检索结果-内蒙古大学图书馆

Conference on Medical Imaging - Physics of Medical Imaging

作者： Schmidt, Taly Gilat Wang, Adam Coradi, Thomas Haas, Benjamin Star-Lack, Josh Marquette Univ Dept Biomed Engn Milwaukee WI 53233 USA Varian Med Syst Palo Alto CA USA

ISBN: (纸本)9781510600188

The overall goal of this work is to develop a rapid, accurate and fully automated software tool to estimate patient-specific organ doses from computed tomography (CT) scans using a deterministic Boltzmann Transport Equation solver and automated CT segmentation algorithms. This work quantified the accuracy of organ dose estimates obtained by an automated segmentation algorithm. The investigated algorithm uses a combination of feature-based and atlas-based methods. A multi atlas approach was also investigated. We hypothesize that the autosegmentation algorithm is sufficiently accurate to provide organ dose estimates since random errors at the organ boundaries will average out when computing the total organ dose. To test this hypothesis, twenty head-neck CT scans were expertly segmented into nine regions. A leave-one-out validation study was performed, where every case was automatically segmented with each of the remaining cases used as the expert atlas, resulting in nineteen automated segmentations for each of the twenty datasets. The segmented regions were applied to gold-standard Monte Carlo dose maps to estimate mean and peak organ doses. The results demonstrated that the fully automated segmentation algorithm estimated the mean organ dose to within 10% of the expert segmentation for regions other than the spinal canal, with median error for each organ region below 2%. In the spinal canal region, the median error was 7% across all data sets and atlases, with a maximum error of 20%. The error in peak organ dose was below 10% for all regions, with a median error below 4% for all organ regions. The multiple-case atlas reduced the variation in the dose estimates and additional improvements may be possible with more robust multi-atlas approaches. Overall, the results support potential feasibility of an automated segmentation algorithm to provide accurate organ dose estimates.

关键词： image segmentation Computed tomography Monte Carlo methods Algorithm development image processing algorithms and systems Ions Lung Brain Radiation dosimetry Software development

来源：评论

学校读者我要写书评

暂无评论

SINGLE-image SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS 23

SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSI...

引用

23rd Congress of the International-Society-for-Photogrammetry-and-Remote-Sensing (ISPRS)

作者： Liebel, L. Koerner, M. Tech Univ Munich Comp Vis Res Grp Remote Sensing Technol Arcisstr 21 D-80333 Munich Germany

In optical remote sensing, spatial resolution of images is crucial for numerous applications. Space-borne systems are most likely to be affected by a lack of spatial resolution, due to their natural disadvantage of a large distance between the sensor and the sensed object. Thus, methods for single-image super resolution are desirable to exceed the limits of the sensor. Apart from assisting visual inspection of datasets, post-processing operations-e.g., segmentation or feature extraction-can benefit from detailed and distinguishable structures. In this paper, we show that recently introduced state-of-the-art approaches for single-image super resolution of conventional photographs, making use of deep learning techniques, such as convolutional neural networks (CNN), can successfully be applied to remote sensing data. With a huge amount of training data available, end-to-end learning is reasonably easy to apply and can achieve results unattainable using conventional handcrafted algorithms. We trained our CNN on a specifically designed, domain-specific dataset, in order to take into account the special characteristics of multispectral remote sensing data. This dataset consists of publicly available SENTINEL-2 images featuring 13 spectral bands, a ground resolution of up to 10m, and a high radiometric resolution and thus satisfying our requirements in terms of quality and quantity. In experiments, we obtained results superior compared to competing approaches trained on generic image sets, which failed to reasonably scale satellite images with a high radiometric resolution, as well as conventional interpolation methods.

关键词： Single-image Super Resolution Deep Learning Convolutional Neural Networks Sentinel-2

来源：评论

学校读者我要写书评

暂无评论

NASA Technical Reports Server (Ntrs) 19820014683: Multiresource Analysis and Information System Concepts for Incorporating Landsat and Gis Technology Into Large Area Forest Surveys. [south Carolina

引用

2016年

NASA Technical Reports Server (Ntrs) 19820014683: Multiresource Analysis and Information System Concepts for Incorporating Landsat and Gis Technology Into Large Area Forest Surveys. [south Carolina by NASA Technical R... 详细信息

关键词： (ntrs) [south 19820014683: aerial photography algorithms analysis carolina classifications data correlation earth resources program forests ground truth image processing information systems land use langley, p. g. matrices (mathematics) nasa technical reports server (ntrs) regression analysis satellite observation sediment transport thematic mapping transformations (mathematics)

来源：评论

学校读者我要写书评

暂无评论

FREQUENCY-MODULATED CONTINUOUS-WAVE SYNTHETIC-APERTURE RADAR: IMPROVEMENTS IN SIGNAL processing

FREQUENCY-MODULATED CONTINUOUS-WAVE SYNTHETIC-APERTURE RADAR...

引用

作者： Yake Li Memorial University of Newfoundland

学位级别：博士

With the advance of solid state devices, frequency-modulated continuous-wave (FMCW) designs have recently been used in synthetic-aperture radar (SAR) to decrease cost, size, weight and power consumption, making it deployable on smaller mobile plat- forms, including small (< 25 kg) unmanned aerial vehicle(s) (UAV). To foster its mobile uses, several SAR capabilities were studied: moving target indication (MTI) for increased situational awareness, bistatic operation, e. g. in UAV formation flights, for increased range, and signal processing algorithms for faster real-time performance. Most off-the-shelf SAR systems for small mobile platforms are commercial proprie- tary and/or military (ITAR, International Trades in Arms Regulations) restricted. As such, it necessitated the design and build of a prototype FMCW SAR system at the early stage to serve as a research tool. This enabled unrestricted hardware and software modifica- tions and experimentation. A model to analyze the triangularly modulated (TM) linear frequency modulated (LFM) waveform as one signal was established and used to develop a MTI algorithm which is effective for slow moving targets detection. Experimental field data collected by the prototyped FMCW SAR was then used to validate and demonstrate the effectiveness of the proposed MTI method. A bistatic FMCW SAR model was next introduced: Bistatic configuration is a poten- tial technique to overcome the power leakage problem in monostatic FMCW SAR. By mounting the transmitter and receiver on spatially separate mobile (UAV) platforms in formation deployment, the operation range of a bistatic FMCW SAR can be significantly improved. The proposed approximation algorithm established a signal model for bistatic FMCW SAR by using the Fresnel approximation. This model allows the existing signal processing algorithms to be used in bistatic FMCW SAR image generation without sig- nificant modification simplifying bistatic FMCW SAR signal processing. The proposed ra

关键词： Synthetic aperture radar Frequency modulated continuous wave FMCW SAR system Range migration algorithm

来源：评论

学校读者我要写书评

暂无评论

NASA Technical Reports Server (Ntrs) 20150002127: Vision Algorithm for the Solar Aspect System of the High Energy Replicated Optics to Explore the Sun Mission

引用

2016年

NASA Technical Reports Server (Ntrs) 20150002127: Vision Algorithm for the Solar Aspect System of the High Energy Replicated Optics to Explore the Sun Mission by NASA Technical Reports Server (Ntrs); NASA Technical Re... 详细信息

关键词： (ntrs) 20150002127: algorithm algorithms applications programs (computers) aspect cameras circles (geometry) computer vision cramer, alexander krishnan detection energy error analysis high altitude balloons image processing markers matched filters nasa technical reports server (ntrs) optical tracking pattern registration payloads pitch (inclination) pixels pointing control systems solar observatories solar sensors space detection and tracking system spacing yaw

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Relocalization for Keyframe-Based SLAM Using Geometric Model Selection 18

Fast and Accurate Relocalization for Keyframe-Based SLAM Usi...

引用

IEEE Virtual Reality Conference (IEEE VR)

作者： Moteki, Atsunori Yamaguchi, Nobuyasu Karasudani, Ayu Yoshitake, Toshiyuki Fujitsu Labs Ltd Kawasaki Kanagawa Japan

ISBN: (纸本)9781509008360

In this paper, we propose a relocalization method for keyframe-based SLAM that enables real-time and accurate recovery from tracking failures. To realize an AR-based application in a real world situation, not only accurate camera tracking but also fast and accurate relocalization from tracking failure is required. The previous keyframe-based relocalization methods have some drawbacks with regard to speed and accuracy. The proposed relocalization method selects two algorithms adaptively depending on the relative camera pose between a current frame and a target keyframe. In addition, it estimates a degree of false matches to speed up RANSAC-based model estimation. We present effectiveness of our method by an evaluation using public tracking dataset.

关键词： H.5.1 [Information Interfaces and Presentation]: Multimedia Information systems-Artificial, augmented and virtual realities I.4.8 [image processing and Computer Vision]: Scene Analysis-Tracking

来源：评论

学校读者我要写书评

暂无评论

Improving Real-World Performance of Vision Aided Navigation in a Flight Environment

Improving Real-World Performance of Vision Aided Navigation ...

引用

作者： Donald T. Venable Air Force Institute of Technology

学位级别：博士

The advent of the Global Positioning System has redefined the role of navigation for both commercial and military consumers. Current civil and military applications depend heavily on the Global Positioning System, and the realization of this depen- dence has caused application designers to seek alternatives and backups for situations where GPS is unavailable. One category of alternatives seeks to find cost-e? ective alternatives for military systems by leveraging information from non-navigation sen- sors that are already deployed on fielded platforms. The motivation of this research is to fuse information from an airborne imaging sensor with information extracted from satellite imagery in order to provide accurate global position in scenarios where GPS is unavailable for an extend duration. The research outlines the architecture for an image Positioning System, composing of three elements: a position acquisition algorithm, a fine-tracking algorithm, and a database of image keypoints that supports both estimation components. This research provides a description of the image pro- cessing pipeline, where multiple types of point features are extracted from imagery. These keypoints are computed from a corpus of existing georeferenced satellite and airborne imagery to create a keypoint database. An o? ine algorithm utilizes the database in order to predict which keypoints will be most useful during the online navigation algorithms. The first step in the online portion of the airborne image po- sitioning system is to recover coarse position when faced with a large initial position uncertainty. This research details a novel algorithm for recovering coarse pose using by comparing keypoints extracted from the airborne imagery to the reference database. This coarse position is used to bootstrap a local-area georegistration algorithm, which provides GPS-level position estimates. This research derives optimizations for exist- ing local-area methods for operation in flight enviro

关键词： Navigation image processing Computer Vision image Georegistration

来源：评论

学校读者我要写书评

暂无评论

A comparison of cost construction methods onto a C6678 platform for stereo matching

A comparison of cost construction methods onto a C6678 platf...

引用

Conference on Design and Architectures for Signal and image processing

作者： Judicaël Menant Guillaume Gautier Jean-François Nezan Muriel Pressigout Luce Morin IETR / INSA Rennes

Stereo matching techniques aim at reconstructing depth information from a pair of images. The use of stereo matching algorithms in embedded systems is very challenging due to the complexity of state-of-the-art algorithms. Most stereo matching algorithms are made of three different parts; the cost construction, the cost aggregation and the disparity selection. This paper focuses on comparing the efficiency of different cost construction methods implemented on a Digital Signal Processor (DSP) C6678 platform. Three cost construction algorithms based on census, Sum of Absolute Differences (SAD) and Mutual Information (MI) have been compared in terms of output quality and execution time. Each method has its own specificity discussed in this paper. The SAD is the simplest one and is used as reference in this paper. The census has a good output quality, and the MI is faster.

关键词： Signal processing algorithms Digital signal processing Embedded systems Table lookup Mutual information Stereo image processing VLIW

来源：评论

学校读者我要写书评

暂无评论

Ensemble based classifiers using dictionary learning

Ensemble based classifiers using dictionary learning

引用

International Conference on systems, Signals and image processing, IWSSIP

作者： Goksu Tuysuzoglu Nazanin Moarref Yusuf Yaslan Computer Engineering Department Istanbul Technical University Turkey

Dictionary learning is used in signal, image, audio and video processing applications to represent signals by a sparse set of atoms where sparse representations are managed for the problems of compression, denoising, feature extraction and data classification. In many machine learning applications, classifier ensembles are shown to be superior than their single classifier counterparts. In this paper, we propose to use dictionary learning as a base classifier in ensemble learning methods and introduce Random Subspace Dictionary Learning (RDL) and Bagging Dictionary Learning (BDL) algorithms by learning ensembles of dictionaries for each class using feature/instance subspaces. The experimental results show that the ensemble based dictionary learning methods outperform the single dictionary learning (DL), Support Vector Machines (SVM), and SVM based ensemble classifiers.

关键词： Dictionaries Support vector machines Training Bagging Classification algorithms Learning systems image processing

来源：评论

学校读者我要写书评

暂无评论

CAMA: Contact-Aware Matrix Assembly with Unified Collision Handling for GPU-based Cloth Simulation

引用

COMPUTER GRAPHICS FORUM 2016年第2期35卷 511-521页

作者： Tang, Min Wang, Huamin Tang, Le Tong, Ruofeng Manocha, Dinesh Zhejiang Univ Hangzhou Zhejiang Peoples R China Univ N Carolina Chapel Hill NC 27515 USA Ohio State Univ Columbus OH 43210 USA

We present a novel GPU-based approach to robustly and efficiently simulate high-resolution and complexly layered cloth. The key component of our formulation is a parallelized matrix assembly algorithm that can quickly build a large and sparse matrix in a compressed format and accurately solve linear systems on GPUs. We also present a fast and integrated solution for parallel collision handling, including collision detection and response computations, which utilizes spatio-temporal coherence. We combine these algorithms as part of a new cloth simulation pipeline that incorporates contact forces into implicit time integration for collision avoidance. The entire pipeline is implemented on GPUs, and we evaluate its performance on complex benchmarks consisting of 100 - 300K triangles. In practice, our system takes a few seconds to simulate one frame of a complex cloth scene, which represents significant speedups over prior CPU and GPU-based cloth simulation systems.

关键词： Graphics processing units (Computers) Computer graphics Computer art Digital image processing Graphic arts

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：