检索结果-内蒙古大学图书馆

A novel video shot boundary detection framework employing DCT and pattern matching

MULTIMEDIA TOOLS AND APPLICATIONS 2019年第24期78卷 34707-34723页

作者： Dhiman, Shekhar Chawla, Rashmi Gupta, Shailender JC Bose Univ Sci & Technol Dept Elect Engn YMCA Faridabad India

The video Shot Boundary Detection (SBD) is an elementary step in realising a system capability to perform content based video search, structural analysis, data retrieval and video summation. Myriad research works in the past have been reported to construct SBD algorithms. However, the need of an error-free, meticulous and cost-effective SBD technique still persists;for applications viz. apt management, storage, browsing, video indexing and retrieval of multimedia data. This paper is an effort in the same direction with the aim of achieving high execution speed and greater accuracy. The proposed SBD technique in this paper incorporates three steps: (i) Candidate Segment Selection (ii) Cut Transition detection (iii) Gradual Transition detection. This paper adopts pixel based technique with candidate segment selection to speed up the SBD. For Cut Transition detection, the proposed method employs Discrete Cosine Transform (DCT) and for Gradual Transition detection, it employs image Histogram and Pattern Matching. The comparison of MATLAB simulation results of the proposed SBD technique with those in literature manifest better results in terms of execution speed and accuracy.

关键词： Fast Shot Boundary detection Discrete Cosine Transform (DCT) Adaptive Threshold Candidate segment Cut Transition and Gradual Transition detection Cosine Distance

来源：评论

学校读者我要写书评

暂无评论

Multimedia processing using deep learning technologies, high-performance computing cloud resources, and Big Data volumes

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2020年第17期32卷 e5699-e5699页

作者： Mahmoudi, Sidi Ahmed Belarbi, Mohammed Amin Mahmoudi, Said Belalem, Ghalem Manneback, Pierre UMONS Fac Engn Comp Sci Unit Mons Belgium Univ Oran 1 Fac Exact & Appl Sci Comp Sci Dept Oran Algeria Univ Mons Comp Sci Unit 9 Rue Houdain Mons B-7000 Mons Belgium

The last few years have been marked by the presence of very large sets of images and videos in our everyday lives. These multimedia objects have a very fast frequency of creation and sharing since images and videos can come from different devices such as smartphones, satellites, cameras, or drones. They are generally used to illustrate objects in different situations (public areas, train stations, hospitals, political and sport events and competitions, etc). As consequence, image and video processing algorithms have got increasing importance for several computer vision applications that should be adapted for managing large-scale volumes and exploiting high performance computing resources (local or cloud). In this work, we propose a cloud-based toolbox (platform) for computer vision applications. This platform integrates a toolbox of image and video processing algorithms that can (i) exploit high performance computing cloud resources, (ii) execute applications in real time, and (iii) manage large-scale database using Big Data technologies. The related libraries and hardware drivers are automatically integrated and configured in order to offer to users an access to the different applications without the need to download, install, and configure software or hardware. Experiments were conducted using three kinds of applications: (i) image and video processing applications, (ii) deep learning techniques for images classification and multiobject localization, and (iii) images indexation and retrieval. These experiments demonstrated the interest of our platform for sharing, in an efficient way, our scientific contributions and annotated databases in order to improve the quality and performance of computer vision applications.

关键词： Big Data cloud computing deep Learning high performance computing images indexation and retrieval multimedia processing

来源：评论

学校读者我要写书评

暂无评论

Human Motion Data retrieval Based on Staged Dynamic Time Deformation Optimization Algorithm

引用

COMPLEXITY 2020年第1期2020卷

作者： Bao, Hongshu Yao, Xiang Anhui Univ Technol Dept Sports Maanshan 243000 Anhui Peoples R China

In recent years, with the rapid development of computer storage capabilities and network transmission capabilities, users can easily share their own video and image information on social networking sites, and the amount of multimedia data on the network is rapidly increasing. With the continuous increase of the amount of data in the network, the establishment of effective automated data management methods and search methods has become an increasingly urgent need. This paper proposes a retrieval method of human motion data based on motion capture in index space. By extracting key frames from the original motion to perform horizontal dimensionality reduction and defining features based on Laban motion analysis, the motion segment is subjected to vertical feature dimensionality reduction. After extracting features from the input motion segment, motion matching is performed on the index space. This paper designs the optimization method of the phased dynamic time deformation algorithm in time efficiency and analyzes the optimization method of the phased dynamic time deformation algorithm in time complexity. Considering the time efficiency redundancy, this paper optimizes the time complexity of the phased dynamic time deformation method. This improves the time efficiency of the staged dynamic time warping algorithm, making it suitable for larger-scale human motion data problems. Experiments show that the method in this paper has the advantage of speed, is more in line with the semantics of human motion, and can meet the retrieval requirements of human motion databases.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Object retrieval in images using SIFT and R-CNN

Object Retrieval in Images using SIFT and R-CNN

引用

Innovative Trends in Information Technology (ICITIIT), International Conference on

作者： I C Amitha N K Narayanan Kannur University Kerala India Indian Institute of Information Technology Kottayam Valavoor (P.O.) Kottayam Kerala

ISBN: (数字)9781728142104

ISBN: (纸本)9781728142111

image-based object retrieval has numerous applications in the field of machine vision to inquire from an appropriate image or video sequence for a given query object. The object retrieval task is conventionally carried out by a set of handcrafted algorithms, which provides image depictions in the fashion of visual characteristics. During the last decade, an extensive change has been practiced to describe visual content from handcrafted characteristics to the application of machine learning approaches and to the real layout of the image descriptors. The extensive movement is based on Convolutional Neural Networks (CNN) which is popularly known as Deep Learning. This proposed work deals with a combination of both conventional and machine learning approaches to retrieve an image object from a given dataset. This is done by a series of activities such as feature extraction and storage of training images, query image selection and feature extraction. Similarity matching between database and query image features. Final retrieval is based on the objectness score.

关键词： Convolutional neural networks Machine learning Feature extraction Task analysis Proposals Visualization databases

来源：评论

学校读者我要写书评

暂无评论

Binary convolutional neural network features off-the-shelf for image to video linking in endoscopic multimedia databases

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第21期77卷 28817-28842页

作者： Petscharnig, Stefan Schoeffmann, Klaus Alpen Adria Univ Klagenfurt Univ Str 65-67 A-9020 Klagenfurt Am Worthersee Austria

With a rigorous long-term archival of endoscopic surgeries, vast amounts of video and image data accumulate. Surgeons are not able to spend their valuable time to manually search within endoscopic multimedia databases (EMDBs) or manually maintain links to interesting sections in order to quickly retrieve relevant surgery sections. Enabling the surgeons to quickly access the relevant surgery scenes, we utilize the fact that surgeons record external images additionally to the surgery video and aim to link them to the appropriate video sequence in the EMDB using a query-by-example approach. We propose binary Convolutional Neural Network (CNN) features off-the-shelf and compare them to several baselines: pixel-based comparison (PSNR), image structure comparison (SSIM), hand-crafted global features (CEDD and feature signatures), as well as CNN baselines Histograms of Class Confidences (HoCC) and Neural Codes (NC). For evaluation, we use 5.5 h of endoscopic video material and 69 query images selected by medical experts and compare the performance of the aforementioned image mathing methods in terms of video hit rate and distance to the true playback time stamp (PTS) for correct video predictions. Our evaluation shows that binary CNN features are compact, yet powerful image descriptors for retrieval in the endoscopic imaging domain. They are able to maintain state-of-the-art performance, while providing the benefit of low storage space requirements and hence provide the best compromise.

关键词： Content-based video retrieval Endoscopic multimedia CNNs

来源：评论

学校读者我要写书评

暂无评论

Label Consistent Matrix Factorization Hashing for Large-Scale Cross-Modal Similarity Search

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2019年第10期41卷 2466-2479页

作者： Wang, Di Gao, Xinbo Wang, Xiumei He, Lihuo Xidian Univ Sch Comp Sci & Technol 2 South Taibai Rd Xian 710071 Shaanxi Peoples R China Xidian Univ Video & Image Proc Syst VIPs Lab Sch Elect Engn 2 South Taibai Rd Xian 710071 Shaanxi Peoples R China

Multimodal hashing has attracted much interest for cross-modal similarity search on large-scale multimedia data sets because of its efficiency and effectiveness. Recently, supervised multimodal hashing, which tries to preserve the semantic information obtained from the labels of training data, has received considerable attention for its higher search accuracy compared with unsupervised multimodal hashing. Although these algorithms are promising, they are mainly designed to preserve pairwise similarities. When semantic labels of training data are given, the algorithms often transform the labels into pairwise similarities, which gives rise to the following problems: (1) constructing pairwise similarity matrix requires enormous storage space and a large amount of calculation, making these methods unscalable to large-scale data sets;(2) transforming labels into pairwise similarities loses the category information of the training data. Therefore, these methods do not enable the hash codes to preserve the discriminative information reflected by labels and, hence, the retrieval accuracies of these methods are affected. To address these challenges, this paper introduces a simple yet effective supervised multimodal hashing method, called label consistent matrix factorization hashing (LCMFH), which focuses on directly utilizing semantic labels to guide the hashing learning procedure. Considering that relevant data from different modalities have semantic correlations, LCMFH transforms heterogeneous data into latent semantic spaces in which multimodal data from the same category share the same representation. Therefore, hash codes quantified by the obtained representations are consistent with the semantic labels of the original data and, thus, can have more discriminative power for cross-modal similarity search tasks. Thorough experiments on standard databases show that the proposed algorithm outperforms several state-of-the-art methods.

关键词： Hashing multimodal supervised similarity search cross-modal

来源：评论

学校读者我要写书评

暂无评论

Textual description based video annotation methods

Textual description based video annotation methods

引用

2018 International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2018

作者： Shama, P.S. Prakash, Pattan PDA College of Engineering Department of Computer Science and Engineering Kalaburagi585102 India

ISBN: (纸本)9781538679494

In the Present days, a large number of multimedia significant resources create the browsing, retrieval task. In this survey different types of methods are using, to foster the browsing of large video storage and provides sufficient access to contents. The video annotation initially cuts the detected video sequence, where the succeeding frames take out to show each shot or frames with a huge difference. The extraction of key frames that shows in every image is compressing the few images by using standard technologies like HOG, fuzzy clustering and Genetic algorithm regarding the textual depiction of the scene. video Annotation improves the sufficient searching and retrieving of the video components. They are inspired and are sometimes directly taken from image techniques. Thus, numerous varieties of images are easily applied to video annotation. © 2018 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Classification and retrieval of radiology images in H.264/AVC compressed domain

引用

SIGNAL image AND video PROCESSING 2017年第3期11卷 573-580页

作者： Yamaghani, Mohammadreza Zargari, Farzad Islamic Azad Univ Sci & Res Branch Dept Comp Engn Tehran Iran Res Inst ICT Dept Informat Technol Tehran Iran

The ever-increasing number of produced radiology images in medical centers makes storage, classification and retrieval of these images an important and vital issue in management of medical centers' databases. In this paper, we employ H.264/AVC standard for coding of radiology images and study its performance on storage, classification and retrieval of radiology images. The conducted experiments indicate that coding of radiology images by H.264/AVC standard, on general, reduces the size of coded image to less than half of the coding in PNG format. Moreover, we employ a compressed domain indexing and retrieval method for H.264/AVC coded images, which avoids full decompression of coded image and in turn reduces the indexing and retrieval time. Experimental results indicate that employing this compressed domain feature vector achieves on average 93% accuracy on classification and 85% overall precision in retrieval of radiology images.

关键词： Medical images Coding Classification retrieval Compressed domain

来源：评论

学校读者我要写书评

暂无评论

Large-scale image retrieval with supervised sparse hashing

引用

NEUROCOMPUTING 2017年 229卷 45-53页

作者： Xu, Yan Shen, Fumin Xu, Xing Gao, Lianli Wang, Yuan Tan, Xiao Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Nanjing Jiangsu Peoples R China Natl Univ Singapore Dept Ind & Syst Engn Singapore Singapore Univ Hong Kong Hong Kong Hong Kong Peoples R China

In recent years, learning based hashing becomes an attractive technique in large-scale image retrieval due to its low storage and computation cost. Hashing methods map each high-dimensional vector onto a low-dimensional hamming space by projection operators. However, when processing high dimensional data retrieval, many existing methods including hashing cost a majority of time on projection operators. In this paper, we solve this problem by implementing a sparsity regularizer. On one hand, due to the sparse property of the projection matrix, our method effectively lower both the storage and computation cost. On the other hand, we reduce the effective number of parameters involved in the learned projection matrix according to sparsity regularizer, which helps avoid overfitting problem. Without relaxing binary constraints, an iterative scheme jointly optimizing the objective function directly was given, which helps to obtain effective and efficient binary codes. We evaluate our method on three databases and compare it with some state-of-the-art hashing methods. Experimental results demonstrate that our method outperforms the comparison approaches.

关键词： Learning based hashing Medical Sparsity image retrieval

来源：评论

学校读者我要写书评

暂无评论

ClickPoints: an expandable toolbox for scientific image annotation and analysis

引用

METHODS IN ECOLOGY AND EVOLUTION 2017年第6期8卷 750-756页

作者： Gerum, Richard C. Richter, Sebastian Fabry, Ben Zitterbart, Daniel P. Univ Erlangen Nurnberg BioPhys Grp Erlangen Germany Woods Hole Oceanog Inst Appl Ocean Phys & Engn Woods Hole MA 02543 USA Helmholtz Ctr Polar & Marine Res Alfred Wegener Inst Bremerhaven Germany

1. Optical recordings are ubiquitous in current scientific research. As recording and storing images and videos have become simpler and cheaper over the past years, new and more efficient tools are needed to analyse the growing amount of data. While current scientific image analysis tools focus on medical 3D data sets, a tool for efficiently handling large-scale 2D time-series recordings is still missing. 2. We developed Click Points, an expandable, open-source, Python-based software to fill this gap. ClickPoints combines and streamlines the three main steps of image analysis - visualization, annotation and evaluation - in one program. 3. ClickPoints enables the user to (i) efficiently review large data sets of images and videos, (ii) annotate interesting findings and (iii) facilitate manual and automatic evaluations. ClickPoints is highly versatile, ranging from clicking and selecting objects with simple markers, drawing masks and computing trajectories, up to (iv) custom-written Python add-ons for adapting or extending the available features. These add-ons (v) reduce development time by utilizing Click Points' display, interface and storage solutions. In addition, ClickPoints provides an (vi) extensive data base application programming interface to facilitate efficient storage and retrieval of results. 4. ClickPoints is designed to simplify repetitive and labour-intensive scientific tasks, especially when dealing with large image and video time-series recordings. ClickPoints offers cross-platform support for Windows and Linux and is released under the GPLv3 license. Download, documentation and numerous examples are available at http://***.

关键词： ground truth image annotation image evaluation labelling open source Python time-series data visual data processing

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：