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： Reza, Md. Alimoor David, Philip Kosecka, Jana George Mason Univ Dept Comp Sci Fairfax VA 22030 USA US Army Res Lab Adelphi MD USA

ISBN: (纸本)9781538680940

This paper introduces the problem of long-range monocular depth estimation for outdoor urban environments. Range sensors and traditional depth estimation algorithms (both stereo and single view) predict depth for distances of less than 100 meters in outdoor settings and 10 meters in indoor settings. The shortcomings of outdoor single view methods that use learning approaches are, to some extent, due to the lack of long-range ground truth training data, which in turn is due to limitations of range sensors. To circumvent this, we first propose a novel strategy for generating synthetic long-range ground truth depth data. We utilize Google Earth images to reconstruct large-scale 3D models of different cities with proper scale. The acquired repository of 3D models and associated RGB views along with their long-range depth renderings are used as training data for depth prediction. We then train two deep neural network models for long-range depth estimation: i) a Convolutional Neural Network (CNN) and ii) a Generative Adversarial Network (GAN). We found in our experiments that the GAN model predicts depth more accurately. We plan to open-source the database and the baseline models for public use.

关键词： Three-dimensional displays Solid modeling Estimation image reconstruction Urban areas Google Meters

来源：评论

学校读者我要写书评

暂无评论

Classification of Hanging Garments Using Learned Features Extracted from 3D Point Clouds

Classification of Hanging Garments Using Learned Features Ex...

引用

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

作者： Stria, Jan Hlavac, Vaclav Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague Czech Republic

ISBN: (纸本)9781538680940

The presented work deals with classification of garment categories including pants, shorts, shirts, T-shirts and towels. The knowledge of the garment category is crucial for its robotic manipulation. Our work focuses particularly on garments being held in a hanging state by a robotic arm. The input of our method is a set of depth maps taken from different viewpoints around the garment. The depths are fused into a single 3D point cloud. The cloud is fed into a convolutional neural network that transforms it into a single global feature vector. The network utilizes a generalized convolution operation defined over the local neighborhood of a point. It can deal with permutations of the input points. It was trained on a large dataset of common 3D objects. The extracted feature vector is classified with SVM trained on smaller datasets of garments. The proposed method was evaluated on publicly available data and compared to the original methods, achieving competitive performance and better generalization capability.

关键词： Clothing Three-dimensional displays Feature extraction Robot sensing systems Convolution image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Full-View 3D Imaging System for Functional and Anatomical Screening of the Breast

Full-View 3D Imaging System for Functional and Anatomical Sc...

引用

conference on Photons Plus Ultrasound - Imaging and Sensing

作者： Oraevsky, Alexander Su, Richard Nguyen, Ha Moore, James Lou, Yang Bhadra, Sayantan Forte, Luca Anastasio, Mark Yang, Wei TomoWave Labs 6550 Mapleridge St Ste 103-124 Houston TX 77081 USA Washington Univ 1 Brookings Dr Box 1097 St Louis MO 63130 USA Univ Texas MD Anderson Canc Ctr 1515 Holcombe Blvd Houston TX 77030 USA

ISBN: (数字)9781510614741

ISBN: (纸本)9781510614741

Laser Optoacoustic Ultrasonic Imaging System Assembly (LOUISA-3D) was developed in response to demand of diagnostic radiologists for an advanced screening system for the breast to improve on low sensitivity of x-ray based modalities of mammography and tomosynthesis in the dense and heterogeneous breast and low specificity magnetic resonance imaging. It is our working hypothesis that co-registration of quantitatively accurate functional images of the breast vasculature and microvasculature, and anatomical images of breast morphological structures will provide a clinically viable solution for the breast cancer care. Functional imaging is LOUISA-3D is enabled by the full view 3D optoacoustic images acquired at two rapidly toggling laser wavelengths in the near-infrared spectral range. 3D images of the breast anatomical background is enabled in LOUISA-3D by a sequence of B-mode ultrasound slices acquired with a transducer array rotating around the breast. This creates the possibility to visualize distributions of the total hemoglobin and blood oxygen saturation within specific morphological structures such as tumor angiogenesis microvasculature and larger vasculature in proximity of the tumor. The system has four major components: (i) a pulsed dual wavelength laser with fiberoptic light delivery system, (ii) an imaging module with two arc shaped probes (optoacoustic and ultrasonic) placed in a transparent bowl that rotates around the breast, (iii) a multichannel electronic system with analog preamplifiers and digital data acquisition boards, and (iv) computer for the system control, data processing and image reconstruction. The most important advancement of this latest system design compared with previously reported systems is the full breast illumination accomplished for each rotational step of the optoacoustic transducer array using fiberoptic illuminator rotating around the breast independently from rotation of the detector probe. We report here a pilot case studies

关键词： optoacoustic ultrasound image co-registration functional imaging breast cancer tumor microvasculature ultrawide-band ultrasonic transducer

来源：评论

学校读者我要写书评

暂无评论

Notice of Violation of IEEE Publication Principles: Radio Interferometric image reconstruction Algorithm Based on Primal Dual

Notice of Violation of IEEE Publication Principles: Radio In...

引用

International conference on Communication Software and Networks, ICCSN

作者： Bao-qiang Lao Tao An Shanghai Astronomical Observatory Chinese Academy of Sciences Nandan Road 80 Shanghai China

Notice of Violation of IEEE Publication Principles "Radio Interferometric image reconstruction Algorithm Based on Primal Dual" by Bao-qiang Lao and Tao An in the Proceedings of the 10th International conference on Communications Software and Networks, October 2018, pp.405-410 After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles. This paper duplicated content from the paper cited below. The original content was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission. "Scalable Splitting Algorithms for Big-data Interferometric Imaging in the SKA Era" by Alexandru Onose, Rafael E. Carrillo, Audrey Repetti, Jason D. McEwen, Jean-Philippe Thiran, Jean-Christophe Pesquet and Yves Wiaux in Monthly Notices of the Royal Astronomical Society (MNRAS), September 2016, pp. 4314-4335 The last-standing ill-posed inverse problem of radio interferometric imaging is analyzed. A new convex optimization algorithm, Primal Dual, is applied to radio interferometric imaging to recover the emission structure from the incomplete sampling. The convex optimization problem is defined as the primal problem and its dual problem is calculated. According to the characteristics of these two problems, the final solution of the primal problem is solved and the image of radio sources are reconstructed by iteratively alternating between solving the primal problem and the dual problem by using moreau decomposition, forward-backward method and the proximity operator. The algorithm parameters are analyzed from the simulations based on experimental data. The algorithm is validated and the parameters are optimized. The comparison between the images inferred from the compressed sensing and classical CLEAN algorithms shows that the signal to noise ratio and the dynamic range in the reconstructed

关键词：

来源：评论

学校读者我要写书评

暂无评论

CT reconstruction from Limited-view Cone-beam Projections Using 3D image Moments 4

CT Reconstruction from Limited-view Cone-beam Projections Us...

引用

4th International conference on Information Science and Control Engineering (ICISCE)

作者： Xu, Kaikai Dai, Xiubin Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Coll Geog & Biol Informat Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538630136

Limiting the views of cone-beam CT scan can effectively reduce the damage to the human's health brought by X-rays when taking CT examination. However, the CT images reconstructed from the limited-view cone-beam projections will degrade greatly. To improve the quality of the reconstructed images when the cone-beam projections are incomplete, this paper proposes a new method by using 3D image moments for limited-view cone-beam CT reconstruction. It uses 3D geometric moments to establish the relationship between 3D Radon data and image moments. After converting the cone-beam projection acquired in limited views into known 3D Radon data, we use this relationship to estimate unknown 3D Radon data from known ones. In this way, 3D Radon data become complete. Finally, with help of the inverse formula of the first derivative of the 3D Radon transform, we reconstruct the 3D CT images from the complete 3D Radon data. The experimental results show that our method has good performance in limited-view CT reconstruction. The experimental results show that our method can improve the reconstructed cone-beam CT images when only limited-view projections are given.

关键词： cone-beam CT reconstruction limited-view projections 3D geometric moments 3D Radon transform

来源：评论

学校读者我要写书评

暂无评论

Accuracy of Classified imagery without using Reference data Set

Accuracy of Classified Imagery without using Reference Data ...

引用

International conference on System Modeling & Advancement in Research Trends (SMART)

作者： Ranjana Sharma P. K. Garg P. K. Dwivedi Uttarakhand Technical University Dehradun Uttarakhand India IIT Rorkee India CCSIT Teerthnakar Mahaveer University Moradabad India

ISBN: (纸本)9781538663707

For the validation aspect the estimation of accuracy of classifiers is significant factor of analyzing the result of classifiers. If the pixel found in single class. So we prefer the hard classification. But satellite data does not find in single class. The pixel of satellite data belongs more than one class. So in that case we prefer the soft classification. The classification is only one parameter and other parameter is assessment of accuracy and we know without assessment of accuracy classification of classifiers is incomplete. There are several method to find out the the accuracy of classifiers like MLC, FERM, RMSE, and Entropy. Accuracy results are generated for soft classified data set from AWiFS, LISS-iii and LISS-IV sensor. The output results from tool used to investigation effect of sampling on assessed accuracy.

关键词： Agriculture Forestry Entropy Satellites image resolution Remote sensing Systems modeling

来源：评论

学校读者我要写书评

暂无评论

Multi-modal weighted quadratic priors for robust intensity independent synergistic PET-MR reconstruction

Multi-modal weighted quadratic priors for robust intensity i...

引用

IEEE Nuclear Science Symposium and Medical Imaging conference (NSS/MIC) / 24th International Symposium on Room-Temperature Semiconductor X-Ray and Gamma-Ray Detectors

作者： Mehranian, Abolfazl Belzunce, Martin A. McGinnity, Colm J. Prieto, Claudia Hammers, Alexander Reader, Andrew J. Kings Coll London Sch Biomed Engn & Imaging Sci Dept Biomed Engn London England Kings Coll London Sch Biomed Engn & Imaging Sci London England St Thomas Hosp Guys & St Thomas PET Ctr London England

ISBN: (纸本)9781538622827

In this work, a robust methodology is presented for synergistic PET-MR image reconstruction, irrespective of their relative signal intensities and contrasts. Mutually-weighted quadratic priors were devised to encourage the formation of common boundaries between PET and MR images while reducing noise, PET Gibbs and MR under-sampling artefacts. These priors are iteratively reweighted using normalized multi-modal Gaussian similarity kernels to modulate smoothing across common boundaries. Synergistic reconstruction was performed using a 3-step optimization: i) maximum a posteriori expectation maximization (MAP-EM) for regularized PET reconstruction, ii) penalized weighted least squares with the conjugate gradient algorithm (PWLS-CG) for regularized sensitivity encoding (SENSE) parallel MR reconstruction and iii) update of joint Gaussian kernels. The performance of the proposed prior was compared against standard reconstruction, separate total variation (TV) regularization and prior-image guided reconstruction using 3D realistic simulations and a real PET-MR dataset. Our results showed that TV regularization reduces noise and artifacts in PET and MR images, but at the expense of resolution degradation, while prior-image guided reconstructions, which exploit high quality fully-sampled MR data, notably improve the image quality but at the expense of suppressing unique lesions. Whereas the proposed method, which exploits information obtained from PET and undersampled MR images, leads to noise and artefact reduction while recovery the details and preserving unique lesions. In conclusion, the proposed algorithm was found promising for multi-modal synergistic image reconstruction.

关键词： image reconstruction TV Lesions reconstruction algorithms Kernel Encoding image resolution

来源：评论

学校读者我要写书评

暂无评论

A Double Recursion Algorithm to image Restoration from Random Limited Frequency data 9th

A Double Recursion Algorithm to Image Restoration from Rando...

引用

9th International conference on image and Graphics (ICIG)

作者： Liu, Xiaoman Liu, Jijun Southeast Univ Sch Math Nanjing 211189 Peoples R China

ISBN: (纸本)9783319715988;9783319715971

One of the main tasks in image restoration is to catch the picture characteristics such as interfaces and textures from incomplete noisy frequency data. For the cost functional with data matching term in frequency domain and the total variation together with Frobenius norm penalty terms in spatial domain, the properties of the minimizer of cost functional and the error estimates on the regularizing solution are established. Then we propose an algorithm with double recursion to restore piecewise smooth image. The Bregman iteration with lagged diffusivity fixed point method is used to solve the corresponding nonlinear Euler-Lagrange equation. By implementing recursion algorithms a few times, the satisfactory reconstructions can be obtained using random band sampling data. Numerical implementations demonstrate the validity of our proposed algorithm with good edge-preservations.

关键词： image restoration Random sampling Total variation Bregman iteration Adjoint conjugate gradient method

来源：评论

学校读者我要写书评

暂无评论

Development and future trends in the application of visualization toolkit (VTK): The case for medical image 3D reconstruction

引用

AIP conference Proceedings 2019年第1期2092卷

作者： Welsey Daniel C. Advincula Jose Antonio G. Choco Kryzz Amiel G. Magpantay Leonard Angelo N. Sabellina, iii Jolo Gerard Miel F. Tolentino Renann G. Baldovino Nilo T. Bugtai Aaron Raymond See Yi-Chun Du 1Manufacturing Engineering and Management (MEM) Department De La Salle University 2401 Taft Avenue 0922 Manila Philippines 2Department of Electrical Engineering Southern Taiwan University of Science and Technology No. 1 Nantai Street Yongkang District Tainan City Taiwan 710

Three-dimensional reconstruction of medical images plays a vital role in clinical medicine and medical research. It serves as a powerful tool to help doctors analyze multiple 2D medical images in a 3D perspective. The developed 3D model offers a faster and accurate approach in clinical diagnosis and therapy. Before, the development of 3D reconstruction programs it has always been a challenge to visualize in a 3D perspective but with the advent of powerful computing and graphics processing, medical imaging equipment development is on the rise. The advancement of 3D image reconstruction is not only due to the innovative hardware, but also because of the increase in open-source platforms or libraries, such as visualization toolkit (VTK), that assist on its development to provide an information visualization framework and advanced 3D modeling techniques. VTK is an object-oriented 3D graphics software program that is free to obtain and used both for open- and closed-source applications such as 3D computer graphics, image processing, and visualization. In medical imaging, data from ultrasound systems, magnetic resonance imaging (MRI), and computed tomography (CT) scans can be managed in VTK. Different algorithms of image processing such as color mapping, image re-slicing or resampling, iso-contouring, thresholding, and other algorithms can be utilized to make volume images from the data. Subsequently, data presentation is simplified with the data reconstruction through the use of supplemental software for analysis. VTK library contains a large number of filters, which are multi-threaded to facilitate parallel processing and interpretation. In this paper, recent technologies on the application of VTK for 3D reconstruction of biomedical images will be presented. Moreover, current methodologies will be discussed to clearly understand the different integral steps needed in image data conversion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3DMatch: Learning Local Geometric Descriptors from RGB-D reconstructions 30

3DMatch: Learning Local Geometric Descriptors from RGB-D Rec...

引用

30th IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zeng, Andy Song, Shuran Niessner, Matthias Fisher, Matthew Xiao, Jianxiong Funkhouser, Thomas Princeton Univ Princeton NJ 08544 USA Stanford Univ Stanford CA 94305 USA AutoX San Jose CA USA Adobe Syst San Jose CA USA

ISBN: (纸本)9781538604571

Matching local geometric features on real-world depth images is a challenging task due to the noisy, low-resolution, and incomplete nature of 3D scan data. These difficulties limit the performance of current state-of-art methods, which are typically based on histograms over geometric properties. In this paper, we present 3D Match, a data-driven model that learns a local volumetric patch descriptor for establishing correspondences between partial 3D data. To amass training data for our model, we propose a self-supervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions. Experiments show that our descriptor is not only able to match local geometry in new scenes for reconstruction, but also generalize to different tasks and spatial scales (e.g. instance-level object model alignment for the Amazon Picking Challenge, and mesh surface correspondence). Results show that 3D Match consistently outperforms other state-of-the-art approaches by a significant margin. Code, data, benchmarks, and pre-trained models are available online at http://***.

关键词： Three-dimensional displays image reconstruction Solid modeling Training Geometry Surface reconstruction

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：