检索结果-内蒙古大学图书馆

international conference on 3D Imaging, Modeling, processing, Visualization and Transmission (3DIMPVT)

作者： Katja Wolff Changil Kim Henning Zimmer Christopher Schroers Mario Botsch Olga Sorkine-Hornung Alexander Sorkine-Hornung Disney Research Department of Computer Science ETH Zurich Bielefeld University

ISBN: (纸本)9781509054084

Point sets generated by image-based 3D reconstruction techniques are often much noisier than those obtained using active techniques like laser scanning. Therefore, they pose greater challenges to the subsequent surface reconstruction (meshing) stage. We present a simple and effective method for removing noise and outliers from such point sets. Our algorithm uses the input images and corresponding depth maps to remove pixels which are geometrically or photometrically inconsistent with the colored surface implied by the input. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. Our algorithm is efficient, easy to implement, and robust to varying amounts of noise. We demonstrate the benefits of our algorithm in combination with a variety of state-of-the-art depth and surface reconstruction methods.

关键词： Three-dimensional displays Surface reconstruction image reconstruction Noise measurement Surface treatment Robustness Noise reduction

来源：评论

学校读者我要写书评

暂无评论

Autonomous flight and vision-based target tracking for a flapping-wing MAV

Autonomous flight and vision-based target tracking for a fla...

引用

IEEE/RSJ international conference on Intelligent Robots and Systems

作者： Seungwan Ryu Ukjin Kwon H. Jin Kim Department of Mechanical and Aerospace Engineering Seoul National University Korea Department of Electrical and Computer Engineering Seoul National University Korea

ISBN: (纸本)9781509037636

In this paper, we design an autonomous flight controller for height regulation and bang-bang controller for directional control of a light-weight flapping-wing micro air vehicle (FWMAV) with limited payload. We also present autonomous vision-based target tracking for a FWMAV equipped with a low-cost and light-weight first person view (FPV) camera. We construct a ground station, integrated with control and vision algorithms, which performs the image processing and the computation of control inputs based on the acquired state variables from motion capture system. In addition, we employ a vision algorithm for a low-quality camera to detect a static target with the discussions on the techniques to improve the reliability of visual detection. Experimental results show satisfactory flight performance, achieving the height regulation and directional control, and autonomous vision-based target tracking.

关键词： Cameras Target tracking Vehicles Streaming media Actuators Data models Batteries

来源：评论

学校读者我要写书评

暂无评论

Superpixel-based automatic segmentation of villi in confocal endomicroscopy

Superpixel-based automatic segmentation of villi in confocal...

引用

IEEE EMBS international conference on Information Technology Applications in Biomedicine (ITAB)

作者： D. Boschetto H. Mirzaei R. W. L. Leong E. Grisan IMT School for Advanced Studies Lucca 55100 Lucca Italy Gastroenterology and Liver Services The University of New South Wales Sydney Australia Department of Information Engineering University of Padova Padova Italy

Confocal Laser Endomicroscopy (CLE) is a technique permitting on-site microscopy of the gastrointestinal mucosa after the application of a fluorescent agent, allowing the evaluation of mucosa alterations. These are used as features by skilled technicians to stage the severity of multiple diseases, celiac disease or irritable bowel syndrome among the others. We present an automatic method for villi detection from confocal endoscopy images, whose appearance changes with mucosal alterations. Superpixel segmentation, a well-known technique originating from computer vision, is used to identify and cluster together pixels belonging to uniform regions. Each image in the dataset is analyzed in a multiscale fashion (scale 1, 0.5 and 0.25). From each superpixel, 37 features are extracted at multiple image scales. Each superpixel is classified using a random forest, and a post-processing step is performed to refine the final output. Results in the test set (70 images, 30870 superpixels) show 85.87% accuracy, 92.88% sensitivity, 76.99% specificity in the superpixel space, and 86.36% of accuracy and 87.44% Dice score in the pixel domain.

关键词： Feature extraction Junctions Diseases image segmentation Training Tuning computer vision

来源：评论

学校读者我要写书评

暂无评论

A prototype 1024 electrode embedded computer based Epiretinal Prosthesis System

A prototype 1024 electrode embedded computer based Epiretina...

引用

international conference on Signal processing and Integrated Networks (SPIN)

作者： N. Sharmili V. Bhujanga Rao P. Seetharamaiah N. Swapna Dept. of Computer Science and Engg. VIIT Visakhapatnam India Defense R&D Organization DRDO New Delhi India Dept. of Computer Science and Systems Engg. Andhra University Visakhapatnam India Dept. of Computer Science and Engg. RIET Rajahmundry India

ISBN: (纸本)9781467391986

Epiretinal prosthesis is a biomedical implant technology currently being developed around the world in hopes of restoring useful vision for patients suffering from retinal degenerative diseases such as Age-related Macular Degeneration (AMD) and Retinitis Pigmentosa (RP). Epiretinal Prosthesis System (EPS) consists of four parts that includes Body Worn image Processor (BWIP), Retinal Implantable Receiver Stimulator (RIRS), wireless telemetry and electrode array. images are captured by BWIP's camera and encoded into a 1 Mbps bit stream by BWIP. The bit stream is modulated on 8.195 MHz carrier and transmitted serially to RIRS through wireless telemetry. RIRS converts the bit stream into electrical pulses and drives 1024 electrode array to stimulate the survival parts of retina electrically with visual cues for understanding the video picture/image. This paper presents the design of flexible high resolution 1024- electrode embedded computer based EPS using embedded computer based efficient control algorithms for better visual prediction. Finally, the integrity of the EPS has been verified visually through video display on LCD/LED array. The experimental results of EPS are enumerated for the object of human face using 1024-electrode/pixel LED array.

关键词： Prosthetics Electrodes Retina Wireless communication Streaming media Telemetry Radio frequency

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 9th international conference on computer Recognition Systems CORES 2015 1

引用

丛书名： Advances in Intelligent Systems and Computing

2016年

作者： Robert Burduk, Konrad Jackowski, Marek Kurzyński, Michał Woźniak, Andrzej Żołnierek (eds.)

ISBN: (数字)9783319262277

ISBN: (纸本)9783319262253;9783319262277

The computer recognition systems are nowadays one of the most promising directions in artificial intelligence. This book is the most comprehensive study of this field. It contains a collection of 79 carefully selected articles contributed by experts of pattern recognition. It reports on current research with respect to both methodology and applications. In particular, it includes the following sections: Features, learning, and classifiers Biometrics Data Stream Classification and Big Data Analytics image processing and computer vision Medical applications Applications RGB-D perception: recent developments and applications This book is a great reference tool for scientists who deal with the problems of designing computer pattern recognition systems. Its target readers can be the as well researchers as students of computer science, artificial intelligence or robotics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of MVI for fault detection in automated assembly machines

Performance evaluation of MVI for fault detection in automat...

引用

IEEE/ASME (AIM) international conference on Advanced Intelligent Mechatronics

作者： Vedang Chauhan Brian Surgenor Mechanical and Materials Engineering Department Queen's University Kingston On Canada

ISBN: (纸本)9781509020669

Automated assembly machines are designed to be operated round-the-clock to maintain high production rates. Continuous operation of an assembly machine results in wear of its various mechanisms that in turn lead to machine faults and subsequent machine downtime. The goal of this research project is to develop and validate a Machine vision Inspection (MVI) system to detect and classify multiple faults using a single camera as a sensor. The results are experimental in nature, with an industrial O-ring assembly machine used for test purposes. The machine places O-rings on to continuously moving plastic carriers at a rate of over 100 assemblies per minute. The machine is controlled by a PLC with an HMI used to introduce the controlled faults such as transfer track jams, air knife jams, and hopper supply failures. Three MVI methods based on computer vision techniques are developed for this application: 1) Gaussian Mixture Models with blob analysis, 2) optical flow and 3) running average. In order to provide a measure of performance that can be used to better differentiate relative performance, a novel Machine vision Performance Index (MVPI) was developed. The MVPI is based on five measures of performance: accuracy, processing time, speed of response, robustness against noise, and ease of tuning. The MVPI for the three MVI methods is reported and the significance of the results is discussed.

关键词： Fault detection Structural rings Wheels computer vision Cameras Machine vision image motion analysis

来源：评论

学校读者我要写书评

暂无评论

High-fidelity simulation for evaluating robotic vision performance

High-fidelity simulation for evaluating robotic vision perfo...

引用

IEEE/RSJ international conference on Intelligent Robots and Systems

作者： John Skinner Sourav Garg Niko Sunderhauf Peter Corke Ben Upcroft Michael Milford ARC Centre of Excellence for Robotic Vision Queensland University of Technology (QUT) Brisbane Australia

ISBN: (纸本)9781509037636

Robotic vision, unlike computer vision, typically involves processing a stream of images from a camera with time varying pose operating in an environment with time varying lighting conditions and moving objects. Repeating robotic vision experiments under identical conditions is often impossible, making it difficult to compare different algorithms. For machine learning applications a critical bottleneck is the limited amount of real world image data that can be captured and labelled for both training and testing purposes. In this paper we investigate the use of a photo-realistic simulation tool to address these challenges, in three specific domains: robust place recognition, visual SLAM and object recognition. For the first two problems we generate images from a complex 3D environment with systematically varying camera paths, camera viewpoints and lighting conditions. For the first time we are able to systematically characterise the performance of these algorithms as paths and lighting conditions change. In particular, we are able to systematically generate varying camera viewpoint datasets that would be difficult or impossible to generate in the real world. We also compare algorithm results for a camera in a real environment and a simulated camera in a simulation model of that real environment. Finally, for the object recognition domain, we generate labelled image data and characterise the viewpoint dependency of a current convolution neural network in performing object recognition. Together these results provide a multi-domain demonstration of the beneficial properties of using simulation to characterise and analyse a wide range of robotic vision algorithms.

关键词： robot vision Cameras images high fidelity object recognition image data Simulation models Environments simulating Lighting

来源：评论

学校读者我要写书评

暂无评论

Data Association of Aerial Robot Monocular Simultaneous Localization and Mapping

引用

SENSORS AND MATERIALS 2016年第9期28卷 1013-1021页

作者： Wang, Yin-Tien Sun, Chung-Hsun Chen, Ting-Wei Chi, Chen-Tung Tamkang Univ Dept Mech & Electromech Engn 151 Ying Chuan Rd New Taipei 25137 Taiwan Taipei City Univ Sci & Technol Dept Mech Engn 2 Xueyuan Rd Taipei 112 Taiwan

This paper presents an algorithm for data association for the visual navigation of aerial robots. The major objective is to provide the aerial robot with the capabilities of localization and mapping in global positioning system (GPS) denied environments. The visual sensor system could measure information for robot state estimation and environmental mapping as the aerial robot navigates in a GPS-denied environment. Only one single camera was used to reduce the load on the aerial robot. The captured image was transmitted to a personal computer for image processing using a radio frequency transmitter. In this study, an efficient data association method based on fuzzy rules was developed to determine the robust landmarks for robot mapping. An ultrasonic sensor was designed to provide distance measurements and to solve the map scale determination problem of monocular vision. The software program of the robot navigation system was developed on a windows-based personal computer. The navigation system integrated the visual sensor, the algorithm for data association, and the state estimator. The integrated system was used to carry out simultaneous localization and mapping for aerial robots.

关键词： visual simultaneous localization and mapping (vSLAM) image depth parameterization data association map management

来源：评论

学校读者我要写书评

暂无评论

An image matching and object recognition system using webcam robot

An image matching and object recognition system using webcam...

引用

international conference on Parallel Distributed and Grid Computing (PDGC)

作者： Sanjana Yadav Archana Singh Dept.of Computer Science & Engineering Hindustan college of Science & Technology Farah Mathura Dept.of Information Technology Hindustan college of Science & Technology Farah Mathura

ISBN: (纸本)9781509036707

Finding relation among multiple images is a core and vital step in the field of computer vision. This can be achieved if we can track correspondence over consecutive frames in an image and then matching among them can be identified. This paper proposes a precise approach for image matching in real time scenario and also in the field of ROBOTICS. We are constructing an application based image matching model that can detect images that are exactly the same, as well as images that have been edited in some ways. Implementation of this image Matching and object recognition system is based on tracking an object, calculating its feature Points, and classification with the help of trained Data Sets. The system is capable to perform matching of images, both automatically and manually. On the other hand, to operate the proposed system manually, user itself takes the images of an object or something, and will store it in database. After that system will through some steps, and image matching will be performed. Black & White point calculation of an image, Chamfer matching Algorithm, 3-4 Distance Transformation with canny edge detector is applied in the application which is well suited for calculating the pixel values. The whole system is reliable and capable to match the two images in Digital image processing.

关键词： Decision support systems image matching image edge detection Robots Object recognition Databases Webcams

来源：评论

学校读者我要写书评

暂无评论

Regularized 3D Modeling from Noisy Building Reconstructions

Regularized 3D Modeling from Noisy Building Reconstructions

引用

international conference on 3D Imaging, Modeling, processing, Visualization and Transmission (3DIMPVT)

作者： Thomas Holzmann Friedrich Fraundorfer Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology Austria

ISBN: (纸本)9781509054084

In this paper, we present a method for regularizing noisy 3D reconstructions, which is especially well suited for scenes containing planar structures like buildings. At horizontal structures, the input model is divided into slices and for each slice, an inside/outside labeling is computed. With the outlines of each slice labeling, we create an irregularly shaped volumetric cell decomposition of the whole scene. Then, an optimized inside/outside labeling of these cells is computed by solving an energy minimization problem. For the cell labeling optimization we introduce a novel smoothness term, where lines in the images are used to improve the regularization result. We show that our approach can take arbitrary dense meshed point clouds as input and delivers well regularized building models, which can be textured afterwards.

关键词： Three-dimensional displays Labeling image reconstruction Computational modeling Buildings Solid modeling Cameras

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：