检索结果-内蒙古大学图书馆

Plant species identification using discriminant bag of words (DBoW) 15

Plant species identification using discriminant bag of words...

15th international Joint conference on computer vision, Imaging and computer graphics theory and Applications, VISIGRAPP 2020

作者： Murtaza, Fiza Saba, Umber Haroon Yousaf, Muhammad Viriri, Serestina Computer Engineering Department University of Engineering and Technology Taxila Pakistan Swarm Robotics Lab-NCRA University of Engineering and Technology Taxila Pakistan University of KwaZulu-Natal Durban South Africa

ISBN: (纸本)9789897584022

Plant species identification is necessary for protecting biodiversity which is declining rapidly throughout the world. this research work focuses on plant species identification in simple and complex background using computer vision techniques. Intra-class variability and inter-class similarity are the key challenges in a large plant species dataset. In this paper, multiple organs of plants such as leaf, flower, stem, fruit, etc. are classified using hand-crafted features for identification of plant species. We propose a novel encoding scheme named as Discriminant Bag of Words (DBoW) to identify multiple organs of plants. the proposed DBoW extracts the class specific codewords, and assigns the weights to codewords in order to signify discriminant power of the codewords. We evaluated our proposed method on two publicly available datasets: Flavia and ImageClef. the experimental results achieved classification accuracy rates of 98% and 94% on FLAVIA and ImageClef datasets, respectively. Copyright © 2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

Acquisition evaluation on outdoor scanning for archaeological artifact digitalization 15

Acquisition evaluation on outdoor scanning for archaeologica...

引用

15th international Joint conference on computer vision, Imaging and computer graphics theory and Applications, VISIGRAPP 2020

作者： Kusuma Frisky, Aufaclav Zatu Fajri, Adieyatna Brenner, Simon Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered Technology Faculty of Informatics TU Wien Wien Austria Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia Department of Archaeology Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9789897584022

Archaeological archives are important assets because they provide primary information resources for research, mainly digital archives that not degraded. Instead of directly visiting a site, an archaeologist can examine and manipulate the data without harming the real object. However, choosing an efficient scanning scheme with detailed results is a challenging task. In this work, we present new sculpture models obtained in three different ways and assess it in two comparison approaches: A quantitative and qualitative assessment. the quantitative comparison architecture provides a detailed assessment of three different scanning mechanisms in two stages: point cloud and mesh comparison. this evaluation is purposed to describe the differences between unmodified data. Finally, a qualitative evaluation is performed by an expert and practitioner to explain the difference based on four different produced models to help their needs in the real application. Copyright © 2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

Virtual postman - an illustrative example of virtual video

引用

international Journal of Robotics and Automation 2000年第1期15卷 9-16页

作者： Lipton, A.J. Robotics Institute Carnegie Mellon University 5000 Forbes Ave Pittsburgh PA 15213 United States DiamondBack Vision Inc. 2000 N. 15th Street Arlington VA 22201 United States

this paper presents a new paradigm for data interaction called virtual video. the concept is that video streams can be interactively augmented in real-time by both addition and removal of visual information. Removed information must be seamlessly replaced with relevant 'background' information. Added information can be in the form of computer graphics, as in conventional augmented reality, or imagery derived from the video stream itself. Adding video-derived imagery means that a 'real' character can be simulated in different places or times in the video stream, or interacting (fictiously) with other characters. Achieving this requires an understanding of the motion and appearance of the target character so that it can be realistically inserted. Video understanding technology is now sufficiently advanced to make interactive, real-time virtual video a possibility. An example is given in the form a computer game called Virtual Postman in which moving characters detected in a video stream can be 'killed' and thus removed from that stream. Furthermore, characters detected in the video stream are stored, analyzed for rigid or periodic motion and then smoothly re-inserted into the video stream at arbitrary places, times and scales as 'clones' of live characters or 'zombies' of dead ones.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Estimation of Geometric Parameters in 3D Reconstruction Problems Using Linear Matrix Inequalities 7

Estimation of Geometric Parameters in 3D Reconstruction Prob...

引用

Joint 7th international conference on Soft Computing and Intelligent Systems (SCIS) and 15th international Symposium on Advanced Intelligent Systems (ISIS)

作者： Ito, Yoshimichi Irie, Katsumi Otsuka, Shun Osaka Electrocommun Univ Dept Elect & Elect Engn 18-8 Hatsucho Neyagawa Osaka 5728530 Japan

ISBN: (纸本)9781479959556

this paper proposes methods for estimating geometrical parameters, such as coordinate vectors of feature points, camera positions, camera orientations, and so on, in 3D reconstruction problems. In particular, we consider the following two problems: for given camera projection matrices and coordinate vectors of projected feature points on the image planes, find coordinate vectors of feature points;and, for given coordinate vectors of feature points and coordinate vectors of projected feature points on image planes, find camera projection matrices. these problems are formulated as the matrix optimization problem of finding the matrix that minimizes the matrix norm of a certain matrix. the matrix optimization problem is reduced to a convex optimization problem with linear matrix inequalities (LMI), which is widely used in control engineering. the proposed method is evaluated through numerical examples.

关键词： computational geometry computer graphics computer vision estimation theory image sensors linear matrix inequalities 3D reconstruction problems camera orientations camera positions camera projection matrices control engineering coordinate vectors feature points geometric parameter estimation image planes Cameras computer vision Estimation Least squares methods Linear matrix inequalities Optimization Vectors

来源：评论

学校读者我要写书评

暂无评论

Using the Toulmin Model of Argumentation to Explore the Differences in Human and Automated Hiring Decisions 15

Using the Toulmin Model of Argumentation to Explore the Diff...

引用

15th international Joint conference on computer vision, Imaging and computer graphics theory and Applications (VISIGRAPP) / 4th international conference on Human computer Interaction theory and Applications

作者： Bubakr, Hebah Baber, Chris Univ Birmingham Dept Elect Elect & Syst Engn Birmingham W Midlands England

ISBN: (纸本)9789897584022

Amazon developed an experimental hiring tool, using AI to review job applicants' resumes, with the goal of automating the search for the best talent. However, the team found that their software was biased against women because the models were trained on resumes submitted to the company for the previous 10 years and most of these were submitted by men, reflecting male dominance in the tech business. As a result, the models learned that males were preferable, and it excluded resumes that could be inferred to come from female applicants. Gender bias was not the only issue. As well rejecting plausible candidates, problems with the data lead the models to recommend unqualified candidates for jobs. To understand the conflict in this, and similar examples, we apply Toulmin model of argumentation. By considering how arguments are constructed by a human and how a contrasting argument might be constructed by AI, we can conduct pre-mortems of potential conflict in system operation.

关键词： Toulmin Model of Argumentation Artificial Intelligence Human computer Interaction

来源：评论

学校读者我要写书评

暂无评论

Finding thin Points in an Abstract Cellular Complex

Finding Thin Points in an Abstract Cellular Complex

引用

15th international conference in Central Europe on computer graphics, Visualization and computer vision

作者： Ungvichian, Varakorn Kanongchaiyos, Pizzanu Chulalongkorn Univ Dept Comp Engn Bangkok Thailand

ISBN: (纸本)9788086943022

this research describes an algorithm to find "thin points" in a solid represented as an Abstract Cellular Complex. the algorithm is mostly iterative, adding one face at a time to a set of previously selected faces, and choosing the selections that produce the loops with the shortest lengths for the next iteration. the output from the algorithm is a set of loops that indicate the thinnest portions of the solid. As implemented, the algorithm allows a threshold to be set to limit the number of loops that are selected in each iteration. the results indicate that, while it does occasionally produce errors, the algorithm is mostly accurate, and a lower threshold increases its speed, without negatively affecting its accuracy.

关键词： Geometry computer graphics Abstract Cellular Complex topology

来源：评论

学校读者我要写书评

暂无评论

Maintaining Sharp Features in Surface Construction for Volumetric Objects

Maintaining Sharp Features in Surface Construction for Volum...

引用

15th international conference in Central Europe on computer graphics, Visualization and computer vision

作者： Loke, Robert Edward Jansen, Frederik W. IIT CNR Pisa Italy Delft Univ Technol EWI Delft Netherlands

ISBN: (纸本)9788086943022

Discretized Marching Cubes (DMC) is a standard method in computer graphics and visualization for constructing 3D surfaces in data represented on a regular grid. After thresholding, it builds high-resolution surfaces by tiling surface patches halfway between objects and background in the data. this paper shows that if surfaces are built locally, in a high-resolution sub-grid of a cell instead of directly in a cell, sharp surfaces can be generated in order to preserve concave and convex object features. the main advantage is the improved geometric models that are extracted. this makes lower approximation errors and lower triangle counts possible.

关键词： computer graphics: Curve surface solid and object representations computer aided design (modeling of curves and surfaces) Computational geometry Image processing

来源：评论

学校读者我要写书评

暂无评论

Medical computer vision. Recognition Techniques and Applications in Medical Imaging: Second international MICCAI Workshop, MCV 2012, Nice, France, October 5, 2012, Revised Selected Papers 1

引用

丛书名： Lecture Notes in computer Science 7766

2013年

作者： Chen-Rui Chou, Stephen Pizer (auth.), Bjoern H. Menze, Georg Langs, Le Lu, Albert Montillo, Zhuowen Tu, Antonio Criminisi (eds.)

ISBN: (数字)9783642366208

ISBN: (纸本)9783642366192;9783642366208

this book constitutes the thoroughly refereed workshop proceedings of the Second international Workshop on Medical computer vision, MCV 2012, held in Nice, France, October 2012 in conjunction with the 15th international conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2012. the 24 papers have been selected out of 42 submissions. At MCV 2012, 12 papers were presented as a poster and 12 as a poster together with a plenary talk. the book also features four selected papers which were presented at the previous CVPR Medical computer vision workshop held in conjunction with the international conference on computer vision and Pattern Recognition on June 21 2012 in Providence, Rhode Island, USA. the papers explore the use of modern computer vision technology in tasks such as automatic segmentation and registration, localization of anatomical features and detection of anomalies, as well as 3D reconstruction and biophysical model personalization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic image conversion to tactile graphic

Automatic image conversion to tactile graphic

引用

15th international ACM SIGACCESS conference on computers and Accessibility, ASSETS 2013

作者： Ferro, Tyler J. Pawluk, Dianne T.V. Virginia Commonwealth University 401 West Main Street Richmond VA 23284 United States

ISBN: (纸本)9781450324052

Currently, individuals who are blind or visually impaired have limited resources to allow them to interpret information contained in images. the aim of this project is to provide an accessible system to automatically generate tactile graphics for those who need to interpret information contained in visual images. the fundamental steps to accomplish this are to segment and simplify the image. the focus of this paper will be on several methods to segment an image.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

3DSAL: An efficient 3D-CNN architecture for video saliency prediction 15

3DSAL: An efficient 3D-CNN architecture for video saliency p...

引用

15th international Joint conference on computer vision, Imaging and computer graphics theory and Applications, VISIGRAPP 2020

作者： Dahou Djilali, Yasser Abdelaziz Sayah, Mohamed McGuinness, Kevin O’Connor, Noel E. Institut National des Télécommunications et des TIC Oran Algeria Université Oran1 FSEA Oran Algeria Insight Center for Data Analytics Dublin City University Dublin 9 Ireland

ISBN: (纸本)9789897584022

In this paper, we propose a novel 3D CNN architecture that enables us to train an effective video saliency prediction model. the model is designed to capture important motion information using multiple adjacent frames. Our model performs a cubic convolution on a set of consecutive frames to extract spatio-temporal features. this enables us to predict the saliency map for any given frame using past frames. We comprehensively investigate the performance of our model with respect to state-of-the-art video saliency models. Experimental results on three large-scale datasets, DHF1K, UCF-SPORTS and DAVIS, demonstrate the competitiveness of our approach. Copyright © 2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved

关键词： computer vision

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：