检索结果-内蒙古大学图书馆

27th International Conference on Neural Information processing

作者： He, Ruhan Cheng, Ming Xiong, Mingfu Qin, Xiao Liu, Junping Hu, Xinrong Wuhan Text Univ Engn Res Ctr Hubei Prov Clothing Informat Wuhan 430200 Peoples R China Auburn Univ Dept Comp Sci & Software Engn Auburn AL 36849 USA

ISBN: (纸本)9783030638290;9783030638306

Clothing parsing has been actively studied in the vision community in recent years. Inspired by the color coherence for clothing and the self-attention mechanism, this paper proposes a Triple Attention Network (TANet) equipped with a color attention module, a position attention module and a channel attention module, to facilitate fine-grained segmentation of clothing images. Concretely, the color attention module is introduced for harvesting color coherence, which selectively aggregates the color feature of clothing. The position attention module and the channel attention module are designed to emphasize the semantic interdependencies in spatial and channel dimensions respectively. The outputs of the three attention modules are incorporated to further improve feature representation which contributes to more precise clothing parsing results. The proposed TANet has achieved 69.54% mIoU - a promising clothing parsing performance on ModaNet, the latest large-scale clothing parsing dataset. Especially, the color attention module is also demonstrated to bring semantic consistency and precision improvement obviously. The source code is made available in the public domain.

关键词： image processing and computer vision Clothing parsing Attention network Color coherence

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image Fusion 1

引用

2013年

作者： Subhasis Chaudhuri Ketan Kotwal

ISBN: (数字)9781461474708

ISBN: (纸本)9781461474692;9781489993755

is the first text dedicated to the fusion techniques for such a huge volume of data consisting of a very large number of images. This monograph brings out recent advances in the research in the area of visualization of hyperspectral data. It provides a set of pixel-based fusion techniques, each of which is based on a different framework and has its own advantages and disadvantages. The techniques are presented with complete details so that practitioners can easily implement them. It is also demonstrated how one can select only a few specific bands to speed up the process of fusion by exploiting spatial correlation within successive bands of the hyperspectral data. While the techniques for fusion of hyperspectral images are being developed, it is also important to establish a framework for objective assessment of such techniques. This monograph has a dedicated chapter describing various fusion performance measures that are applicable to hyperspectral image fusion. This monograph also presents a notion of consistency of a fusion technique which can be used to verify the suitability and applicability of a technique for fusion of a very large number of images. This book will be a highly useful resource to the students, researchers, academicians and practitioners in the specific area of hyperspectral image fusion, as well as generic image fusion.

关键词： image processing and computer vision Data Mining and Knowledge Discovery Signal, image and Speech processing

来源：评论

学校读者我要写书评

暂无评论

The Digital Dividend of Terrestrial Broadcasting 1

引用

2012年

作者： Roland Beutler

来源：评论

学校读者我要写书评

暂无评论

A Fully Physics-Based CMOS Camera Model Within a 3-D Virtual World Ray Trace Simulation Engine

引用

SN computer Science 2024年第1期5卷 1-16页

作者： Pecharromán-Gallego, Raúl Ibeo Automotive Eindhoven B.V. High Tech Campus 69 Eindhoven 5656 AG Netherlands

CMOS based cameras are present nowadays for many imaging applications, ranging from any consumer, industrial or artistic use, they will also be introduced into the simulation engines applied to any raytracing technology, like electro optical, radar or LiDAR sensors simulation in the automotive industry, which is the scope of this work, that introduces a holistic model of CMOS camera that can be customized for different applications from input specifications. Starting with a ray trace simulation environment of the surrounding scene to its light reaching the lens, to photon conversion into electron–hole pairs within the image sensor photodiodes, to final image rendering and shown in display. Both the camera model and the ray tracing engine are fully physics-based. The whole system is validated within a simulated environmental illumination system including the camera sensor pipeline for final image processing. We also use industrial standard color and resolution targets and methodologies for image quality validation. Furthermore, a HDR image fusion by using fusion of images captured at different exposure values is also introduced. Moreover, validation against real photographs on color targets and the resolution methodologies introduced here leads to feasibility of the whole process presented. In summary, this work presents a number of well proven methodologies on CMOS camera simulation valid within both a ray trace environment and real world, and its automotive application feasibility supported with full real measurements validation. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： CMOS sensor simulation Graph algorithms image processing and computer vision image quality Model validation Raytracing

来源：评论

学校读者我要写书评

暂无评论

Mobile Cosmetics Advisor: An Imaging Based Mobile Service

Mobile Cosmetics Advisor: An Imaging Based Mobile Service

引用

Conference on Multimedia on Mobile Devices 2010

作者： Bhatti, Nina Baker, Harlyn Chao, Hui Clearwater, Scott Harville, Mike Jain, Jhilmil Lyons, Nic Marguier, Joanna Schettino, John Suesstrunk, Sabine Hewlett Packard Labs 1501 Page Mill Dr Palo Alto CA 94304 USA Ecole Polytech Fed Lausanne LCAV Lausanne Switzerland

ISBN: (纸本)9780819479358

Selecting cosmetics requires visual information and often benefits from the assessments of a cosmetics expert. In this paper we present a unique mobile imaging application that enables women to use their cell phones to get immediate expert advice when selecting personal cosmetic products. We derive the visual information from analysis of camera phone images, and provide the judgment of the cosmetics specialist through use of an expert system. The result is a new paradigm for mobile interactions-image-based information services exploiting the ubiquity of camera phones. The application is designed to work with any handset over any cellular carrier using commonly available MMS and SMS features. Targeted at the unsophisticated consumer, it must be quick and easy to use, not requiring download capabilities or preplanning. Thus, all application processing occurs in the back-end system and not on the handset itself. We present the imaging pipeline technology and a comparison of the services' accuracy with respect to human experts.

关键词： image processing and computer vision Applications and Expert Systems Applications

来源：评论

学校读者我要写书评

暂无评论

Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data 1

引用

丛书名： Intelligent Systems Reference Library

2016年

作者： Robert B. Fisher Yun-Heh Chen-Burger Daniela Giordano Lynda Hardman Fang-Pang Lin

ISBN: (数字)9783319302089

ISBN: (纸本)9783319302065;9783319807508

This book gives a start-to-finish overview of the whole Fish4Knowledge project, in 18 short chapters, each describing one aspect of the project. The Fish4Knowledge project explored the possibilities of big video data, in this case from undersea video. Recording and analyzing 90 thousand hours of video from ten camera locations, the project gives a 3 year view of fish abundance in several tropical coral reefs off the coast of Taiwan. The research system built a remote recording network, over 100 Tb of storage, supercomputer processing, video target detection and tracking, fish species recognition and analysis, a large SQL database to record the results and an efficient retrieval mechanism. Novel user interface mechanisms were developed to provide easy access for marine ecologists, who wanted to explore the dataset. The book is a useful resource for system builders, as it gives an overview of the many new methods that were created to build the Fish4Knowledge system in a manner that also allows readers to see how all the components fit together.

关键词： Computational Intelligence image processing and computer vision Fish & Wildlife Biology & Management Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Automating and Optimizing the Design Process of Solar Module Installation and Providing Necessary Forecasts using Machine Learning Algorithm 2018

Automating and Optimizing the Design Process of Solar Module...

引用

10th International Conference on Machine Learning and Computing (ICMLC)

作者： Shende, Prasad Mehendarge, Shivani Goel, Anubhav Kasturkar, Vaishnavi Chougule, Sachin Takalikar, Mukta Pune Inst Comp Technol Dept Comp Engn Pune Maharashtra India Inteliment Technol India Pvt Ltd India Pune Maharashtra India

ISBN: (纸本)9781450363532

Solar energy is the most readily available and the cheapest form of energy available. In a data-driven world of today, the data analysis tools combined with machine learning algorithms and sensors can be used to analyze and crunch data to solve various problems plaguing the solar industry. Designing a system that recognizes the accurate positions for installing the PV modules on a rooftop, predict the power production capacity of the solar power plant and also manage the maintenance cycles, will not only help in minimizing the losses due to installation at improper places but also will increase the efficiency of the plant and reduce the cost of electricity production as a whole. This paper aims at using machine learning algorithms and image analysis tools to find the proper areas wherein the PV modules can be installed so as to maximize the production and at the same time predicting and visualizing the maintenance cycles of the power plant. The paper also aims to provide relevant data points for prediction of weather and power, which will be tabulated in a user-friendly way for further analytics.

关键词： Artificial intelligence image processing and computer vision connectism and neural nets genetic algorithms un- supervised learning and data management systems

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Human Activity Understanding

Skeleton-Based Human Activity Understanding

引用

作者： Jun Liu Nanyang Technological University

学位级别：博士

Human activity understanding is an important research problem due to its relevance to a wide range of applications. Recently, 3D skeleton-based activity analysis becomes popular due to its succinctness, robustness, and view-invariant representation. In this thesis, we focus on human activity understanding in 3D skeleton sequences. Recent works attempted to utilize recurrent neural networks (RNNs) and long short-term memory (LSTM) networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the 3D skeletal data. As the first work of this thesis, we apply recurrent analysis to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect's skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit's memory cell. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method. In skeleton-based action recognition, not all skeletal joints are informative for activity analysis, and the irrelevant joints often bring noise which can degrade the performance. Therefore, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In our second piece of work, we propose a new class of LSTM network, global context-aware attention LSTM, for skeleton-based action recognition, which is capable of selectively focusing on the

关键词： Computing methodologies image processing and computer vision Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Best and Worst External Viewpoints for Teleoperation Visual Assistance

Best and Worst External Viewpoints for Teleoperation Visual ...

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Shilleh, Mahmood M. Amer, Qusai A. Dufek, Jan Murphy, Robin R. Texas A&M Univ Comp Sci & Engn College Stn TX 77843 USA

ISBN: (纸本)9781450382908

A HRI study with 31 expert robot operators established that an external viewpoint from an assisting robot could increase teleoperation performance by 14% to 58% while reducing human error by 87% to 100% This video illustrates those findings with a side-by-side comparison of the best and worst viewpoints for the passability and traversability affordances. The passability scenario uses a small unmanned aerial system as a visual assistant that can reach any viewpoint on the idealized hemisphere surrounding the task action. The traversability scenario uses a small ground robot that is restricted to a subset of viewpoints that are reachable.

关键词： Robotics User/Machine Systems Distributed Intelligence image processing and computer vision

来源：评论

学校读者我要写书评

暂无评论

RoboCup 2004: Robot Soccer World Cup VIII 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Daniele Nardi Martin Riedmiller Claude Sammut José Santos-Victor

ISBN: (数字)9783540322566

ISBN: (纸本)9783540250463

ThesearetheproceedingsoftheRoboCup2004Symposium,heldattheInstituto Superior T´ ecnico, in Lisbon, Portugal in conjunction with the RoboCup c- petition. The papers presented here document the many innovations in robotics that result from RoboCup. A problem in any branch of science or engineering is how to devise tests that can provide objective comparisons between alt- native methods. In recent years, competitive engineering challenges have been established to motivate researchers to tackle di?cult problems while providing a framework for the comparison of results. RoboCup was one of the ?rst such competitions and has been a model for the organization of challenges foll- ing sound scienti?c principles. In addition to the competition, the associated symposium provides a forum for researchers to present refereed papers. But, for RoboCup, the symposium has the greater goal of encouraging the exchange of ideas between teams so that the competition, as a whole, progresses from year to year and strengthens its contribution to robotics. One hundred and eighteen papers were submitted to the Symposium. Each paper was reviewed by at least two international referees; 30 papers were - cepted for presentation at the Symposium as full papers and a further 38 were accepted for poster presentation. The quality of the Symposium could not be maintained without the support of the authors and the generous assistance of the referees.

关键词： Artificial Intelligence computer Communication Networks Software Engineering User Interfaces and Human computer Interaction image processing and computer vision Control, Robotics, Mechatronics

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：