检索结果-内蒙古大学图书馆

A Smart Mathematic Morphology Method for recognition and Understanding of Airfield

Wuhan University Journal of Natural Sciences 2005年第5期10卷 867-872页

作者： WANG Zhi-cheng TIAN Yan TIAN Jin-wen LIU Jian LIANG Chao-sheng TAO Wen-bin State Education Commission Key Laboratory for Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan430074 Hubei China Department of Electronics and Information Engineering Huazhong University of Science and Technology Wuhan 430074 Hubei China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 Hubei China

A method used for recognition and understanding of airfield based on mathematical morphology is proposed in this paper. The new approach can he divided into three steps. First, to extract the typical geometric structure features of airfield, a segmentation method called recursive Otsu algorithm is employed on an airfield image. Second, thinning and shrinking algorithms are utilized to obtain the contour of airfield with single pixel and to remove diffused small particles. Finally, Radon transform is adopted to extract two typical and important components, primary and secondary runways of airfield exactly. At the same time, region growing algorithm is exploited to get the other components such as parking apron and garages. The experimental results demonstrate that the proposed method gives good performance.

关键词： mathematical morphology shrinking algorithm Radon transform Region growing

来源：评论

学校读者我要写书评

暂无评论

Efficient VLSI architecture for multi-dimensional discrete wavelet transform

Efficient VLSI architecture for multi-dimensional discrete w...

引用

MIPPR 2005: SAR and Multispectral Image processing

作者： Xiong, Cheng-Yi Tian, Jin-Wen Liu, Jian College of Electronic Information Engineering South-Center University for Nationalities Wuhan 430074 China Institute of Pattern Recognition and Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

Efficient VLSI architectures for multi-dimensional (m-D) discrete wavelet transform (DWT), e.g. m=2, 3, are presented, in which the lifting scheme of DWT is used to reduce efficiently hardware complexity. The parallelism of 2 m subbands transforms in lifting-based m-D DWT is explored, which increases efficiently the throughput rate of separable m-D DWT. The proposed architecture is composed of m2m-1 1-D DWT modules working in parallel and pipelined, which is designed to process 2m input samples per clock cycle, and generate 2m subbands coefficients synchronously. The total time of computing one level of decomposition for a 2-D image (3-D image sequence) of size N2 (MN2) is approximately N2/4 (MN2/8) intra- clock cycles (ccs). An efficient line-based architecture framework for both 2D+t and t+2D 3-D DWT is first proposed. Compared with the similar works reported in previous literature, the proposed architecture has good performance in terms of production of computation time and hardware cost. The proposed architecture is simple, regular, scalable and well suited for VLSI implementation.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Background suppression based-on wavelet transformation to detect infrared target

Background suppression based-on wavelet transformation to de...

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Sun, Y.U.-Qiu Tian, Jin-Wen Liu, Jian School of Information and Mathematics Yangtze University Jingzhou 434023 China State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China State Education Commission Key Laboratory for Image Processing and Intelligent Control Dept. of Electronic Information and Enginery Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)078039092X

Target detection and location in infrared clutter background is very important to infrared search and track system. Especially for small target detection in infrared image in background of sea and sky, there are no geometric and structure character to use. When targets such as ship and naval vessel sailing at long distance, they always appear around the sea-level line, and it is mixed with cloud and sea-wave clutter. It is difficult to segment and locate precisely. Background suppression based-on wavelet transformation is proposed in the paper. Wavelet decomposition makes it possible to analyze a signal both in time and frequency domains. In the paper infrared sea and key background images are processed. For their SNR is low and background is complex, using wavelet transformation decomposes an original image and extract approximate feature to reconstruct an image, which mainly includes background information. A new image will be obtained using background image subtracted from original image. There are mainly target and noise points left in the new image. By setting proper threshold, the target can be detected perfectly. At last, experiment results are given and show the method is practical. © 2005 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Two-band Infrared Data Fusion Method Based-on Fractal Dimension

Two-band Infrared Data Fusion Method Based-on Fractal Dimens...

引用

2005 International Conference on Neural Networks and Brain(ICNN&B’05)

作者： Yuqiu Sun Jinwen Tian Jian Liu Image Processing and Intelligence Control Key Laboratory of State Educational Ministry Institute of Pattern Recognition and Artificial IntelligenceHuazhong University of Science and Technology School of information and mathematics Yangtze University Dept.of Electronic Information and Enginery of Huazhong University of Science and Technology

ISBN: (纸本)0780394224

＜正＞Researches indicate that the gray-scale images mapped from most nature objects accord to the fractal Brown stochastic field which foundation is self-similarity,an image is self-similarity means the image is made up of copies of itself in a reduced *** fractal dimension can quantificational depict the fractal character and the property of an image. Therefore,a new method based-on fractal dimension to fuse mid-wave infrared images and long-wave infrared images is presented in the ***,images are decomposed into different scale using wavelet ***,the fractal dimensions of sub-images of original images are computed,and then take them as weight to fuse sub-images at the same level according to different ***,reconstruct the fused images by wavelet inverse *** experimental results imply that the method can effectively preserve the information of source images with a high contrast and may be very practical.

关键词： Fractals Infrared imaging Artificial intelligence Fuses Educational technology Image reconstruction Layout Infrared detectors Intelligent control Process control

来源：评论

学校读者我要写书评

暂无评论

A robust approach to the detection and tracking of small targets with low contrast

A robust approach to the detection and tracking of small tar...

引用

IEEE International Workshop on VLSI Design and Video Technology, IWVDVT

作者： Xinyu Wang Guilin Zhang Ying Chu State Key Laboratory for Image Processing and lntelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780390059

An effective approach to the detection and tracking of small moving targets with low contrast is proposed. In our application, small moving targets are detected and tracked in a low quality video sequence captured from an airborne platform. The detection and tracking system includes three modules. First, the global motion parameters are estimated using fast least trimmed squares (FAST-ITS) regression and hierarchical processing. Once the global motion is robustly estimated, relatively stationary background can be eliminated almost completely through image warping. Then a motion-based fast target detector selects candidate pixels of the moving targets with motions statistically different from that of the background, and a particle filtering tracker examines the temporal consistency of targets to identify them and update their states. Information in the system flows in a closed loop form, in which the tracker instructs the detector where to look for a target, and the detector returns what it has found. Experimental results prove that the proposed method can reliably and effectively detect and track the real small moving target in real-time even if there is strong clutter influence.

关键词： Robustness Target tracking Detectors Motion estimation Video sequences Parameter estimation Motion detection Filtering Particle tracking Tracking loops

来源：评论

学校读者我要写书评

暂无评论

High Performance Reconfigurable Hardware System for real-time Image processing

引用

Journal of Systems Engineering and Electronics 2005年第3期000卷 502-509页

作者： Zhao Guangzhou Zhang Tianxu Wang Yuehuan Cao Zhiguo Zuo Zhengrong State Key Laboratory for Image Processing and Intelligent Control，Inst.for Pattern Recognition and Artificial Intelligence，Huazhong Univ.of Science and Technology，Wuhan 430074，P.R.China

A novel reconfigurable hardware system which uses both multi-DSP and FPGA to attain high performance and real-time image processing are presented. The system structure and working principle of mainly processing multi-DSP board, extended multi-DSP board are analysed. The outstanding advantage is that the communication among different board components of this system is supported by high speed link ports & serial ports for increasing the system performance and computational power. Then the implementation of embedded real-time operating systems (RTOS) by us is discussed in detail. In this system, we adopt two kinds of parallel structures controlled by RTOS for parallel processing of algorithms. The experimental results show that exploitive period of the system is short, and maintenance *** it is suitable for real-time image processing and can get satisfactory effect of image recognition.

关键词： rmulti-DSP field programmable gate arrays real-time image processing real time operating systems paralld structure

来源：评论

学校读者我要写书评

暂无评论

Real-time signal processing system for target tracking based on ADSP21060 and FPGA

Real-time signal processing system for target tracking based...

引用

International Conference on Communications, Circuits and Systems (ICCCAS)

作者： Guangzhou Zhao Tianxu Zhang State Key Laboratory for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780390156

This paper presents a novel real-time signal processing system using for target tracking, it uses both ADSP21060 and FPGA to attain high performance and high-speed image processing. It analyses the flexible hardware architecture based on the idea of reconfigurability and modularization, and discusses three main modules and extensibility of the hardware system. Then the implementation of the image pre-processing and target intelligent tracking algorithm is discussed in detail. The experimental result shows that the system processing rate reaches 30 frames per second. The system can automatically detect targets and output the tracking information in real-time.

关键词： Real time systems Signal processing Target tracking Field programmable gate arrays Digital signal processing Hardware Logic arrays Signal processing algorithms Image processing Image analysis

来源：评论

学校读者我要写书评

暂无评论

Support value based fusing images with different focuses

Support value based fusing images with different focuses

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Sheng Zheng Yu-Qiu Sun Jin-Wen Tian Jian Liu State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China China Three Gorges University Yichang China

Many vision-related processing tasks, including edge detection and image segmentation, can be performed more easily when all objects in the scene are in good focus. However, in practice, this may not be always feasible as optical lenses, especially those with long focal lengths, only have a limited depth of field. One classical approach to recover an everywhere-in-focus image is to use Laplacian pyramid image fusion. First, several source images with different focuses of the same scene are taken and decomposed into the low/high-frequency components image sequences. Within these decompositions, the high-frequency components image sequences with the largest magnitude are selected at each pixel location. Finally, the fused image can be recovered from the decomposed components image sequences. In the support vector machine (SVM), the pixels with larger support values have a physical meaning in the sense that they reveal relative more importance of the data points for contributing to the SVM model. In this paper, we use Laplacian pyramid for the multi resolution decomposition, and then replace the traditional salient features by support values of the mapped least squares (LS)-SVM for fusing image. Experimental results illustrate that the proposed method outperforms the traditional approach.

关键词： Focusing Image sequences Support vector machines Layout Laplace equations Image edge detection Image segmentation Optical sensors Lenses Image fusion

来源：评论

学校读者我要写书评

暂无评论

A combining method for tumors detection from near-infrared breast imaging

A combining method for tumors detection from near-infrared b...

引用

2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

作者： Wang, Zhicheng Liu, Jian Tian, Jinwen Xie, Zeping State Education Commission Key Laboratory for Image Processing and Intelligent Control Huazhong Univ. of Sci. and Tech. Wuhan 430074 China Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Tech. Wuhan 430074 China School of Life Sci. and Tech. Huazhong Univ. of Sci. and Tech. Wuhan 430074 China

ISBN: (纸本)0780387406

This paper introduces the new qualitative and quantitative methods, which can diagnose breast tumors. Qualitative methods include blood vessel display inside and outside of pathological changes part of breast, display of equivalent pixel curves at the part of pathological changes and display of breast tumor image edge. Accordingly, three feature extraction operators are proposed, i.e. the combination operators of anisotropic gradient and smoothing operator, an improved Sobel operator and an edge sharpening operator. Furthermore, quantitative diagnose approaches are discussed based on blood and oxygen contents according to abundant clinical data and pathological mechanism of breast tumors. The results of clinic show that the methods of combining qualitative and quantitative diagnose are effective for breast tumor images, especially for early and potential breast cancer. © 2005 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

An improved mapping method of buffer for line-based architecture of 2-D DWT

An improved mapping method of buffer for line-based architec...

引用

International Conference on Communications, Circuits and Systems (ICCCAS)

作者： Cheng-Yi Xiong Cheng-Jun Wang Jin-wen Tian Jian Liu Institute of Pattern Recognition & Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China College of Electronic Information Engineering South-Center University for Nationalities Wuhan China

ISBN: (纸本)0780390156

The number of arithmetic units used in the one-dimensional (1D) discrete wavelet transform (DWT) is the main consideration for reducing the area of VLSI implementation of 1D DWT, while the size of intermediate memory used for data buffering is another dominate factor of effecting hardware complexity of VLSI implementation for two-dimensional (2D) DWT. In this paper, we exploit the essential relationship between the size of temporal buffer (TB) required in the line-based architecture for 2D DWT (LBA2DDWT) and the number of registers used in the 1D DWT module, and present an improved method of mapping the registers used in the 1D DWT to the TB required in LBA2DDWT. Comparison results with the other design reported in previous literature demonstrate that, the proposed mapping method can reduce efficiently the size of memory required in LBA2DDWT.

关键词： Discrete wavelet transforms Registers Two dimensional displays Very large scale integration Hardware Convolution Pipeline processing Arithmetic Signal analysis 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：