检索结果-内蒙古大学图书馆

Special Section Guest Editorial: Advances in Deep Learning for Hyperspectral Image Analysis and Classification

JOURNAL OF APPLIED REMOTE SENSING 2019年第2期13卷

作者： Zareappor, Masoumeh Ren, Jinchang Zhou, Huiyu Yang, Wankou Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China Univ Strathclyde Strathclyde Hyperspectral Imaging Ctr Dept Elect & Elect Engn Glasgow Lanark Scotland Univ Leicester Knowledge Discovery & Machine Learning Theme Biomed Image Proc Lab Leicester Leics England Southeast Univ Sch Automat Nanjing Jiangsu Peoples R China

This guest editorial introduces the Special Section on Advances in Deep Learning for Hyperspectral Image Analysis and Classification

关键词： Hyperspectral imaging Image analysis Image classification Image processing computer vision technology Machine learning Machine vision Pattern recognition Remote sensing Video surveillance

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Modal Pig-body Phenotype Detection Based on Hybrid Patterns 19

An Exploration of Modal Pig-body Phenotype Detection Based o...

引用

3rd International Conference on computer Science and Application Engineering (CSAE)

作者： Wang, Minjuan Zhong, Zhen Gao, Wanlin China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China

ISBN: (纸本)9781450362948

To explore the phenotypic model of human life activities and deeply analyze changes in life phenotype, phenotypic analysis of modal animals plays a great important part in the study of human life. However, automation and intelligence are still a challenge problem in practice. Due to high adaptability to the complex environments, computer vision technology can effectively improve the automation and intelligence performance in phenotypic analysis system. In this paper, to effectively apply computer vision technology in the field of phenotypic analysis, we systematically summarize the research progress of modal pig-body phenotype detection in the computer vision technology based on three kinds of pattern, namely, (1) visible pattern;(2) thermal infrared pattern;(3) depth pattern. Based on further analysis of methods, we carry out comprehensive study for exploring pig-body phenotype detection by solving multiple problems.

关键词： Phenotypic analysis Modal animal computer vision technology Visible patterns Thermal infrared patterns Depth patterns

来源：评论

学校读者我要写书评

暂无评论

Content Based Retrieval of Video Segments from Minimally Invasive Surgery Videos using Deep Convolutional Video Descriptors and Iterative Query Refinement

Content Based Retrieval of Video Segments from Minimally Inv...

引用

Conference on Medical Imaging - Image-Guided Procedures, Robotic Interventions, and Modeling

作者： Chittajallu, Deepak R. Basharat, Arslan Tunison, Paul Horvath, Samantha Wells, Katerina O. Leeds, Steven G. Fleshman, James W. Sankaranarayanan, Ganesh Enquobahrie, Andinet Kitware Inc Carrboro NC 27510 USA Baylor Univ Med Ctr Dallas TX USA

ISBN: (纸本)9781510625501

Despite a strong evidence of the clinical and economic benefits of minimally invasive surgery (MIS) for many common surgical procedures, there is a gross underutilization of MIS in many US hospitals, potentially due to its steep learning curve. Intraoperative videos captured using a camera inserted into the body during MIS procedures are emerging as an invaluable resource for MIS education, skill assessment and quality assurance. However, these videos often have a duration of several hours and there is a pressing need for automated tools to help surgeons quickly find key semantic segments of interest within MIS videos. In this paper, we present a novel integrated approach for facilitating content-based retrieval of video segments that arc semantically similar to a query video within a large collection of MIS videos. We use state-of-the-art deep 3D convolutional neural network (CNN) models pre-trained on large public video classification datasets to extract spatiotemporal features from MIS video segments and employ an iterative query refinement (IQR) strategy where in a support vector machine (SVM) classifier trained online based on relevance feedback from the user is used to refine the search results iteratively. We show that our method outperforms the state-of-the-art on the SurgicalActions160 dataset containing 160 video clips of typical surgical actions in gynecologic MIS procedures.

关键词： Video computer vision technology Content based image retrieval Laparoscopy Machine learning

来源：评论

学校读者我要写书评

暂无评论

Robust Visual Tracking via Multilayer CaffeNet Features and Improved Correlation Filtering

引用

IEEE ACCESS 2019年 7卷 174495-174506页

作者： Xiao, Yuqi Pan, Difu Cent South Univ Sch Traff & Transportat Engn Changsha 410075 Peoples R China

For problems related to the robust tracking of visual objects in various challenging tracking conditions, a robust visual tracking method based on multilayer convolutional features and correlation filtering is proposed. To solve the problems of mean deviation and insufficient discrimination ability in traditional convolutional neural networks (CNN), this study proposes randomized parametric rectified linear units (RPReLU) as the activation function. Meanwhile, the zero-setting operation of weights in the traditional dropout process occurs randomly and fails to discriminate the features with different weights, which leads to a low learning efficiency. Therefore, this study proposes an improved dropout method based on a support vector machine (SVM), which provides a selective dropout rate to increase the manual orientation and improve the learning efficiency of the dropout process. In addition, traditional CNN trackers only employ the output of the last layer, which can effectively capture semantic features but not spatial features. To solve this problem, we propose to use the rich features of the multiple convolution layers of CaffeNet as the target representation. Furthermore, we propose an improved correlation filter to further improve the tracking performance and improve the tracker's capability of dealing with scale changes, which effectively solves the problem of adaptive estimating of target size. The extensive experimental evaluations have been carried out through the OTB2015, VOT2016 and VOT2018 datasets, proving that the proposed method is very effective in dealing with a variety of challenging factors.

关键词： Convolutional neutral network correlation filter target tracking computer vision technology

来源：评论

学校读者我要写书评

暂无评论

Methods of Traffic Conflict and Definition 2018

Methods of Traffic Conflict and Definition

引用

Asia-Pacific Conference on Intelligent Medical (APCIM) / 7th International Conference on Transportation and Traffic Engineering (ICTTE)

作者： Li Lihong Yu Tongshuai Zhao Wei Henan Univ Sci & Technol Sch Vehicle & Transportat Engn Luoyang 471003 Peoples R China

ISBN: (纸本)9781450366045

Traffic conflict is an important factor affecting traffic safety. Traffic conflict technology enriched the connotation of traffic engineering. At present, the technology has become a hot research topic in the field of transportation. Conflict data collection and definition are key steps in the research process. Analysis of the current research on traffic conflicts at home and abroad, Comparing the traditional traffic conflict observation and definition methods with computer vision technology, Summarized the limitations of traditional technologies and the feasibility of computer-based visual recognition technology. In view of the shortcomings of current methods of traffic conflict data collection and definition, this paper proposes constructive suggestions for improvement.

关键词： Traffic conflict Traffic safety Transportation computer vision technology

来源：评论

学校读者我要写书评

暂无评论

Development and Challenges of Phenotypic Characterization in Modal Animals 18

Development and Challenges of Phenotypic Characterization in...

引用

2nd International Conference on computer Science and Application Engineering (CSAE)

作者： Wang, Minjuan Zhong, Zhen Gao, Wanlin China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China

ISBN: (纸本)9781450365123

In-1 recent years, science technology has developed rapidly, phenotypic analysis of modal animals plays a vital role in the study of human life and computer vision technology is an indispensable part of modal animal phenotype analysis. With the speed of computer operation has been significantly improved, some novel computer vision technologies emerged based on visible images. Due to higher adaptability of the complex environments under the visible light shine, the automation and efficiency of work has greatly promoted by computer vision technology, and it can effectively avoid the error arising from manual operation. In this paper, we mainly summarize the research progress in the image aspects of computer vision technology for the existing methods into three groups, namely, (1) image preprocessing;(2) image feature extraction;(3) image classification. Based on depth analysis of methods, we explore the image analysis method of modal animal phenotypic representation through solving different problem.

关键词： phenotypic analysis modal animal computer vision technology image preprocessing image feature extraction image classification

来源：评论

学校读者我要写书评

暂无评论

Leveraging synthetic imagery for collision-at-sea avoidance 8

Leveraging synthetic imagery for collision-at-sea avoidance

引用

Conference on Geospatial Informatics, Motion Imagery, and Network Analytics VIII

作者： Ward, Chris M. Harguess, Josh Corelli, Alexander G. Space & Naval Warfare Syst Ctr Pacific 53560 Hull St San Diego CA 92152 USA

ISBN: (数字)9781510618022

ISBN: (纸本)9781510618022

Maritime collisions involving multiple ships are considered rare, but in 2017 several United States Navy vessels were involved in fatal at-sea collisions that resulted in the death of seventeen American Servicemembers. The experimentation introduced in this paper is a direct response to these incidents. We propose a shipboard Collision-At-Sea avoidance system, based on video image processing, that will help ensure the safe stationing and navigation of maritime vessels. Our system leverages a convolutional neural network trained on synthetic maritime imagery in order to detect nearby vessels within a scene, perform heading analysis of detected vessels, and provide an alert in the presence of an inbound vessel. Additionally, we present the Navigational Hazards - Synthetic (NAVHAZ-Synthetic) dataset. This dataset, is comprised of one million annotated images of ten vessel classes observed from virtual vessel-mounted cameras, as well as a human "Topside Lookout" perspective. NAVHAZ-Synthetic includes imagery displaying varying sea-states, lighting conditions, and optical degradations such as fog, sea-spray, and salt-accumulation. We present our results on the use of synthetic imagery in a computer vision based collision-at-sea warning system with promising performance.

关键词： Cameras Data modeling Light sources and illumination Machine learning Machine vision computer vision technology Convolutional neural networks Databases Maritime surveillance Optical navigation

来源：评论

学校读者我要写书评

暂无评论

An Investigation into Strategies to Improve Optical Flow on Degraded Data 8

An Investigation into Strategies to Improve Optical Flow on ...

引用

Conference on Geospatial Informatics, Motion Imagery, and Network Analytics VIII

作者： Harguess, Josh Marez, Diego Ronquillo, Nancy Space & Naval Warfare Syst Ctr Pacific San Diego CA 92152 USA Univ Calif San Diego La Jolla CA 92093 USA

ISBN: (数字)9781510618022

ISBN: (纸本)9781510618022

Much progress has been made in recent years in almost every research area within computer vision. This has led to an increased interest in applying computer vision algorithms to real-world problems, such as robot navigation, driver-less cars, and first-person video analysis. However, in each of these real-world applications, there are still significant challenges in processing degraded data, particularly when estimating motion from a single camera, which is commonly solved using optical flow. Previous studies have shown that state-of-the-art optical flow methods fail under realistic conditions of added noise, compression artifacts, and other types of degradations. In this paper we investigate strategies to improve the robustness of optical flow to these degradations by using the degradations and data augmentations in the training and fine-tuning stages of deep learning approaches to optical flow. We test these strategies using real and simulated data and attempt to illuminate this important area of research to the community.

关键词： Optical flow Data modeling Video Motion estimation Motion models Video compression computer vision technology Machine vision

来源：评论

学校读者我要写书评

暂无评论

Drawing a baseline in Aesthetic Quality Assessment 10

Drawing a baseline in Aesthetic Quality Assessment

引用

10th International Conference on Machine vision (ICMV)

作者： Rubio, Fernando Flores, M. Julia Puerta, Jose M. UCLM I3A SIMD Lab Albacete Spain UCLM ESII Comp Syst Dept Albacete Spain

ISBN: (数字)9781510619425

ISBN: (纸本)9781510619425

Aesthetic classification of images is an inherently subjective task. There does not exist a validated collection of images/photographs labeled as having good or bad quality from experts. Nowadays, the closest approximation to that is to use databases of photos where a group of users rate each image. Hence, there is not a unique good/bad label but a rating distribution given by users voting. Due to this peculiarity, it is not possible to state the problem of binary aesthetic supervised classification in such a direct mode as other computer vision tasks. Recent literature follows an approach where researchers utilize the average rates from the users for each image, and they establish an arbitrary threshold to determine their class or label. In this way, images above the threshold are considered of good quality, while images below the threshold are seen as bad quality. This paper analyzes current literature, and it reviews those attributes able to represent an image, differentiating into three families: specific, general and deep features. Among those which have been proved more competitive, we have selected a representative subset, being our main goal to establish a clear experimental framework. Finally, once features were selected, we have used them for the full AVA dataset. We have to remark that to perform validation we report not only accuracy values, which is not that informative in this case, but also, metrics able to evaluate classification power within imbalanced datasets. We have conducted a series of experiments so that distinct well-known classifiers are learned from data. Like that, this paper provides what we could consider valuable and valid baseline results for the given problem.

关键词： computer vision technology Machine vision Data modeling Photography Visual process modeling Feature extraction Image quality Image processing Performance modeling

来源：评论

学校读者我要写书评

暂无评论

Mask Size Independent and Orientation Invariant Object Finding 28

Mask Size Independent and Orientation Invariant Object Findi...

引用

Conference on Automatic Target Recognition XXVIII

作者： Li, Bing C. Lockheed Martin 1801 State Route 17CMD0315 Owego NY 13827 USA

ISBN: (数字)9781510618084

ISBN: (纸本)9781510618084

Finding an object in images with orientation invariance has many applications in computer vision and pattern recognition. Template matching is a typical approach for finding objects. However, template matching requires pixel additions and multiplications on each pixel in a template and for each pixel in images, which involves a significant amount of pixel operations. Many techniques have been investigated to reduce the computational cost including FFT techniques, partial illumination approaches, and coarse to fine methods. These techniques may work for finding objects with the same orientation. However, when the object orientation in templates is different from the orientation in images, the computational cost is prohibitive even for the latest fast template matching techniques. In this paper, by combining the ideas of moment invariants in pattern recognition, Green theorem from physics and Bresenham line algorithm from computer graphics, we propose a mask size independent and orientation invariant object finding technique. From theoretical analysis and experiments, we demonstrate that this new technique significantly reduces computational cost for orientation free object finding from 0((NM2)-M-3) of the direct implementation to 0(N-2)

关键词： Algorithms Algorithm development Distortion Pattern recognition Visualization computer vision technology Detection and tracking algorithms Lithium Machine vision Physics

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：