检索结果-内蒙古大学图书馆

MEBCIS: Multi-Energy Betatron-based Cargo Inspection System

MEBCIS: Multi-Energy Betatron-based Cargo Inspection System

IEEE Nuclear Science Symposium / Medical Imaging Conference / Room-Temperature Semiconductor Detector Workshop (NSS/MIC/RTSD)

作者： Arodzero, Anatoli Boucher, Salime Kutsaev, Sergey v. Lanza, Richard C. Palermo, vincent O'Shea, Finn Ziskin, vitaliy RadiaBeam Technol Santa Monica CA 90404 USA MIT Dept Nucl Sci & Engn 77 Massachusetts Ave Cambridge MA 02139 USA Vertilon Corp Westford MA USA

ISBN: (纸本)9781509016426

The security market requirements for state-of-the-art mobile and portal radiography inspection systems include high imaging resolution (better than 5 mm line pair), penetration beyond 300 mm steel equivalent, material discrimination (three groups of Z) at speeds up to 16 km/h with 100% image sampling, low dose and small radiation exclusion zone. New research into radiography methods and systems has been actively pursued in order to achieve these challenging requirements. Recently, a significant portion of the R&D effort has been devoted to re-examining betatron based X-ray inspection systems. The advantages of the betatron-based inspection systems over conventional linac-based designs include small focal spot (which improves resolution), low weight and form-factor, a simpler control system and relatively low cost. A novel, low-dose Multi-Energy Betatron-based Cargo Inspection System, MEBCIS, presented in this paper relies on an innovative technique of extracting two X-ray pulses with lower-and higher-energies within a single betatron acceleration cycle (in contrast to conventional dual-energy betatrons with one Xray pulse produced during separate betatron acceleration cycles). In addition to the new betatron, new types of fast X-ray Scintillation-Cherenkov detectors, rapid processing of detector signals, an adaptive detector feedback algorithm for control of the betatron, and algorithms for intelligent material discrimination are parts of the overall MEBCIS system. The key advantage of the MEBCIS concept is that the material discrimination data is acquired in a single scan line rather than two. Thus, for the same betatron pulse rate, the scan rate can be twice as fast (better throughput) or can be done with a lower dose, even without adaptive dynamic pulse adjustment. Application of these techniques will maximize material discrimination, penetration, and contrast resolution while simultaneously reducing dose to the environment, resulting in a smaller exclusion zone.

关键词： Homeland security cargo inspection X-ray radiography material discrimination betatron X-ray detectors

来源：评论

学校读者我要写书评

暂无评论

Synthesis and optimization of image processing accelerators using domain knowledge

引用

JOURNAL OF systems ARCHITECTURE 2015年第10期61卷 646-658页

作者： Reiche, Oliver Haeublein, Konrad Reichenbach, Marc Schmid, Moritz Hannig, Frank Teich, Juergen Fey, Dietmar Friedrich Alexander Univ Erlangen Nurnberg FAU Dept Comp Sci Nurnberg Germany

In the domain of image processing, often real-time constraints are required. In particular, in safety-critical applications, timing is of utmost importance. A common approach to maintain real-time capabilities is to offload computations to dedicated hardware accelerators, such as Field Programmable Gate Arrays (FPGAs). Designing such architectures is per se already a challenging task, but finding the right design point between achieving as much throughput as necessary while spending as few resources as possible is an even bigger challenge. To address this design challenge in the domain of image processing, several approaches have been presented that introduce an additional layer of abstraction between the developer and the actual target hardware. One approach is to use a Domain-Specific Language (DSL) to generate highly optimized code for synthesis by general purpose High-Level Synthesis (HLS) frameworks. Another approach is to instantiate a generic vHDL IP-Core library for local imaging operators. Elevating the description of image algorithms to such a higher abstraction level can significantly reduce the complexity for designing hardware accelerators targeting FPGAs. We provide a comparison of results for both approaches, a non-expert algorithm developer can achieve. Furthermore, we present an automatic optimization process to give the algorithm developer even more control over trading execution time for resource usage, that could be applied on top of both approaches. To evaluate our optimization procedure, we compare the resulting FPGA accelerators to highly optimized Graphics processing Unit (GPU) implementations of several image filters relevant for close-to-sensor image and video processing with stringent real-time constraints, such as in the automotive domain. (C) 2015 Elsevier B.v. All rights reserved.

关键词： Hardware accelerators image processing Synthesis Code generation

来源：评论

学校读者我要写书评

暂无评论

Robust non-local stereo matching for outdoor driving images using segment-simple-tree

引用

SIGNAL processing-image COMMUNICATION 2015年第PartA期39卷 173-184页

作者： Cuong Cao Pham vinh Quang Dinh Jeon, Jae Wook Sungkyunkwan Univ Coll Informat & Commun Engn Suwon South Korea

Non-local cost aggregation has recently emerged as a promising approach for stereo-matching and has attracted much interest over the past few years. Most non-local algorithms are reportedly better than state-of-the-art local algorithms for high-quality indoor images. However, the accuracy of non-local algorithms is still limited for outdoor images. Computing disparity maps for outdoor images in driver assistance systems is one of the most actively researched topics in the field of stereo vision. In this paper, we present a robust non-local stereo matching algorithm that improves the performance of non-local approaches for outdoor driving images. The proposed algorithm is inspired by the non-local cost aggregation method based on a minimum spanning tree, and it improves the estimation accuracy by introducing an alternate, effective segment-simple-tree that is more adequate for outdoor driving images than the minimum spanning tree. Experimental results showed that the proposed algorithm is superior to the existing local and non-local algorithms, and is comparable to semi-global matching. (C) 2015 Elsevier B.v. All rights reserved.

关键词： Stereo matching Non-local cost aggregation Tree structure Driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Fast algorithms for Convolutional Neural Networks

Fast Algorithms for Convolutional Neural Networks

引用

IEEE Conference on Computer vision and Pattern Recognition

作者： Andrew Lavin Scott Gray Nervana Systems

ISBN: (纸本)9781467388528

Deep convolutional neural networks take GPU-days of computation to train on large data sets. Pedestrian detection for self driving cars requires very low latency. image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3×3 filters. We introduce a new class of fast algorithms for convolutional neural networks using Winograd's minimal filtering algorithms. The algorithms compute minimal complexity convolution over small tiles, which makes them fast with small filters and small batch sizes. We benchmark a GPU implementation of our algorithm with the vGG network and show state of the art throughput at batch sizes from 1 to 64.

关键词： Fasting Neural network state of the art Convolution Filters Mobile phones algorithms

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

Sequential computational procedure for remote sensing data forgery detection

引用

Pattern Recognition and image Analysis 2015年第4期25卷 645-653页

作者： Kuznetsov, A.v. Myasnikov, v.v. Samara State Aerospace University Moskovskoye sh. 34 Samara443086 Russia Image Processing Systems Institute Russian Academy of Sciences ul. Molodogvardeiskaya 151 Samara443001 Russia

This article considers the problem of constructing a sequential computational procedure for detecting artificial changes of remote sensing data (RSD) using a set of elementary algorithms of detecting artificial RSD changes. The stated task has been solved within the framework of the passive approach, which requires determining actual changes (forgeries) in RSD based on computer analysis. © 2015, Pleiades Publishing, Ltd.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Scale-Aware Alignment of Hierarchical image Segmentation

Scale-Aware Alignment of Hierarchical Image Segmentation

引用

IEEE Conference on Computer vision and Pattern Recognition

作者： Yuhua Chen Dengxin Dai Jordi Pont-Tuset Luc van Gool Computer Vision Lab ETH Zurich

ISBN: (纸本)9781467388528

image segmentation is a key component in many computer vision systems, and it is recovering a prominent spot in the literature as methods improve and overcome their limitations. The outputs of most recent algorithms are in the form of a hierarchical segmentation, which provides segmentation at different scales in a single tree-like structure. Commonly, these hierarchical methods start from some low-level features, and are not aware of the scale information of the different regions in them. As such, one might need to work on many different levels of the hierarchy to find the objects in the scene. This work tries to modify the existing hierarchical algorithm by improving their alignment, that is, by trying to modify the depth of the regions in the tree to better couple depth and scale. To do so, we first train a regressor to predict the scale of regions using mid-level features. We then define the anchor slice as the set of regions that better balance between over-segmentation and under-segmentation. The output of our method is an improved hierarchy, re-aligned by the anchor slice. To demonstrate the power of our method, we perform comprehensive experiments, which show that our method, as a post-processing step, can significantly improve the quality of the hierarchical segmentation representations, and ease the usage of hierarchical image segmentation to high-level vision tasks such as object segmentation. We also prove that the improvement generalizes well across different algorithms and datasets, with a low computational cost.

关键词： image segmentation Computer vision systems Hierarchical Boat anchors segmentation Object segmentation Social Hierarchy trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

variational mode feature-based hyperspectral image classification

引用

Advances in Intelligent systems and Computing 2016年 380卷 365-373页

作者： Nechikkat, Nikitha Sowmya, v. Soman, K.P. Center for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham CoimbatoreTamil Nadu India

ISBN: (纸本)9788132225225

Hyperspectral image analysis is considered as a promising technology in the field of remote sensing over the past decade. There are various processing and analysis techniques developed that interpret and extract the maximum information from high-dimensional hyperspectral datasets. The processing techniques significantly improve the performance of standard algorithms. This paper uses variational mode decomposition (vMD) as the processing algorithm for hyperspectral data scenarios followed by classification based on sparse representation. variational Mode Decomposition decomposes the experimental data set into few different modes of separate spectral bands, which are unknown. These modes are given as raw input to the classifier for performance analysis. Orthogonal matching pursuit (OMP), the sparsity-based algorithm is used for classification. The proposed work is experimented on the standard dataset, namely Indian pines collected by the airborne visible/infrared imaging spectrometer (AvIRIS). The classification accuracy obtained on the hyperspectral data before and after applying variational Mode Decomposition was analyzed. The experimental result shows that the proposed work leads to an improvement in the overall accuracy from 84.82 to 89.78%, average accuracy from 85.03 to 89.53% while using 40% data pixels for training. © Springer India 2016.

关键词： variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Detection for Robots using CNN with a Feature-Based Layered Pre-filter

Real-Time Human Detection for Robots using CNN with a Featur...

引用

IEEE International Symposium on Robot and Human Interactive Communication

作者： E. Martinson v. Yalla Toyota InfoTechnology Center Mountain View CA 94043 USA

ISBN: (纸本)9781509039302

Convolutional neural networks (CNNs), in combination with big data, are increasingly being used to engineer robustness into visual classification systems including human detection. One significant challenge to using a CNN on a mobile robot, however, is the associated computational cost and detection rate of running the network. In this work, we demonstrate how fusion with a feature-based layered classifier can help. Not only does score-level fusion of a CNN with the layered classifier improve precision/recall for detecting people on a mobile robot, but using the layered system as a pre-filter can substantially reduce the computational cost of running a CNN - reducing the number of objects that need to be classified while still improving precision. The combined real-time system is implemented and evaluated on a two robots with very different GPU capabilities.

关键词： image segmentation Classification algorithms Robots Neural networks Graphics processing units Cameras Mathematical model Robot Sorting algorithm Cameras image segmentation pre-filter Neural network Graphics processing Unit Mathematical Model Mobile robots layered systems big data

来源：评论

学校读者我要写书评

暂无评论

Depth map occlusion filling and scene reconstruction using modified exemplar-based inpainting 13

Depth map occlusion filling and scene reconstruction using m...

引用

Conference on image processing - algorithms and systems XIII

作者： voronin, v. v. Marchuk, v. I. Fisunov, A. v. Tokareva, S. v. Egiazarian, K. O. Don State Tech Univ Dept Radioelect Syst Shakhty 346500 Russia Tampere Univ Technol Dept Signal Proc FI-33720 Tampere Finland

ISBN: (纸本)9781628414899

RGB-D sensors are relatively inexpensive and are commercially available off-the-shelf. However, owing to their low complexity, there are several artifacts that one encounters in the depth map like holes, mis-alignment between the depth and color image and lack of sharp object boundaries in the depth map. Depth map generated by Kinect cameras also contain a significant amount of missing pixels and strong noise, limiting their usability in many computer vision applications. In this paper, we present an efficient hole filling and damaged region restoration method that improves the quality of the depth maps obtained with the Microsoft Kinect device. The proposed approach is based on a modified exemplar-based inpainting and LPA-ICI filtering by exploiting the correlation between color and depth values in local image neighborhoods. As a result, edges of the objects are sharpened and aligned with the objects in the color image. Several examples considered in this paper show the effectiveness of the proposed approach for large holes removal as well as recovery of small regions on several test images of depth maps We perform a comparative study and show that statistically, the proposed algorithm delivers superior quality results compared to existing algorithms.

关键词： image processing inpainting depth map Kinect occlusion filtering

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：