检索结果-内蒙古大学图书馆

A center-driven image set partition algorithm for efficient structure from motion

INFORMATION SCIENCES 2019年 479卷 101-115页

作者： Sun, Kun Tao, Wenbing China Univ Geosci Sch Comp Sci Hubei Key Lab Intelligent Geoinformat Proc Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Hubei Peoples R China

This paper proposes a novel center-driven image set partitioning method dedicated for efficient Structure from Motion (SfM) on unevenly distributed images. First, multiple base clusters are found at places with high image density. Instead of building a small initial model from two images, we build multiple initial base models from these base clusters. This promises that the scene is reconstructed from dense places to sparse areas, which can reduce error accumulation when images have weak overlap. Second, the whole image set is divided into several region clusters to decide which images should be reconstructed from the same base model. In this step, the base models are treated as centers and the affinity between an image with each of them is measured by the reconstruction path length. To enable faster speed, images in each region cluster are further divided into several sub-region clusters so that they could be added to the same base model simultaneously. Based on the above partitioning results, the partial 3D models are reconstructed in parallel and then merged. Experiments show that the proposed method achieves remarkable speedup and better completeness than state-of-the-art methods, without significant accuracy deterioration. (C) 2018 Elsevier Inc. All rights reserved.

关键词： Center-driven image set partitioning 3D reconstruction Structure from Motion

来源：评论

学校读者我要写书评

暂无评论

The Research of Implementation Method of Canny Edge Detection of Video on FPGA

The Research of Implementation Method of Canny Edge Detectio...

引用

Information Science, parallel and distributed Systems (ISPDS), International Conference on

作者： Li Quan Tan Bin He School of information science and technology Beijing University of chemical technology

ISBN: (数字)9781728196688

ISBN: (纸本)9781728196695

Edge detection algorithm has an important application in video image processing. The algorithm overcomes the shortcomings of traditional video image edge detection methods, and significantly improves the quality of video image edge detection. However, the amount of calculation is very large, and the traditional implementation method is difficult to meet the real-time requirements of video image edge detection, and the implementation cost is high. In this design, field programmable gate array (FPGA) is used as the core to construct and implement Canny video image edge detection system. Firstly, the video image is collected by ov7725 camera in real time; then, the edge detection of video image based on Canny algorithm is implemented in FPGA. Finally, the effect of Canny video image edge detection is compared and analyzed. This design has a good reference value for canny video image edge detection.

关键词： image edge detection Information science image filtering

来源：评论

学校读者我要写书评

暂无评论

Joint Channel Pruning and Quantization-Based CNN Network Learning with Mobile Computing-Based image Recognition

引用

WIRELESS COMMUNICATIONS & MOBILE COMPUTING 2021年第1期2021卷

作者： Liu, Huanyu Luo, Qing Shao, Mingmei Pan, Jeng-Shyang Li, Junbao Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Aerosp Engn Nanjing 210016 Peoples R China Shenyang Aircraft Design & Res Inst Shenyang 110035 Peoples R China Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao 266590 Peoples R China

The development of the Internet and communication technology has ushered in a new era of the Internet of Things (IoT). Moreover, with the rapid development of artificial intelligence, objects are endowed with intelligence, such as home automation and smart healthcare, which are typical applications of artificial intelligence technology in IoT. With the rise of convolutional neural network (CNN) in the field of computer vision, more and more practical applications need to deploy CNN on mobile devices. However, due to the large amount of CNN computing operations and the large number of parameters, it is difficult to deploy on ordinary edge devices. The neural network model compression method has become a popular technology to reduce the computational cost and has attracted more and more attention. We specifically design a small target detection network for hardware platforms with limited computing resources, use pruning and quantization methods to compress, and demonstrate in VOC dataset and RSOD dataset on the actual hardware platform. Experiments show that the proposed method can maintain a fairly accurate rate while greatly speeding up the inference speed.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Norm-Aware Embedding for Efficient Person Search

Norm-Aware Embedding for Efficient Person Search

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chen, Di Zhang, Shanshan Yang, Jian Schiele, Bernt Nanjing Univ Sci & Technol Sch Comp Sci & Engn Minist Educ PCA LabKey Lab Intelligent Percept & Syst High D Nanjing Peoples R China Jiangsu Key Lab Image & Video Understanding Socia Nanjing Peoples R China Max Planck Inst Informat Saarland Informat Campus Saarbrucken Germany

ISBN: (纸本)9781728171685

Person Search is a practically relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID). Specifically, it requires to find and locate all instances with the same identity as the query person in a set of panoramic gallery images. One major challenge comes from the contradictory goals of the two sub-tasks, i.e., person detection focuses on finding the commonness of all persons while person re-ID handles the differences among multiple identities. Therefore, it is crucial to reconcile the relationship between the two sub-tasks in a joint person search model. To this end, we present a novel approach called Norm-Aware Embedding to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training. We further extend the proposal-level person embedding to pixel-level, whose discrimination ability is less affected by misalignment. We outperform other one-step methods by a large margin and achieve comparable performance to two-step methods on both CUHK-SYSU and PRW. Also, our method is easy to train and resource-friendly, running at 12 fps on a single GPU.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of an HPC-based Expert System to speed-up Retail Data Analysis using Residual Networks Combined with parallel Association Rule Mining and Scalable Recommenders

Design and Evaluation of an HPC-based Expert System to speed...

引用

Proceedings of the International Convention MIPRO

作者： C. Barakat M. Riedel S. Brynjólfsson G. Cavallaro J. Busch R. Sedona School of Engineering and Natural Sciences University of Iceland Iceland Jülich Supercomputing Centre Forschungszentrum Jülich Germany

Given the Covid-19 pandemic, the retail industry shifts many business models to enable more online purchases that produce large transaction data quantities (i.e., big data). Data science methods infer seasonal trends about products from this data and spikes in purchases, the effectiveness of advertising campaigns, or brand loyalty but require extensive processing power leveraging High-Performance Computing to deal with large transaction datasets. This paper proposes an High-Performance Computing-based expert system architectural design tailored for ‘big data analysis’ in the retail industry, providing data science methods and tools to speed up the data analysis with conceptual interoperability to commercial cloud-based services. Our expert system leverages an innovative Modular Supercomputer Architecture to enable the fast analysis by using parallel and distributed algorithms such as association rule mining (i.e., FP-Growth) and recommender methods (i.e., collaborative filtering). It enables the seamless use of accelerators of supercomputers or cloud-based systems to perform automated product tagging (i.e., residual deep learning networks for product image analysis) to obtain colour, shapes automatically, and other product features. We validate our expert system and its enhanced knowledge representation with commercial datasets obtained from our ON4OFF research project in a retail case study in the beauty sector.

关键词：

来源：评论

学校读者我要写书评

暂无评论

基于并行计算的抛光轴表面缺陷检测研究

引用

机电工程 2020年第12期37卷 1540-1546页

作者：姜庆胜李研彪计时鸣浙江工业大学机械工程学院浙江杭州310023

针对在生产实践中抛光轴表面缺陷检测的实时性和缺陷分类需求问题,对抛光轴表面缺陷检测系统、缺陷图像采集、图像特征、传统检测方法等方面进行了研究,归纳了轴表面缺陷检测的处理方法。提出了两种基于并行计算的检测系统,即基于云的Sp... 详细信息

针对在生产实践中抛光轴表面缺陷检测的实时性和缺陷分类需求问题,对抛光轴表面缺陷检测系统、缺陷图像采集、图像特征、传统检测方法等方面进行了研究,归纳了轴表面缺陷检测的处理方法。提出了两种基于并行计算的检测系统,即基于云的Spark多机并行的分布式计算机集群检测系统和单机多核的CUDA并行处理检测系统;通过Spark架构多机分布式并行计算机理的分析,以及结合CUDA单机多核并行运算原理,从数学角度进行了并行化处理,最后进行了相应的实验。研究结果表明:基于CUDA的单机多核的并行处理检测系统适合实时检测,基于Spark的多机分布式并行检测系统不适合实时检测系统,但适合大数据处理系统。

关键词：图像处理 Spark 分布式并行计算图像处理单元 CUDA

来源：评论

学校读者我要写书评

暂无评论

Generic framework for vessel detection and tracking based on distributed marine radar image data

引用

CEAS SPACE JOURNAL 2019年第1期11卷 65-79页

作者： Siegert, Gregor Hoth, Julian Banys, Pawel Heymann, Frank German Aerosp Ctr DLR Inst Commun & Nav Kalkhorstweg 53 D-17235 Neustrelitz Germany

Situation awareness is understood as a key requirement for safe and secure shipping at sea. The primary sensor for maritime situation assessment is still the radar, with the AIS being introduced as supplemental service only. In this article, we present a framework to assess the current situation picture based on marine radar image processing. Essentially, the framework comprises a centralized IMM-JPDA multi-target tracker in combination with a fully automated scheme for track management, i.e., target acquisition and track depletion. This tracker is conditioned on measurements extracted from radar images. To gain a more robust and complete situation picture, we are exploiting the aspect angle diversity of multiple marine radars, by fusing them a priori to the tracking process. Due to the generic structure of the proposed framework, different techniques for radar image processing can be implemented and compared, namely the BLOB detector and SExtractor. The overall framework performance in terms of multi-target state estimation will be compared for both methods based on a dedicated measurement campaign in the Baltic Sea with multiple static and mobile targets given.

关键词： Maritime situation awareness Multi-target tracking Multi-radar fusion IMM-JPDA filtering Radar image processing BLOB detector SExtractor

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Classification on the Base of Convolutional Neural Networks 2nd

Fuzzy Classification on the Base of Convolutional Neural Net...

引用

2nd International Conference of Artificial Intelligence, Medical Engineering, Education (AIMEE)

作者： Puchkov, A. Dli, M. Kireyenkova, M. Natl Res Univ Moscow Power Engn Inst Branch Smole Energetichesky Proyezd 1 G Smolensk 2014013 Russia

ISBN: (纸本)9783030120825;9783030120818

The paper deals with the algorithm of object classification based on the method of fuzzy logic and the application of artificial convolutional neural networks. Every object can be characterized by a set of data presented in the numerical form and in the form of images (photographs in different parts of the light spectrum). In this case, one object can be matched with a few images associated with it;they can be received by different methods and from different sources. In the algorithm, this generalized totality of images is recognized by convolutional neural networks. A separate neural network is formed for every channel of data receiving. Then, the network outputs are combined for processing in the system of classification on the basis of fuzzy logic output. The normalized outputs of convolutional neural networks are used as values of a membership function to terms of outputs variables when a fuzzy classifier works. For the first adjustment of the convolution neural network hyperparameters, the gradient method is applied. The algorithm is realized in Python language with the use of Keras deep learning library and Tensor Flow library of parallel computation with CUDA technology from NVIDIA company. This paper presents the results of practical application of the developed neuro-fuzzy classifier to forecast the problem of working time losses.

关键词： Fuzzy logic Classification image recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MAD-C: Multi-stage Approximate distributed Cluster-Combining for Obstacle Detection and Localization 24th

MAD-C: Multi-stage Approximate Distributed Cluster-Combining...

引用

24th International European Conference on parallel and distributed Computing (Euro-Par)

作者： Keramatian, Amir Gulisano, Vincenzo Papatriantafilou, Marina Tsigas, Philippas Nikolakopoulos, Yiannis Chalmers Univ Technol Gothenburg Sweden

ISBN: (纸本)9783030105495;9783030105488

Efficient distributed multi-sensor monitoring is a key feature of upcoming digitalized infrastructures. We address the problem of obstacle detection, having as input multiple point clouds, from a set of laser-based distance sensors;the latter generate high-rate data and can rapidly exhaust baseline analysis methods, that gather and cluster all the data. We propose MAD-C, a distributed approximate method: it can build on any appropriate clustering, to process disjoint subsets of the data distributedly;MAD-C then distills each resulting cluster into a data-summary. The summaries, computable in a continuous way, in constant time and space, are combined, in an order-insensitive, concurrent fashion, to produce approximate volumetric representations of the objects. MAD-C leads to (i) communication savings proportional to the number of points, (ii) multiplicative decrease in the dominating component of the processing complexity and, at the same time, (iii) high accuracy (with RandIndex > 0.95), in comparison to its baseline counterpart. We also propose MAD-C-ext, building on the MAD-C's output, by further combining the original data-points, to improve the outcome granularity, with the same asymptotic processing savings as MAD-C.

关键词： Point cloud processing Approximations Fog computing

来源：评论

学校读者我要写书评

暂无评论

Malicious code detection based on CNNs and multi-objective algorithm

引用

JOURNAL OF parallel AND distributed COMPUTING 2019年 129卷 50-58页

作者： Cui, Zhihua Du, Lei Wang, Penghong Cai, Xingjuan Zhang, Wensheng TaiYuan Univ Sci & Technol Complex Syst & Computat Intelligence Lab Taiyuan 030024 Shanxi Peoples R China Chinese Acad Sci Inst Automat State Key Lab Intelligent Control & Management Co Beijing 100190 Peoples R China

An increasing amount of malicious code causes harm on the internet by threatening user privacy as one of the primary sources of network security vulnerabilities. The detection of malicious code is becoming increasingly crucial, and current methods of detection require much improvement. This paper proposes a method to advance the detection of malicious code using convolutional neural networks (CNNs) and intelligence algorithm. The CNNs are used to identify and classify grayscale images converted from executable files of malicious code. Non-dominated Sorting Genetic Algorithm ii (NSGA-ii) is then employed to deal with the data imbalance of malware families. A series of experiments are designed for malware image data from Vision Research Lab. The experimental results demonstrate that the proposed method is effective, maintaining higher accuracy and less loss. (C) 2019 Elsevier Inc. All rights reserved.

关键词： Malicious code Deep learning CNN Imbalance data NSGA-ii

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：