检索结果-内蒙古大学图书馆

IEEE/CvF conference on Computer vision and Pattern Recognition (CvPR)

作者： Kim, Jongwan Lee, DongJin Na, Byunggook Park, Seongsik Jo, Jeonghee Yoon, Sungroh Seoul Natl Univ Interdisciplinary Program AI Seoul South Korea Seoul Natl Univ Dept ECE Seoul South Korea Seoul Natl Univ ISRC INMC ASRIAIIS Seoul South Korea Korea Inst Sci & Technol Seoul South Korea

ISBN: (纸本)9781665469463

Event cameras respond to brightness changes in the scene asynchronously and independently for every pixel. Due to the properties, these cameras have distinct features: high dynamic range (HDR), high temporal resolution, and low power consumption. However, the results of event cameras should be processed into an alternative representation for computer vision tasks. Also, they are usually noisy and causes poor performance in areas with few events. In recent years, numerous researchers have attempted to reconstruct videos from events. However, they do not provide good quality videos due to a lack of temporal information from irregular and discontinuous data. To overcome these difficulties, we introduce an E2v-SDE whose dynamics are governed in a latent space by Stochastic differential equations (SDE). Therefore, E2v-SDE can rapidly reconstruct images at arbitrary time steps and make realistic predictions on unseen data. In addition, we successfully adopted a variety of image composition techniques for improving image clarity and temporal consistency. By conducting extensive experiments on simulated and real-scene datasets, we verify that our model outperforms state-of-the-art approaches under various video reconstruction settings. In terms of image quality, the LPIPS score improves by up to 12% and the reconstruction speed is 87% higher than that of ET-Net.

关键词：

来源：评论

学校读者我要写书评

暂无评论

reconstruction OF COMPLEX SCENE RADIATION FIELDS BASED ON image RESTORATION EQUATION 31

RECONSTRUCTION OF COMPLEX SCENE RADIATION FIELDS BASED ON IM...

引用

31st International conference on Nuclear Engineering (ICONE) - 24/7 Clean Nuclear Energy - Solution for Global Warming

作者： Hu, Hao Dong, Xinwen Xu, Yuhan Zhuang, Shuhan Fang, Sheng Tsinghua Univ Inst Nucl & New Energy Technol Beijing 100084 Peoples R China

ISBN: (纸本)9780791888285

In the context of nuclear safety production, the detailed information on three-dimensional radiation field dose rates plays a vital role in enhancing radiation protection and planning for radioactive areas. Research on inversion methods, especially under scenarios of sparse or irregular measurement points, has attracted significant attention. Currently, there are advances in inversion methods based on interpolation algorithms and neural network techniques. Interpolation algorithms are inversion methods capable of rapidly inverting and reconstructing the distribution of radiation field dose rates with limited radiation field data. These methods include grid data interpolation, finite element methods, inverse distance weighting, kriging, and radial basis function methods, and are the most widely used methods for the quick reconstruction of radiation fields at present. Based on the information of known sample points, these algorithms predict information at unsampled points by selecting appropriate analytical models to find suitable mapping relationships. They offer the advantages of simplicity and speed, but have poor capability in restoring the geometric shapes of multiple radiation sources and face significant challenges in the direct inversion and reconstruction of three-dimensional radiation fields. In some cases, sparse sampling data can lead to suboptimal inversion results. Neural network algorithms, renowned for their strong nonlinear mapping capabilities, can approximate complex functions by learning from extensive data sets. Once appropriately trained, neural networks can process incomplete or uncertain knowledge and predict outcomes based on limited data. These algorithms are commonly used in image restoration and inverse problem-solving. In recent radiation field dose rate inversion methods, neural network algorithms have gained attention due to their exceptional data fitting and predictive *** recent years, research has proposed an inversion met

关键词： Radiation Field reconstruction Restoration Equations Complex Scenes

来源：评论

学校读者我要写书评

暂无评论

image bit depth plane digital watermarking for secured classified image data transmission 1

Image bit depth plane digital watermarking for secured class...

引用

1st International conference on Information Security and Privacy

作者： Khandare, Shrinivas Shrawankar, Urmila GH Raisoni Coll Engn Dept Comp Sci & Engn Nagpur Maharashtra India

The demand for rapid use of Internet has increased many folds in distributed environments. It is easy for the custodian of the digital data to transfer images of classification across computers via internet. The information transmitted is not secured. Conventional encryption and decryption algorithms are vulnerable from the thefts of the digital data and do not protect the data from copying after the data is transmitted. The data prone to copyright thefts should be protected against manipulation, misuse and security breaks. First the image is classified using maximum likelihood classification and fuzzy model. Second, for transmission, with copyright information, image is secured, by image bit depth plane digital image watermarking. In this method, image is read and separated into n-bit planes. The accuracy is tested using visual interpretation and assessment. The application of this method is identification of ownership, claim of ownership, online transaction, digital content authorization, file reconstruction. This method is robust against intentional and unintentional attacks of malicious users. (C) 2016 The Authors. Published by Elsevier B.v.

关键词： Information security data security image processing Fuzzy classification Bit plane Watermarking

来源：评论

学校读者我要写书评

暂无评论

Neural Network PET reconstruction using Scattered data in Energy-dependent Sinograms

Neural Network PET Reconstruction using Scattered Data in En...

引用

15th International Joint conference on Biomedical Engineering Systems and Technologies (BIOSTEC) / 9th International conference on Bioimaging (BIOIMAGING)

作者： Fontaine, Gabrielle Lindstrom, Peter Pistorius, Stephen Univ Manitoba Dept Phys & Astron 30A Sifton Rd Winnipeg MB R3T 2N2 Canada CancerCare Manitoba Res Inst 675 McDermot Ave Winnipeg MB R3E 0V9 Canada

ISBN: (纸本)9789897585524

PET image reconstruction largely relies on pre-reconstruction data correction, which may add noise and remove information. This loss is particularly notable when correcting for scattered coincidences, which are useful for image reconstruction, though algorithmic scatter reconstructions require a detector energy resolution that exceeds the current state-of-the-art. Preliminary research has demonstrated the feasibility of using convolutional neural networks (CNNs) to reconstruct images directly from sinogram data. We have extended this approach to reconstruct images from data containing scattered coincidences. Monte Carlo simulations were performed to simulate PET data from digital phantoms. data were modeled using 15% FWHM energy resolution detectors. Energy-dependent sinograms (EDS5), containing true and scattered coincidences, were constructed from the data. After data augmentation, 210,000 sinograms were obtained. A CNN was trained on the EDS-activity pairs for image reconstruction. A second network was trained on sinograms containing only photopeak coincidences. images were also reconstructed using FBP, and MLEM approaches. The EDS trained network outperformed the photopeak trained network, with a higher mean structural similarity index (0.69 +/- .05 vs. 0.63 +/- .05) and lower average mean square error (0.16 +/- .04 vs. 0.20 +/- .04). Our work demonstrates that CNNs have the potential to extract useful information from scattered coincidences, even for data containing significant energy uncertainties.

关键词： Positron Emission Tomography Medical Imaging Neural Network Deep Learning Scattered Coincidences Direct reconstruction

来源：评论

学校读者我要写书评

暂无评论

Synergistic image reconstruction for Hybrid Ultrasound and Photoacoustic Computed Tomography

Synergistic Image Reconstruction for Hybrid Ultrasound and P...

引用

conference on Photons Plus Ultrasound - Imaging and Sensing

作者： Matthews, Thomas P. Wang, Kun Wang, Lihong v. Anastasio, Mark A. Washington Univ Sch Engn & Appl Sci Dept Biomed Engn St Louis MO 63130 USA

ISBN: (纸本)9781628414134

Conventional photoacoustic computed tomography (PACT) image reconstruction methods assume that the object and surrounding medium are described by a constant speed-of-sound (SOS) value. In order to accurately recover fine structures, SOS heterogeneities should be quantified and compensated for during PACT reconstruction. To address this problem, several groups have proposed hybrid systems that combine PACT with ultrasound computed tomography (USCT). In such systems, a SOS map is reconstructed first via USCT. Consequently, this SOS map is employed to inform the PACT reconstruction method. Additionally, the SOS map can provide structural information regarding tissue, which is complementary to the functional information from the PACT image. We propose a paradigm shift in the way that images are reconstructed in hybrid PACT-USCT imaging. Inspired by our observation that information about the SOS distribution is encoded in PACT measurements, we propose to jointly reconstruct the absorbed optical energy density and SOS distributions from a combined set of USCT and PACT measurements, thereby reducing the two reconstruction problems into one. This innovative approach has several advantages over conventional approaches in which PACT and USCT images are reconstructed independently: (1) variations in the SOS will automatically be accounted for, optimizing PACT image quality;(2) The reconstructed PACT and USCT images will possess minimal systematic artifacts because errors in the imaging models will be optimally balanced during the joint reconstruction;(3) Due to the exploitation of information regarding the SOS distribution in the full-view PACT data, our approach will permit high-resolution reconstruction of the SOS distribution from sparse array data.

关键词： ultrasound computed tomography photoacoustic computed tomography joint image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Photoacoustic image reconstruction - A quantitative analysis

Photoacoustic image reconstruction - A quantitative analysis

引用

conference on Novel Optical Instrumentation for Biomedical Applications III

作者： Sperl, Jonathan I. Zell, Karin Menzenbach, Peter Haisch, Christoph Ketzer, Stephan Marquart, Markus Koenig, Hartmut vogel, Mika W. GE Global Res Freisinger Landstr 50 Munich Germany Tech Univ Munich Chair Analyt Chem Munich Germany Innolas GmbH Krailling Germany

ISBN: (纸本)9780819467751

Photoacoustic imaging is a promising new way to generate unprecedented contrast in ultrasound diagnostic imaging. It differs from other medical imaging approaches, in that it provides spatially resolved information about optical absorption of targeted tissue structures. Because the data acquisition process deviates from standard clinical ultrasound, choice of the proper image reconstruction method is crucial for successful application of the technique. In the literature, multiple approaches have been advocated, and the purpose of this paper is to compare four reconstruction techniques. Thereby, we focused on resolution limits, stability, reconstruction speed, and SNR. We generated experimental and simulated data and reconstructed images of the pressure distribution using four different methods: delay-and-sum (DnS), circular backprojection (CBP), generalized 2D Hough transform (HTA), and Fourier transform (FTA). All methods were able to depict the point sources properly. DnS and CBP produce blurred images containing typical superposition artifacts. The HTA provides excellent SNR and allows a good point source separation. The FTA is the fastest and shows the best FWHM. In our study, we found the FTA to show the best overall performance. It allows a very fast and theoretically exact reconstruction. Only a hardware-implemented DnS might be faster and enable real-time imaging. A commercial system may also perform several methods to fully utilize the new contrast mechanism and guarantee optimal resolution and fidelity.

关键词： photoacoustic optoacoustic image reconstruction delay-and-sum circular backprojection Hough transform Fourier transform

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks Conditioned on Brain Activity Reconstruct Seen images

Generative Adversarial Networks Conditioned on Brain Activit...

引用

IEEE International conference on Systems, Man, and Cybernetics (SMC)

作者： St-Yves, Ghislain Naselaris, Thomas Med Univ South Carolina Dept Neurosci 96 Jonathan Lucas St CSB 325c Charleston SC 29425 USA Med Univ South Carolina Dept Neurosci 96 Jonathan Lucas St CSB 325h Charleston SC 29425 USA

ISBN: (纸本)9781538666500

We consider the inference problem of reconstructing a visual stimulus from brain activity measurements (e.g. fMRI) that encode this stimulus. Recovering a complete image is complicated by the fact that neural representations are noisy, high-dimensional, and contain incomplete information about image details. Thus, reconstructions of complex images from brain activity require a strong prior. Here we propose to train generative adversarial networks (GANs) to learn a generative model of images that is conditioned on measurements of brain activity. We consider two challenges of this approach: First, given that GANs require far more data to train than is typically collected in an fMRI experiment, how do we obtain enough samples to train a GAN that is conditioned on brain activity? Secondly, how do we ensure that our generated samples are robust against noise present in fMRI data? Our strategy to surmount both of these problems centers around the creation of surrogate brain activity samples that are generated by an encoding model. We find that the generative model thus trained generalizes to real fMRI data measured during perception of images and is able to reconstruct the basic outline of the stimuli.

关键词： Gallium nitride image reconstruction Brain modeling Generative adversarial networks Encoding Training

来源：评论

学校读者我要写书评

暂无评论

A Model for Representing the Color and Depth Metric Characteristics of Objects in an image

A Model for Representing the Color and Depth Metric Characte...

引用

conference on Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)

作者： Gadasin, D., v Shvedov, A., v Kuzin, I. A. Moscow Tech Univ Commun & Informat Moscow Russia

ISBN: (纸本)9781665415491

In general, a person receives information from the surrounding world with the help of the senses, processes it through the brain, using the knowledge gained earlier, and then transmits and accepts it, again using the senses. In other words, these information processes (receiving, processing, transmitting information), a person implements in a sign-signal form. The considered information processes are closely interrelated. For example, the processing and transmission of information is impossible without its storage, and to save the processed information, it must be transmitted. In this paper, the possibility of storing in the form of a single data structure not only information about the color of each pixel corresponding to the object of the scene fixed on it, but also the depth of its position is considered. A model is constructed for storing rangefinder information for each point of the three-dimensional scene in the image. An image generation algorithm is proposed for this model.

关键词： Three-dimensional reconstruction computer vision depth map data representation model scene reconstruction two-dimensional images three-dimensional images

来源：评论

学校读者我要写书评

暂无评论

Compensation for acoustic heterogeneities in photoacoustic computed tomography using a variable temporal data truncation reconstruction method

Compensation for acoustic heterogeneities in photoacoustic c...

引用

conference on Photons Plus Ultrasound - Imaging and Sensing

作者： Poudel, Joemini Matthews, Thomas P. Anastasio, Mark A. Wang, Lihong v. Washington Univ Dept Biomed Engn 1 Brookings Dr St Louis MO 63130 USA

ISBN: (纸本)9781628419429

Photoacoustic computed tomography (PACT) is an emerging computed imaging modality that exploits optical contrast and ultrasonic detection principles to form images of the absorbed optical energy density within tissue. If the object possesses spatially variant acoustic properties that are unaccounted for by the reconstruction algorithm, the estimated image can contain distortions. While reconstruction algorithms have recently been developed for compensating for this effect, they generally require the object's acoustic properties to be known a priori. To circumvent the need for detailed information regarding an object's acoustic properties, we have previously proposed a half-time reconstruction method for PACT. A half-time reconstruction method estimates the PACT image from a data set that has been temporally truncated to exclude the data components that have been strongly aberrated. In this approach, the degree of temporal truncation is the same for all measurements. However, this strategy can be improved upon when the approximate sizes and locations of strongly heterogeneous structures, such as gas voids or bones, are known. In this work, we investigate PACT reconstruction algorithms that are based on a variable temporal data truncation (vTDT) approach that represents a generalization of the half-time reconstruction approach. In the vTDT approach, the degree of temporal truncation for each measurement is determined by the distance between the corresponding transducer location and the nearest known bone or gas void location. Computer simulation studies are employed to demonstrate the feasibility and effectiveness of the approach.

关键词： photoacoustic computed tomography image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Entropy-based method to evaluate the data integrity

引用

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT 2006年第2期569卷 412-415页

作者： Xu Peng Ma Tianyu Jin Yongjie Tsinghua Univ Dept Engn Phys Beijing 100084 Peoples R China

Projection stage of single photon emission computed tomography (SPECT) was discussed to analyze the characteristics of information transmission and evaluate the data integrity. Information is transferred from the source to the detector in the photon emitting process. In the projection stage, integrity of projection data can be assessed by the information entropy, which is the conditional entropy standing for the average uncertainty of the source object under the condition of projection data. Simulations were performed to study projection data of emission-computed tomography with a pinhole collimator. Several types of collimators were treated. Results demonstrate that the conditional entropy shows the data integrity, and indicate how the algorithms are matched or mismatched to the geometry. A new method for assessing data integrity is devised for those decision makers to help improve the quality of image reconstruction. (c) 2006 Elsevier B.v. All rights reserved.

关键词： data integrity entropy information theory SPECT

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：