micro-satellite (VENlS), Worldview-2 (WV-2), RapidEye-1 (RE-1), HJ1/CCD1, Sentinel-2, Landsat 8/OLI and GaoFen (GF) 1/WFV1. The values of common used spectral indices were calculated based on the simulated sensor bands, respectively. Prediction models were also developed based on the spectral indices and simulated bands. The results showed that the PLSR model by whole spectrum had the good accuracy of LAI estimation with the R2c = 0.726, RMSEc = 0.462, R2cv = 0.635, RMSEcv = 0.538. For the simulated satellite datasets, the better LAI estimation were obtained by Sentinel-2 and Venls bands with the R2cv greater than 0.600 and RMSEcv less than 0.557. The Estimation model by simulated WV-2 bands, and RE-1 bands had the lowest performance with the R2cv between 0.50 and 0.55, and RMSEcv between 0.600 and 0.623. The inversion results demonstrated the potential of the multispectral remote sensing data to calibrate the LAI estimation model of winter pepper for the precision agriculture application. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

How it outsourcing impacts on value creation of manufacturer? 2

How it outsourcing impacts on value creation of manufacturer...

引用

2nd International Conference on Precision Machinery and Manufacturing Technology, ICPMMT 2017

作者： Chen, Li-Shan Tseng, Yen-Ming School of Management Fujian University of Technology China Key Laboratory of Big Data Mining and Application School of Information Science and Engineering Fujian University of Technology China

A growing concern among the manufacturers who are actively involved in Information Technology outsourcing is post-contract management and the ensuing development of what many practitioners have coined the 'outsourcing partnership'. Over the past few decades, information technology outsourcing has become a widely used and researched means for manufacturers to enhance their performance. Increasing attention has been paid to building successful partnerships in information systems outsourcing. This study employs strategic social positioning, customer participation, customer orientation, and communication culture to develop research model. The quantitative method will be used to validate the research model and test hypotheses developed. This study uses survey method to collect data, and analysis of the reliability, validity and test the proposed hypotheses by Smart Partial Least Squares. The purpose of this study is to use above four factors to produce value co-creation between outsourcing vendors and manufacturers. The final aim is for the future collaboration. This combination will allow manufacturers and information technology outsourcing vendors to increase their value co-creations in the fields of these factors. © 2017 The Authors, published by EDP Sciences.

关键词： Outsourcing

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：