检索结果-内蒙古大学图书馆

3rd ieee International Conference on computational intelligence and Computing Research (ICCIC)

作者： Roy, Pradipta Das, Dipak Biswas, P. K. DRDO Optron Ctr ITR Chandipur Orissa India IIT Dept E Kharagpur W Bengal India IIT ECE Kharagpur W Bengal India

ISBN: (纸本)9781467324816;9781467313445

In this paper, we propose a VLSI implementation scheme for region split and merge image segmentation. Region splitting is done using a parallel pixel network. We propose a modified merging criterion to reduce the execution time and corresponding hardware implementation is also proposed. We have shown the modified merge criterion will reduce the number of merging iteration steps. Implementation results are encouraging as the processing time in hardware with a 100MHz clock in XILINX VIRTEX IV FPGA is achieved a few order lower than the software implementation.

关键词： image Segmentation FPGA Split and Merge

来源：评论

学校读者我要写书评

暂无评论

Psychophysiomatics: A new perspective in computational life science

Psychophysiomatics: A new perspective in computational life ...

引用

6th International symposium on image and signal processing and Analysis, ISPA 2009

作者： Pham, Tuan D. Fraser, Donald Mayumi, Oyama-Higa ADFA School of Information Technology and Electrical Engineering University of New South Wales Canberra ACT 2600 Australia Department of Integrated Psychological Science Kwansei Gakuin University Nishinomiya City 662-8501 Japan

ISBN: (纸本)9789531841351

Technologies in engineering, information and life sciences are being introduced at a more rapid rate than has been seen for several decades. The interplay of these scientific technologies are unlocking doors to novel interdisciplinary research avenues. This paper presents the concept of psychophysiomatics as a new perspective in the combination of the diverse knowledge of psychiatry, psychology, physiology, computational science and engineering. With this combination it is hoped to discover new findings at systems level of the life science.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Norm-Aware Margin Assignment for Person Re-Identification

引用

ieee signal processing LETTERS 2022年 29卷 1292-1296页

作者： Huang, Zongheng He, Botao Yang, Bo Gao, Changxin Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Opt & Elect Informat Wuhan 430074 Peoples R China

Margin-based metric losses have shown great success in Person Re-identification and Face Verification. But most existing works adopt a fixed class-level margin regardless of the difference between each training sample. This paper proposes a Norm-Aware Margin Assignment (NAMA) scheme to dynamically adjust the weight of each sample during training. Combined with the existing margin-based classification losses, NAMA improves the robustness of feature embedding by assigning larger margins to more recognizable samples. NAMA is a fully trainable module that automatically models the correlation between the optimal margin and image quality during back-propagation without supervision. To stabilize the training and make the assigned margin more controllable, we introduce a margin re-balance mechanism to align the expectation of learned margins to a pre-defined value. Extensive experiments on three popular ReID benchmarks validate the effectiveness of our NAMA method. Code will be publicly available at: https://***/huangzongheng/NAMA.

关键词： Training image quality Measurement Correlation Visualization Feature extraction Benchmark testing Deep learning person re-dentification metric learning

来源：评论

学校读者我要写书评

暂无评论

ECA Rule-based IO Agent Framework for Greenhouse Control System

ECA Rule-based IO Agent Framework for Greenhouse Control Sys...

引用

1st International symposium on computational intelligence and Design

作者： Lin Dongliang Zhang Kanyu Li Xiaojing Shanghai Univ Dept Mech & Elect Engn & Automat Shanghai 200072 Peoples R China

ISBN: (纸本)9780769533117

In greenhouse environment control system, the diversity of IO interfaces and changing requirement for sensors and actuators make system complex and difficult to maintain. A distributed IO agent network architecture is designed for measurement and manipulation in the control system. The IO agent can be attached various sensors and actuators. An ECA rule based software framework is implemented for IO agents. The ECA rule set can be used to describe IO workflow and defined the IO behavior of the agents. The ECA rule based IO agents encapsulates the hardware interfaces and make the control system easily adapt to different requirements through configuration.

关键词： Control systems Sensor systems Actuators Hardware Centralized control Communication system control Automatic control Computer architecture signal processing Chromium

来源：评论

学校读者我要写书评

暂无评论

computational Medical and Health Care Technology

Computational Medical and Health Care Technology

引用

ieee 43rd International symposium on Multiple-Valued Logic (ISMVL)

作者： Hata, Yutaka Nakajima, Hiroshi Univ Hyogo Himeji Initiat Computat Med & Hlth Technol Himeji Hyogo 6712201 Japan

ISBN: (纸本)9781467360678;9780769549767

This paper describes practical applications on computational medical and health care technology. First, we briefly describe medical image processing for diagnosing. Next, we demonstrate three ultrasonic surgery support systems for orthopedic surgeon, rectum cancer surgeon and urologist. In them, image and signal processing plays a primary role to solve each problem. Second, we describe home health care system. This goal is not clinical use but home use to pay consciousness to health. In it, we introduce a mat senor system, which detects heart rate and respiration, and a thermopile senor system, which detects human moving trajectory. Finally, body weight prediction methods are shown by using autoregressive model. As the results, the models successfully predict the body weights.

关键词： medical imaging health care surgery support soft computing

来源：评论

学校读者我要写书评

暂无评论

Method for real-time signal processing via wavelet transform

Method for real-time signal processing via wavelet transform

引用

International Conference on Non-Linear Speech processing

作者： Rajmic, P Brno Univ Technol Fac Elect Engn & Commun Technol Dept Telecommun Brno 61200 Czech Republic

ISBN: (纸本)3540312579

The new method of segmented wavelet transform (SegWT) makes it possible to compute the discrete-time wavelet transform of a signal segment-by-segment. This means that the method could be utilized for wavelet-type processing of a signal in "real time", or in case we need to process a long signal (not necessarily in real time), but there is insufficient computational memory capacity for it (for example in the signal processors). Then it is possible to process the signal part-by-part with low memory costs by the new method. The method is suitable also for the speech processing, e.g. denoising the speech signal via thresholding the wavelet coefficients or speech coding. In the paper, the principle of the segmented forward wavelet transform is explained and the algorithm is described in detail.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Binocular vision system design and its active object tracking

Binocular vision system design and its active object trackin...

引用

2011 4th International symposium on computational intelligence and Design, ISCID 2011

作者： Tian, Longfei Wu, Licheng Wang, Yan Yang, Guosheng School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China School of Information Engineering Minzu University of China Beijing 100081 China

ISBN: (纸本)9780769545004

A binocular vision system having the ability of actively tracking moving objects is designed and implemented. Management software is also developed for further study. Then the crucial technologies concerned with active tracking of one moving object by such a binocular system have been studied. The general architecture is firstly analyzed, and then the realization of target detection and tracking algorithm is given. Finally, a complete corresponding mechanism in the tracking process for the two cameras in case that they track different targets is proposed and discussed. © 2011 ieee.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

FOURIER DIFFRACTION THEOREM FOR 3D ULTRASOUND IMAGING WITH A ROW-COLUMN ARRAY 21

FOURIER DIFFRACTION THEOREM FOR 3D ULTRASOUND IMAGING WITH A...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Hagemeyer, Paul Lisson, Thomas Dencks, Stefanie Schmitz, Georg Ruhr Univ Bochum Chair Med Engn Bochum Germany

ISBN: (纸本)9798350313345;9798350313338

Row-column arrays (RCAs) have been shown to produce high-resolution, three-dimensional ultrasound volumes while reducing the number of electronic connections. Typically, standard reconstruction methods in the time domain such as delay-and-sum (DAS) beamforming have been applied. Here, we derive the Fourier diffraction theorem for reconstructing 3D volumes from backscattered data obtained using an RCA with broadband plane wave excitation under a range of angles. Based on this theory, we propose a novel spatial frequency domain method that offers additional theoretical insight for the optimization of RCA beamforming. In comparison to time domain methods, it also promises higher computational efficiency by using the fast Fourier transform and it enables alternative signal processing and filtering schemes in the frequency domain. We validate our reconstruction algorithm with simulation data. The results demonstrate improved image quality and resolution compared to DAS beamforming.

关键词： Row-column array three-dimensional image reconstruction Fourier diffraction theorem filtered backpropagation algorithm ultrasound beamforming

来源：评论

学校读者我要写书评

暂无评论

Magnetic Properties-Based Range image Descriptor 15

Magnetic Properties-Based Range Image Descriptor

引用

15th International symposium on computational intelligence and Design, ISCID 2022

作者： Li, Taifeng Chen, Bo Zhang, Feifei Lin, Kun Dong, Qiang Purification Equipment Research Institute of CSIC Handan China

ISBN: (纸本)9781665456166

With the development of a new generation of information technology, range images are being used more and more in the fields of image processing, computer vision, and pattern recognition. More concretely, range images play an increasingly important role in autopilot, medical analysis, and quality inspection. As we all know, the range image is composed of a series of three-dimensional (3D) scattered points. Due to limitations of coordinate data, it makes extremely difficult to distinguish the difference between adjacent points. This paper is such an attempt to address this issue. Through the similarity analysis of electron cloud and range image, this paper presents a range image descriptor based on magnetic properties. Benefit from the classical theory of particle motion in magnetic field, Lorentz force, rotation radius, rotation period, and volume ratio parameters are calculated for each point. On that basis, a complete range image descriptor is designed to encode the potential connection of each point from a higher dimension. Experimental results show the discriminating power of the proposed method. Focusing on range image description, the simple structure of our algorithm can effectively improve the efficiency and accuracy of image processing. © 2022 ieee.

关键词： Magnetic properties

来源：评论

学校读者我要写书评

暂无评论

Equal-intensity map texture modeling for natural scene segmentation 5

Equal-intensity map texture modeling for natural scene segme...

引用

5th ieee Southwest symposium on image Analysis and Interpretation

作者： Celenk, M Zhou, Q Chelberg, D Ohio Univ Sch Elect Engn & Comp Sci Stocker Ctr Athens OH 45701 USA

ISBN: (纸本)0769515371

For accurate segmentation of natural scenes, there is a need for powerful, yet simple, color and texture models [7]. Many of the existing segmentation techniques are able to segment homogeneous color scenes as well as the textured images. Despite their computational power, these methods require the estimation of model parameters that are usually difficult to obtain. We propose a simple, yet effective, image model that can efficiently, describe natural textures for color scene segmentation and, in turn, be utilized in texture synthesis.

关键词： Computer science image analysis image reconstruction image segmentation image texture analysis Layout Lighting Parameter estimation Pixel Robustness

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：