检索结果-内蒙古大学图书馆

International Conference on Mobile Computing and Ubiquitous Networking (ICMU)

作者： Katsuhiko Kaji Kohei Kanagu Kazuya Murao Nobuhiko Nishio Kenta Urano Hirokazu Iida Nobuo Kawaguchi Faculty of Information Science Aichi Institute of Technology College of Information Science and Engineering Ritsumeikan University Graduate School of Engineering Nagoya University

ISBN: (纸本)9781509017423

PDR (Pedestrian Dead Reckoning) is a very promising technology for indoor positioning. We held a technical challenge, entitled the UbiComp/ISWC 2015 PDR Challenge, consisting of the following three categories: a PDR algorithm category; a PDR Evaluation method category; and an exhibition. In this paper, we especially focus on several systems for the PDR algorithm category. A PDR skeleton was prepared for the participants. Using an Android skeleton, participants focus on implementing the PDR algorithm because of the skeleton's various functions, such as sensor data acquisition, trajectory visualization, and sensor data upload. The evaluation server evaluates the accuracy of each PDR algorithm automatically as often as sensor data is uploaded to the server and provides a trajectory image file so that participants can compare their PDR algorithms in real time.

关键词： Servers Signal processing algorithms Sensors Skeleton Smart phones Trajectory Handheld computers

来源：评论

学校读者我要写书评

暂无评论

Salient Object Detection via Adaptive Region Merging

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION systems 2016年第9期10卷 4386-4404页

作者： Zhou, Jingbo Zhai, Jiyou Ren, Yongfeng NUIST Nanjing 210044 Jiangsu Peoples R China Hohai Univ Coll Comp & Informat Nanjing 211100 Jiangsu Peoples R China Huaiyin Inst Technol Fac Comp Engn Huaian 223003 Peoples R China

Most existing salient object detection algorithms commonly employed segmentation techniques to eliminate background noise and reduce computation by treating each segment as a processing unit. However, individual small segments provide little information about global contents. Such schemes have limited capability on modeling global perceptual phenomena. In this paper, a novel salient object detection algorithm is proposed based on region merging. An adaptive-based merging scheme is developed to reassemble regions based on their color dissimilarities. The merging strategy can be described as that a region R is merged with its adjacent region Q if Q has the lowest dissimilarity with Q among all Q's adjacent regions. To guide the merging process, superpixels that located at the boundary of the image are treated as the seeds. However, it is possible for a boundary in the input image to be occupied by the foreground object. To avoid this case, we optimize the boundary influences by locating and eliminating erroneous boundaries before the region merging. We show that even though three simple region saliency measurements are adopted for each region, encouraging performance can be obtained. Experiments on four benchmark datasets including MSRA-B, SOD, SED and iCoSeg show the proposed method results in uniform object enhancement and achieve state-of-the-art performance by comparing with nine existing methods.

关键词： Salient object detection image segmentation Adaptive region merging

来源：评论

学校读者我要写书评

暂无评论

Normalization of Feature Distribution in Motor imagery Based Brain-Computer Interfaces

Normalization of Feature Distribution in Motor Imagery Based...

引用

Mediterranean Conference on Control and Automation

作者： Bartosz Binias Tomasz Grzejszczak Michal Niezabitowski Institute of Automatic Control Silesian Univeristy of Technology 44-100 Gliwice Poland

ISBN: (纸本)9781467383479

Brain-Computer Interfaces (BCIs) are systems capable of capturing and interpreting the consent changes in the activity of brain (e.g. intention of limb movement, attention focus on specific frequency or symbol) and translating them into sets of instructions, which can be used for the control of a computer. The most popular hardware solutions in BCI are based on the signals recorded by the electroencephalograph (EEG). Such signals can be used to record and monitor the bioelectrical activity of the brain. However, raw EEG scalp potentials are characterized by a weak spatial resolution. Due to that reason, multichannel EEG recordings tend to provide an unclear image of the activity of brain and the use of special signal processing and analysis methods is needed. A typical approach towards modern BCIs requires an extensive use of Machine Learning methods. It is generally accepted that the performance of such systems is highly sensitive to the feature extraction step. One of the most effective and widely used descriptors of EEG data is the power of the signal calculated in a specific frequency range. In order to improve the performance of chosen classification algorithm, the distribution of the extracted bandpower features is often normalized with the use of natural logarithm function. In this study the step of normalization of feature distribution was taken into careful consideration. Commonly used logarithm function is not always the best choice for this process. Therefore, the influence on the skewness of features, as well as, on the general classification accuracy of different settings of Box-Cox transformation will be tested in this article and compared to classical approach that employs natural logarithm function. For the better evaluation of the performance of the proposed approach, its effectiveness is tested in the task of classification of the benchmark data provided for the "BCI Competition III" (dataset "IVa") organized by the Berlin Brain-Computer Interface

关键词： Electroencephalography Feature extraction Signal processing algorithms Brain-computer interfaces Scalp Pollution measurement Brain-Computer Interfaces pollution measurement Electroencephalography Signal processing algorithms Logarithm functions Scalp Feature extraction brain activity normalization

来源：评论

学校读者我要写书评

暂无评论

Louvain community detection with parallel heuristics on GPUs

Louvain community detection with parallel heuristics on GPUs

引用

IEEE International Conference on Intelligent Engineering systems (INES)

作者： Richard Forster Faculty of Informatics Eotvos Lorand University Budapest Hungary

Community detection has become an important operation in numerous graph based applications. It is used to reveal groups that exist within real world networks without imposing prior size or cardinality constraints on the set of communities. Despite its potential, the support for parallel computers is rather limited. This is largely because the algorithm is irregular and the underlying heuristics imply a sequential nature. In this paper I present parallelization heuristics for fast community detection using the Louvain method as it is applied on GPUs. The Louvain method is a multi-phase, iterative heuristic for modularity optimization. It was originally developed by Blondel et al. (2008), the method has become increasingly popular owing to its ability to detect high modularity community partitions in a fast and memory-efficient manner. The parallel heuristics used, were first introduced by Hao Lu et al. (2015). As the Louvain method is inherently sequential, it limits the possibility of scalable usage. Thanks to the proposed parallel heuristics, I observe how this method can behave on GPUs. For evaluation I implemented the heuristics using CUDA on a GeForce GTX 980M GPU and for testing I used organization landscapes from the CERN developed Collaboration Spotting project that involves patents and publications to visualize the connections in technologies among its collaborators. Compared to the parallel Louvain implementation running on 8 threads on the same machine that has the used GPU, the CUDA implementation is able to produce community outputs comparable to the CPU generated results, while providing absolute speedups of up to 12 using the GeForce GTX 980M mobile GPU.

关键词： Graphics processing units Computer architecture Instruction sets Parallel algorithms Heuristic algorithms Partitioning algorithms image edge detection

来源：评论

学校读者我要写书评

暂无评论

An image processing VLIW Architecture for Real-Time Depth Detection

An Image Processing VLIW Architecture for Real-Time Depth De...

引用

International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

作者： Dan Iorga Razvan Nane Yi Lu Edwin Van Dalen Koen Bertels Computer Engineering Research Group Delft University of Technology Delft The Netherlands Intel Benelux B.V Eindhoven AG The Netherlands Intel Benelux B.V. Eindhoven Netherlands

ISBN: (纸本)9781509061099

Numerous applications for mobile devices require 3D vision capabilities, which in turn require depth detection since this enables the evaluation of an object's distance, position and shape. Despite the increasing popularity of depth detection algorithms, available solutions need expensive hardware and/or additional ASICs, which are not suitable for low-cost commodity hardware devices. In this paper, we propose a low-cost and low-power embedded solution to provide high speed depth detection. We extend an existing off-the-shelf VLIW image processor and perform algorithmic and architectural optimizations in order to achieve the requested real-time performance speed. Experimental results show that by adding different functional units and adjusting the algorithm to take full advantage of them, a 640×480 image pair with 64 disparities 1 can be processed at 36.75 fps on a single processor instance, which is an improvement of 23% compared to the best state-of-the-art image processor.

关键词： VLIW Hardware Computer architecture Real-time systems Optimization Kernel Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Towards Real-Time People Recognition on Aerial imagery Using Convolutional Neural Networks

Towards Real-Time People Recognition on Aerial Imagery Using...

引用

International Symposium on Object-Oriented Real-Time Distributed Computing

作者： Diulhio Candido De Oliveira Marco Aurelio Wehrmeister Federal University of Technology - Paraná (UTFPR) Curitiba Brazil

ISBN: (纸本)9781467390330

People recognition in aerial imagery is a complex problem since it involves cameras angles, which are subject to six degrees of freedom. Traditional classifiers used in pattern matching algorithms are not robust enough to deal with such issues. Thus it is necessary to use other techniques such as deep learning methods, e.g. Convolutional Neural Networks (CNN), in order to cope with such a complex problem. However, in spite of providing potentially better recognition results, deep learning methods demand greater processing time, hindering its use on on-board embedded systems of small Unmanned Aerial Vehicles (UAV). This work is a step towards real-time (and possibly on-board) people recognition on aerial imagery. We propose a new approach based on CNN for real-time people recognition on aerial images obtained from cameras attached to small UAVs. This approach combines images from a low-cost thermal camera to detect candidate objects and CNN for the classification task. We have compared our approach with two traditional pattern matching approaches: saliency map detection and cascade classifiers. The obtained results show that, by using CNN, higher rates of correct classification within 95% of precision are obtained. These results have been obtained within real-time processing of 1.08 fps in the worst case on a hardware without any GPU processing.

关键词： image recognition Feature extraction Real-time systems Cameras Object recognition Graphics processing units Shape

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Human and Automated Face Verification Accuracy on Unconstrained image Sets

A Comparison of Human and Automated Face Verification Accura...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Austin Blanton Kristen C. Allen Tim Miller Nathan D. Kalka Anil K. Jain Noblis Michigan State University

Automatic face recognition technologies have seen significant improvements in performance due to a combination of advances in deep learning and availability of larger datasets for training deep networks. Since recognizing faces is a task that humans are believed to be very good at, it is only natural to compare the relative performance of automated face recognition and humans when processing fully unconstrained facial imagery. In this work, we expand on previous studies of the recognition accuracy of humans and automated systems by performing several novel analyses utilizing unconstrained face imagery. We examine the impact on performance when human recognizers are presented with varying amounts of imagery per subject, immutable attributes such as gender, and circumstantial attributes such as occlusion, illumination, and pose. Results indicate that humans greatly outperform state of the art automated face recognition algorithms on the challenging IJB-A dataset.

关键词： Face Face recognition Lighting image recognition Probes Protocols Databases

来源：评论

学校读者我要写书评

暂无评论

Real-time tag recognition based on morphology and local contrast

Real-time tag recognition based on morphology and local cont...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Zhiqin Chen Yufeng Zhang Hesheng Wang Weidong Chen Department of Co mputer Science Shanghai Jiao Tong University Shanghai China Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (纸本)9781467389600

With the development of computer and robotic technology, more and more miscellaneous work has been done by robots rather than men. In this case, robot vision, especially object recognition, which can help to locate objects in captured images and extract valuable information from those objects, becomes a significant part in robot design and realization. This process is expected to be real-time. In this paper, the aim is to find out the real-time and accurate algorithms to localize and recognize particular tags. Firstly, new special tags are designed. Then two tag corner localization methods are proposed, in which one is based on morphology and another is based on local contrast. And the character recognition based on OCR are also described. In the end, based on Library Management Robot (LMR), some experiments are taken. As a result, the two tag localization algorithms turn out to have complementary features in recognition distance. Meanwhile, comparing to other methods, the new methods can quickly and accurately extract tags and their information under various conditions including unexpected shadows, different light conditions and different backgrounds.

关键词： Robots Algorithm design and analysis Libraries image color analysis Morphology image recognition Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Privacy protecting, intelligibility preserving video surveillance

Privacy protecting, intelligibility preserving video surveil...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Natacha Ruchaud Jean-Luc Dugelay Eurecom Sophia-Antipolis Biot

ISBN: (纸本)9781509015535

Video surveillance is increasingly omni-present in our everyday life and is a key component of many security systems. Not only is the increasing number of cameras, but also the resolution of visual sensors and the performance of video processing algorithms. This evolution generates some important privacy concerns. This article introduces a new visual filter that includes a good trade-off between privacy and intelligibility. It ensures that people are unrecognizable while keeping the scene understandable in terms of events which allows machines to detect abnormal behavior. The algorithm operates in the DCT domain to be compliant with the popular JPEG and MPEG codecs. For each sensitive area of the picture (i.e. area where privacy needs to be protected), the proposed algorithm uses the low-frequency coefficients of the DCT to display a privacy preserved image of the region and the high-frequency coefficients to hide most of the original information. Finally, our process allows authorized users to nearly reverse the process thanks to the hidden information.

关键词： Privacy Discrete cosine transforms Transform coding image coding Face recognition Video surveillance Cryptography

来源：评论

学校读者我要写书评

暂无评论

DETECTION AND CHARACTERIZATION OF EXOPLANETS USING PROJECTIONS ON KARHUNEN-LOEVE EIGENimageS: FORWARD MODELING

引用

ASTROPHYSICAL JOURNAL 2016年第2期824卷 117页

作者： Pueyo, Laurent Space Telescope Sci Inst 3700 San Martin Dr Baltimore MD 21218 USA

A new class of high-contrast image analysis algorithms that empirically fit and subtract systematic noise has lead to recent discoveries of faint exoplanet/substellar companions and scattered light images of circumstellar disks. These methods are extremely efficient at enhancing the detectability of a faint astrophysical signal, but they generally create systematic biases in their observed properties. This paper provides a general solution for this outstanding problem. We present an analytical derivation of a linear expansion that captures the impact of astrophysical over-subtraction or self-subtraction in current image analysis techniques. We examine the general case for which the reference images of the astrophysical scene move azimuthally and/or radially across the field of view as a result of the observation strategy. Our new method is based on perturbing the covariance matrix underlying any least-squares speckles problem, and propagating this perturbation through the data analysis algorithm. Most of the work in this paper is presented in the Principal Component Analysis framework, but it can be easily generalized to methods relying on the linear combination of images (instead of eigenmodes). Based on this linear expansion, which is obtained in the most general case, we then demonstrate practical applications of this new algorithm. We first consider the spectral extraction of faint point sources in IFS data and illustrate, using public Gemini Planet imager commissioning data, that our novel perturbation-based Forward Modeling, which we named Karhunen Loeve image processing (KLIP-FM), can indeed alleviate algorithmic biases. We then apply KLIP-FM to the detection of point sources and show how it decreases the rate of false negatives while keeping the rate of false positives unchanged when compared to classical KLIP. This can potentially have important consequences on the design of follow-up strategies of ongoing direct imaging surveys.

关键词： planetary systems techniques: image processing

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：