检索结果-内蒙古大学图书馆

Representation of freshwater aquaculture fish behavior in low dissolved oxygen condition based on 3D computer vision

引用

MODERN PHYSICS LETTERS B 2018年第34-36期32卷

作者： Bao, Y. J. Ji, C. Y. Zhang, B. Gu, J. L. Changzhou Inst Technol Sch Elect & Photoelect Engn Changzhou 213032 Peoples R China Nanjing Agr Univ Coll Engn Nanjing 210031 Jiangsu Peoples R China

Dissolved oxygen (DO) plays an important role in industrialized freshwater aquaculture. Such deficiencies such as the high cost of water-quality monitoring system and the failure to accurately monitor or describe aquaculture water-quality existed in freshwater aquaculture water-quality monitoring system. Here, a kind of representation method applied to characterize industrialized aquaculture fish behavior in different degrees of DO deficiency is based on three-dimensional (3D) computer vision. 3D coordinate values of aquaculture fishes in water acquired from 3D computer vision Device by processing aquaculture fish image are applied to represent such parameters as the average activity and height of aquaculture fish in water. This method for representing different behaviors of industrialized freshwater aquaculture fish under the condition of anoxia is realized by using these parameters and combing with the experience of aquaculture. The results show that the representation of industrialized freshwater aquaculture fish based on 3D computer vision System can be applied to describe industrialized aquaculture fish behavior and effectively compensate for the shortfall spatial location of aquaculture fish unable to acquire from 2D monitoring system, which is helpful for the accurate and reasonable control of DO in aquaculture.

关键词： Fish behavior dissolved oxygen three-dimensional vision system

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Sequence Based Human Activity Detection System

A Real-Time Sequence Based Human Activity Detection System

引用

2023 international Multi-Disciplinary conference in Emerging Research Trends, IMCERT 2023

作者： Iqrar, Waqas Shahzad, Aamir Hameed, Waqas Abidien, Malik Zainxul COMSATS University Department of Electrical and Computer Engineering Abbottabad Campus Islamabad Abbottabad Pakistan

ISBN: (纸本)9798350347708

During the last decade, human activity detection is increasingly attracting the attention of researchers, due to its numerous applications, such as in smart and automated shopping malls, hospitals, etc. Particularly, detecting human activity has been a challenge for researchers because complex situations may arise such as background clutter or changing illumination. To solve this issue, video segment classification cannot be tackled just as object identification. Therefore, it becomes inevitable to employ sequence-based techniques for video classification. In this paper, a Convolution Neural Network (CNN) is used in conjunction with Long Short-Term Memory (LSTM) to accomplish real-Time human activity detection. In the proposed method, CNN serves as a spatial information detection algorithm from video while LSTM helps in the sequential tracking of identified objects quickly and accurately. This CNN-LSTM approach reduces the complexity of the model while also enhancing its accuracy along with enabling its real-Time execution. Finally, a Raspberry Pi that functions as a standalone system is utilized for the implementation of the proposed CNN-LSTM approach. The results are presented and analyzed to solidify that the proposed standalone system can detect and classify events for real-Time surveillance. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

2D Face Recognition on CNN with Half-Average-Face

2D Face Recognition on CNN with Half-Average-Face

引用

2018 3rd international conference on Communication,image and Signal processing（CCISP 2018）

作者： Yangfeng Zheng School of Data and Computer Science SUN YAT-SEN UNIVERSITY

As the size of training dataset of face recognition models becomes larger and larger, we are interested in a method called Average-Half-Face（AHF）, which could halve the size of training samples. The AHF method divides a full face into two halves and then averages them together（reversing the columns of one of the halves）. We preprocess the dataset with the method of AHF, and train them on two different models, Eigenfaces and Convolutional Neural Network（CNN）. We compare the prediction results with those models trained on the original dataset. Previous researches showed that AHF is superior to Full-Face（FF）, while our experiment results further showed that in some cases AHF also boosts CNN. The application of AHF can bring both saving in storage and reduction on training cost time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Framework for Automatic Building Detection from Low-Contrast VHR Satellite imagery 19

A Framework for Automatic Building Detection from Low-Contra...

引用

Proceedings of the 3rd international conference on Video and image processing

作者： Junjun Li Jiannong Cao School of Geological Engineering and Surveying Chang'an University Xi'an ShannXi China School of Earth Science and Resources Chang'an University Xi'an ShannXi China

ISBN: (纸本)9781450376822

Automatic separation of buildings from built-up area has attracted considerable interest in computer vision and digital photogrammetry field. While many efforts have been made for building extraction, none of them address the problem completely. This even a greater challenge in low-contrast very-high resolution (VHR) panchromatic satellite images. To alleviate this issue, a framework for automatic building detection approach using dominant structural feature (DSF) is proposed in this study. Firstly, in order to suppress noise while enhancing structural feature, contourlet transform based image contrast enhancement is employed followed by directional morphological filtering operation. Considering the structural characteristics of buildings which are significantly different from the other non-manmade objects. We then exploit DSF by means of windowed structure tensor analysis. Candidate building edges are generated using multi-seed classification technique in DSF space, subsequently. Finally, a series rule- and knowledge-based criterions are elaborate designed for false alarm reduction procedures.

关键词： Building detection Dominant structural feature image enhancement Low-contrast panchromatic satellite image

来源：评论

学校读者我要写书评

暂无评论

The Role of ICT in Poverty Reduction in Onitsha L.G.A of Anambra State 2019

The Role of ICT in Poverty Reduction in Onitsha L.G.A of Ana...

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Wilson Obinna Igbasi Department of Computer Science Nwafor Orizu College of Education Nsugbe Anambra State Nigeria

ISBN: (纸本)9781450376259

The research work is on the role of ICT in poverty reduction in Onitsha L.G.A of Anambra state. A survey research design was adopted for the study. The population consists of the entire indigenes of Onitsha North L.G. A of Anambra state. Stratified sampling technique was used to sample fifty respondents in the area. The questionnaire was the major instrument for data collection and it was validated by an expert in computer education at Nwafor Orizu College of Education, Nsugbe and expert in Measurement and evaluation at Nnamdi Azikiwe University, Awka both in Anambra State. The mean statistics was used to analyse the data collected. The findings of the study showed that ICT can enhance poverty reduction through provision of employment opportunity, capacity building, e-learning among others. However the major challenges for adopting ICT for poverty reduction include high rate of illiteracy, poor infrastructural facilities, inadequate human resources etc. the paper concluded that government should formulate good ICT policy and subsidize the cost of ICT.

关键词： Empowerment Opportunity ICTs Economic Growth Internet Poverty Reduction strategy

来源：评论

学校读者我要写书评

暂无评论

Using Passive DNS to Detect Malicious Domain Name 2019

Using Passive DNS to Detect Malicious Domain Name

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Zhouyu Bao Wenbo Wang Yuqing Lan School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781450376259

With the prosperity of the Internet, the number of malicious domain name is enormous, and the scope and harm of the threats they create are increasing. Using traditional reputation systems and reverse engineering methods to detect malicious domain name cannot be real-time, and the process of detecting malicious domain name is complicated and cumbersome. In order to make up for the deficiencies and maintain accuracy, this paper adopts machine-learning method and uses passive DNS as the analytical data to construct a malicious domain name classification detection model. According to the access characteristics and character characteristics of domain name, we designed a complete feature analysis scheme and proposed a multi-dimensional DGA domain name detection method. We also propose a pornographic domain name detection method based on word vector in combination with the Chinese network environment. Finally, we implement prototype systems for malicious domain name detection and achieve good results.

关键词： Passive DNS Porn domain name Domain generation algorith Malicious domain name

来源：评论

学校读者我要写书评

暂无评论

Solving Dynamic Multi-Objective Optimization Problems Using Cultural Algorithm based on Decomposition 2019

Solving Dynamic Multi-Objective Optimization Problems Using ...

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Ramya Ravichandran Ziad Kobti School of Computer Science University of Windsor Windsor ON Canada

ISBN: (纸本)9781450376259

The importance of dynamic multi-objective optimization problems (DMOPs) is on the rise, in complex systems. DMOPs have several objective functions and constraints that vary over time to be considered simultaneously. As a result, the Pareto optimal solutions (POS) and Pareto front (PF) will also vary with time. The desired algorithm should not only locate the optima but also track the moving optima efficiently. In this paper, we propose a new Cultural Algorithm (CA) based on decomposition (CA/D). The primary objective of the CA/D algorithm is to decompose DMOP into several scalar optimization subproblems and solve simultaneously. The subproblems are optimized utilizing the information shared only by its neighboring problems. The proposed CA/D is evaluated using CEC 2015 optimization benchmark functions. The results show that CA/D outperforms CA, Multi-population CA (MPCA), and MPCA incorporating game strategies (MPCA-GS), particularly in hybrid and composite benchmark problems.

关键词： Cultural Algorithm Decomposition Dynamic Multi-Objective Optimization

来源：评论

学校读者我要写书评

暂无评论

Far Point Algorithm: Active Semi-supervised Clustering for Rare Category Detection 2019

Far Point Algorithm: Active Semi-supervised Clustering for R...

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Rohan Loveland Jonathan Amdahl Department of Computer Science Whitman College Walla WA USA Klipsch School of Electrical and Computer Engineering New Mexico State University Las Cruces NM USA

ISBN: (纸本)9781450376259

In some data sets the number of categories (i.e. classes) that are represented is not known in advance. The process of discovering these categories can be difficult, particularly when a data set is skewed, such that the number of data points of some classes may greatly exceed those of other classes. Rare category detection algorithms address this problem by trying to present a user with at least one data point from each category, while minimizing the overall number of data points presented. We present an algorithm based on active and semi-supervised learning that finds category clusters using a query selection strategy that maximizes the distance from a set of already labeled data points to a query data point. We evaluate the algorithm's performance on artificially skewed versions of the MNIST data set as a rare category detection algorithm, investigating differences in performance due to both the effects of relative frequency and inherent class structure differences in feature space.

关键词： machine learning algorithms detection algorithms partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Shared Word Embedding Space Modeling Method Based on Orthogonal Projection 2019

Shared Word Embedding Space Modeling Method Based on Orthogo...

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Gang Liu Kai Wang Wangyang Liu Yang Cao Guang Li Harbin Engineering University College of Computer Science and Technology Heilongjiang Harbin China CETC big data research institute company limited Guiyang China

ISBN: (纸本)9781450376259

With the continuous development of computer technology, machine learning has been applied in more and more fields. However, the application of word embedding technology in bilingual Chinese and English still needs to be developed. In this paper, we propose a model construction process based on orthogonal projection, and analyze the validity of the model from multiple perspectives. We carry out word sense similarity experiments and word analogy experiments for the quality of single language in the model, and cross-language text similarity experiments for different linguistic quality in the model. Through the analysis of the experimental results, it can be proved that the proposed shared word embedding space model achieves good results compared with the traditional word embedding model, and the effect of the model achieves the desired purpose.

关键词： Cross Language Document Similarity Shared Word Embedding Technology Orthogonal Projection Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Binocular Stereo vision based Indoor Scene Perception

Binocular Stereo Vision based Indoor Scene Perception

引用

2011 3rd international conference on computer Research and Development(ICCrd 2011)

作者： Hong Liu and Jiexin Pu Electronic&Information Engineering College Henan University of Science and Technology Luoyang,China Qinghua Zhang Luoyang Sunray Technology Co.,Ltd.Luoyang,China

Scene perception aims to build a semantic context for various tasks of visual processing,especially for object *** vision system is now widely equipped with mobile intelligent robots,however,monocular images are currently mostly used for scene perception task One can obtain lower classification performance by using features extracted from monocular image as the complexity of natural scene In this paper a binocular stereo vision based approach for scene perception is developed.A feature descriptor of indoor scene is proposed,that is a vector extracted from planes fitting parameters in several specified *** step,scene is classified as empty space and close space classes using feature extracted from disparity map with nearest neighbor *** following step,both empty space and close space scene are classified into some subclasses using Gist and proposed feature *** test our approach we created a dataset of 4 indoor scenes *** experiments show that our approach got excellent classification performance.

关键词： binocular stereo vision indoor scene Gist 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：