检索结果-内蒙古大学图书馆

25th IEEE/RSJ International conference on Intelligent Robots and systems (IROS)

作者： Tankovich, Vladimir Schoenberg, Michael Fanello, Sean Ryan Kowdle, Adarsh Rhemann, Christoph Dzitsiuk, Maksym Schmidt, Mirko Valentin, Julien Izadi, Shahram Google Augmented Percept Grp Mountain View CA 94043 USA

ISBN: (纸本)9781538680940

Depth cameras have accelerated research in many areas of computer vision. Most triangulation-based depth cameras, whether structured light systems like the Kinect or active (assisted) stereo systems, are based on the principle of stereo matching. Depth from stereo is an active research topic dating back 30 years. Despite recent advances, algorithms usually trade-off accuracy for speed. In particular, efficient methods rely on fronto-parallel assumptions to reduce the search space and keep computation low. We present SOS (Slanted O(1) Stereo), the first algorithm capable of leveraging slanted support windows without sacrificing speed or accuracy. We use an active stereo configuration, where an illuminator textures the scene. Under this setting, local methods - such as PatchMatch Stereo - obtain state of the art results by jointly estimating disparities and slant, but at a large computational cost. We observe that these methods typically exploit local smoothness to simplify their initialization strategies. Our key insight is that local smoothness can in fact be used to amortize the computation not only within initialization, but across the entire stereo pipeline. Building on these insights, we propose a novel hierarchical initialization that is able to efficiently perform search over disparity and slants. We then show how this structure can be leveraged to provide high quality depth maps. Extensive quantitative evaluations demonstrate that the proposed technique yields significantly more precise results than current state of the art, but at a fraction of the computational cost. Our prototype implementation runs at 4000 fps on modern GPU architectures.

关键词： Microsoft Windows Cameras image reconstruction Three-dimensional displays Correlation image resolution Optimization

来源：评论

学校读者我要写书评

暂无评论

Robust Feature Descriptors for Object Segmentation Using Active Shape Models 19th

Robust Feature Descriptors for Object Segmentation Using Act...

引用

19th International conference on Advanced Concepts for Intelligent Vision systems (ACIVS)

作者： Medley, Daniela Santiago, Carlos Nascimento, Jacinto C. Inst Super Tecn Inst Syst & Robot Lisbon Portugal

ISBN: (纸本)9783030014490;9783030014483

Object segmentation is still an active topic that is highly visited in image processing and computer vision communities. This task is challenging due not only to difficult image conditions (e.g., poor resolution or contrast), but also to objects whose appearance vary significantly. This paper visits the Active Shape Model (ASM) that has become a widely used deformable model for object segmentation in images. Since the success of this model depends on its ability to locate the object, many detectors have been proposed. Here, we propose a new methodology in which the ASM search takes the form of local rectangular regions sampled around each landmark point. These regions are then correlated to variable or fixed texture templates learned over a training set. We compare the performance of the proposed approach against other detectors based on: (i) the classical ASM edge detection;(ii) the Histogram of Oriented Gradients (HOG);and (iii) the Scale-Invariant Feature Transform (SIFT). The evaluation is performed in two different applications: facial fitting and segmentation of the left ventricle (LV) in cardiac magnetic resonance (CMR) images, showing that the proposed method leads to a significant increase in accuracy and outperforms the other approaches.

关键词： Active shape models image segmentation Texture regions Histogram of oriented gradients Scale-invariant feature transform

来源：评论

学校读者我要写书评

暂无评论

BlueEyes – Easing the navigation and orientation of blind people 12

BlueEyes – Easing the navigation and orientation of blind p...

引用

12th International conference on Interfaces and Human Computer Interaction 2018, 11th International conference on Game and Entertainment Technologies 2018 and 12th International conference on Computer Graphics, Visualization, Computer Vision and image processing 2018, part of the Multi conference on Computer Science and Information systems 2018, MCCSIS 2018

作者： Silva, Marta Gomes, Anabela Teixeira, Ana Rita Orvalho, João Coimbra Education School Polytechnic of Coimbra Rua Dom João III – Solum Coimbra3030-329 Portugal

ISBN: (纸本)9789898533791

As reported by the World Health Organization (WHO), of the 7 billion people alive today, an estimated 253 million live with visual impairment that cannot be corrected with glasses or contact lenses. From these, 30 million blind or partially sighted persons live in Europe. Over the past years, blindness that is caused by diseases has decreased due to the success of public health actions. However, the number of blind people that are over 60 years old is increasing by 2 million per decade. Unfortunately, all these numbers are estimated to be doubled by 2020. With these facts, is necessary to bring awareness and understanding of the challenges blind people face and help to motivate research into new technology to answer those questions. This document starts to identify the challenges people with visual disabilities face in their life. The problem of navigation and orientation as well the different possibilities to deal with the locomotion situation is also addressed in this paper. It describes the traditional navigational solutions as well other which involves more sophisticated technological devices and their multimodal interfaces. The paper ends with the description of the BlueEyes project (Orvalho, 2016), consisting in a solution to help blind people moving in a city. The first phases of the project are described, and the actual research situations is also slightly explained. © 2018.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

ULBP-RF: A Hybrid Approach for Malware image Classification 5

ULBP-RF: A Hybrid Approach for Malware Image Classification

引用

5th IEEE International conference on Parallel, Distributed and Grid Computing (PDGC)

作者： Gupta, Shakshi Bansal, Priti Kumar, Sumit Netaji Subhas Inst Technol Dept IT New Delhi India KIET Grp Inst Dept IT Ghaziabad India

ISBN: (纸本)9781728106465

The growing dependence on internet for performing critical activities in every domain has raised serious concerns about the security of the computer systems. Maiwares have become a significant threat to computer systems and recently, a massive growth has been observed by experts in the number and sophistication of new malwares. Therefore, the task of malware detection and classification is of utmost importance. However, the task of classifying malwares has become more challenging since the introduction of code obfuscation and metamorphism techniques. These techniques easily alter the malwares' code signatures and make the static techniques of malware detection ineffective. Dynamic analysis is effective but time-consuming. Recently, image processing techniques along with machine learning techniques have been explored by researchers for visualization and classification of malwares. In this paper, we introduce a new approach ULBP-RF that uses Uniform local binary pattern with circular neighborhood strategy to extract features from the malware images dataset. The resulting datasets are classified using Random Forest. To assess the performance of the proposed approach, experiments are performed and a comparative analysis of the performance of various combinations of feature extraction techniques and classification algorithms is done. It has been found that ULBP-RF has the highest classification accuracy.

关键词： Malware Uniform Local Binary Pattern feature extraction Classification

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation

Fast and Accurate Semantic Mapping through Geometric-based I...

引用

25th IEEE/RSJ International conference on Intelligent Robots and systems (IROS)

作者： Nakajima, Yoshikatsu Tateno, Keisuke Tombari, Federico Saito, Hideo Keio Univ Dept Sci & Technol Yokohama Kanagawa Japan Tech Univ Munich Chair Comp Aided Med Procedures CAMP Boltzmannstr 3 D-85748 Munich Germany

ISBN: (纸本)9781538680940

We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time. The proposed method assigns class probabilities to each region, not each element (e.g., surfel and voxel), of the 3D map which is built up through a robust SLAM framework and incrementally segmented with a geometric-based segmentation method. Differently from all other approaches, our method has a capability of running at over 30Hz while performing all processing components, including SLAM, segmentation, 2D recognition, and updating class probabilities of each segmentation label at every incoming frame, thanks to the high efficiency that characterizes the computationally intensive stages of our framework. By utilizing a specifically designed CNN to improve the frame-wise segmentation result, we can also achieve high accuracy. We validate our method on the NYUv2 dataset by comparing with the state of the art in terms of accuracy and computational efficiency, and by means of an analysis in terms of time and space complexity.

关键词： Semantics Three-dimensional displays image segmentation Simultaneous localization and mapping Cameras Real-time systems Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Bulk reprocessing of the ALOS PRISM/AVNIR-2 archive of the European Space Agency: Level 1 Orthorectified Data processing and Data Quality Evaluation 24

Bulk reprocessing of the ALOS PRISM/AVNIR-2 archive of the E...

引用

conference on image and Signal processing for Remote Sensing XXIV

作者： Saunier, Sebastien Mannan, Rubinder Schwind, Peter Mueller, Rupert Storch, Tobias Biasutti, Roberto Gascon, Ferran Goryl, Philippe Meloni, Marco Telespazio VEGA UK Ltd IDEAS Luton Beds England DLR IDEAS Munchener Str 20 D-82234 Wessling Germany ESA Earth Observat Programme ESRIN Via Galileo Galilei Frascati Italy Serco DSI Via Sciadonna 24 I-00044 Frascati Italy

ISBN: (纸本)9781510621626

The Advanced Land Observing Satellite (ALOS) was launched on January 24, 2006, by a Japan Aerospace Exploration Agency (JAXA) H-IIA launcher. It carries three remote sensing sensors: the Advanced Visible and Near Infrared Radiometer type 2 (AVNIR-2), the Panchromatic Remote-sensing Instrument for Stereo Mapping (PRISM), and the Phased Array type L-band Synthetic Aperture Radar (PALSAR). Within the framework of ALOS Data European Node (ADEN), as part of the European Space Agency (ESA), has collected 5 years of data observed in Arctic, in Europe and in Africa through the ground stations of Tromsoe (Norway) and Matera (Italy). Some data has been repatriated directly from JAXA from the on-board recorder (in particular over Africa, outside the visibility of the stations). The data were available to the scientific users via on-request ordering from the stations through the ESA ordering system. In ordering to provide a better and easier access to the data in the framework of the ESA Third Party Missions, in 2015 ESA started a project aimed to repatriate the data from the stations, consolidate them, harmonise the format to the ESA standards. For the PALSAR data, view the different processing levels available to the users, ESA decided to setup a dissemination system, able to process automatically at the user demand the data to the requested level (on-the-fly processing). For the optical data, instead, the decision was to systematically process the PRISM and AVNIR-2 as orthorectified products (so to a higher level in respect of what available before) with a systematic quality control. This paper presents the functionalities of the new Level 1 orthorectified products and details the block adjustment algorithms used for refinement of geometric accuracy. A specific quality control strategy has been laid down in order to re analyse the entire archive. Also, validation methods are explained and the final product accuracy specification are given. http://***/conferences-and-exh

关键词： Data archive systems image processing image quality Sensors Modulation transfer functions Data acquisition Clouds Data modeling Deconvolution

来源：评论

学校读者我要写书评

暂无评论

Improved ORB Algorithm Based on Binocular Vision

Improved ORB Algorithm Based on Binocular Vision

引用

IEEE International conference on Computer and Communications

作者： Chao Li Yongxing Jia Huali Wang Chuanzhen Rong Ying Zhu Coege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLA

ISBN: (数字)9781728147437

ISBN: (纸本)9781728147444

In digital image processing, feature extraction is a very important step, and ORB algorithm is the best one in realtime performance, but it is not up to the standard in the system with higher real-time requirements. Through binocular vision calibration, we will delve into how to speed up the operation of ORB algorithm with ensuring accuracy. First, the overlapping regions of the left and right images are extracted, and then the images are subjected to morphological operations, and corner detection is performed at the edges. Secondly, the original description method is improved, and the description sub-selects the window value based on the area ring, which is more in line with the characteristics of the human eye and improves the operation speed. Then, a hierarchical matching strategy is adopted, combined with binocular visual constraints, the matching range is defined, and the accuracy is effectively improved. Finally, construct an experimental platform to process two images and compare them with existing algorithms. The experimental results show that the proposed method has much less computational time consumption than the original algorithm under the condition of improved accuracy, and is suitable for fast matching environment.

关键词： Feature extraction image edge detection Real-time systems Calibration Cameras Morphological operations Robustness

来源：评论

学校读者我要写书评

暂无评论

Predicting First-Episode Psychosis Associated with Cannabis Use with Artificial Neural Networks and Deep Learning 17th

Predicting First-Episode Psychosis Associated with Cannabis ...

引用

17th International conference on Information processing and Management of Uncertainty in Knowledge-Based systems (IPMU)

作者： Stamate, Daniel Alghamdi, Wajdi Stahl, Daniel Pu, Ida Murtagh, Fionn Belgrave, Danielle Murray, Robin di Forti, Marta Goldsmiths Univ London Data Sci & Soft Comp Lab London England Goldsmiths Univ London Dept Comp London England Kings Coll London Inst Psychiat Psychol & Neurosci Dept Biostat & Hlth Informat London England Univ Huddersfield Sch Comp & Engn Huddersfield W Yorkshire England Microsoft Res Cambridge Cambridge England Kings Coll London Inst Psychiat Psychol & Neurosci Dept Psychosis Studies London England Kings Coll London Inst Psychiat Psychol & Neurosci MRC Social Genet & Dev Psychiat Ctr London England

ISBN: (纸本)9783319914794;9783319914787

In recent years, a number of researches started to investigate the existence of links between cannabis use and psychotic disorder. More recently, artificial neural networks and in particular deep learning have set a revolutionary wave in pattern recognition and machine learning. This study proposes a novel machine learning approach based on neural network and deep learning algorithms, to developing highly accurate predictive models for the onset of first-episode psychosis. Our approach is based also on a novel methodology of optimising and post-processing the predictive models in a computationally intensive framework. A study of the trade-off between the volume of the data and the extent of uncertainty due to missing values, both of which influencing the predictive performance, enhanced this approach. Furthermore, we extended our approach by proposing and encapsulating a novel post-processing k-fold cross-testing method in order to further optimise, and test these models. The results show that the average accuracy in predicting first-episode psychosis achieved by our models in intensive Monte Carlo simulation, is about 89%.

关键词： First-episode psychosis Precision medicine Cannabis use Classification Neural network Deep learning Monte Carlo simulation Missing data based uncertainty Prediction modelling Post-processing

来源：评论

学校读者我要写书评

暂无评论

Optimizing GPU-Based Connected Components Labeling algorithms

Optimizing GPU-Based Connected Components Labeling Algorithm...

引用

International image processing, Applications and systems conference (IPAS)

作者： Stefano Allegretti Federico Bolelli Michele Cancilla Costantino Grana Università degli Studi di Modena e Reggio Emilia

ISBN: (纸本)9781728102481;9781728102474

Connected Components Labeling (CCL) is a fundamental image processing technique, widely used in various application areas. Computational throughput of Graphical processing Units (GPUs) makes them eligible for such a kind of algorithms. In the last decade, many approaches to compute CCL on GPUs have been proposed. Unfortunately, most of them have focused on 4-way connectivity neglecting the importance of 8-way connectivity. This paper aims to extend state-of-the-art GPU-based algorithms from 4 to 8-way connectivity and to improve them with additional optimizations. Experimental results revealed the effectiveness of the proposed strategies.

关键词： Kernel Indexes Labeling Vegetation image processing Graphics processing units Arrays

来源：评论

学校读者我要写书评

暂无评论

Global rigid registration of CT to video in laparoscopic liver surgery

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2018年第6期13卷 947-956页

作者： Robu, Maria R. Ramalhinho, Joao Thompson, Stephen Gurusamy, Kurinchi Davidson, Brian Hawkes, David Stoyanov, Danail Clarkson, Matthew J. UCL Wellcome EPSRC Ctr Intervent & Surg Sci London England UCL Ctr Med Image Comp London England UCL Div Surg & Intervent Sci London England

image-guidance systems have the potential to aid in laparoscopic interventions by providing sub-surface structure information and tumour localisation. The registration of a preoperative 3D image with the intraoperative laparoscopic video feed is an important component of image guidance, which should be fast, robust and cause minimal disruption to the surgical procedure. Most methods for rigid and non-rigid registration require a good initial alignment. However, in most research systems for abdominal surgery, the user has to manually rotate and translate the models, which is usually difficult to perform quickly and intuitively. We propose a fast, global method for the initial rigid alignment between a 3D mesh derived from a preoperative CT of the liver and a surface reconstruction of the intraoperative scene. We formulate the shape matching problem as a quadratic assignment problem which minimises the dissimilarity between feature descriptors while enforcing geometrical consistency between all the feature points. We incorporate a novel constraint based on the liver contours which deals specifically with the challenges introduced by laparoscopic data. We validate our proposed method on synthetic data, on a liver phantom and on retrospective clinical data acquired during a laparoscopic liver resection. We show robustness over reduced partial size and increasing levels of deformation. Our results on the phantom and on the real data show good initial alignment, which can successfully converge to the correct position using fine alignment techniques. Furthermore, since we can pre-process the CT scan before surgery, the proposed method runs faster than current algorithms. The proposed shape matching method can provide a fast, global initial registration, which can be further refined by fine alignment methods. This approach will lead to a more usable and intuitive image-guidance system for laparoscopic liver surgery.

关键词： image guidance Laparoscopic liver surgery Global registration Shape matching Surface descriptors Computer-assisted surgery

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：