检索结果-内蒙古大学图书馆

作者： SURBHI SHARMA University of Twente

学位级别：硕士

To elucidate the information present in a remote sensing image, classification has helped significantly. With the presence of uncertainties in remotely sensed images, soft classification techniques are often considered. The desideratum for good classification accuracies with minimized efforts has led to the options where a few labeled data could enhance the classification accuracies. In this research, a semi- supervised approach is considered to minimize the efforts in collecting huge labeled training samples which is often strenuous and time-consuming. To handle uncertainties better, a Possibilistic c means classifier is used and considered with different approaches as per the labeled training data. The similarity between two pixel vectors becomes important when it comes to collecting unlabeled data in a semi- supervised approach, or when the classification is performed based on assigning more membership values to similar pixels. The hybrid spectral similarity measures, Spectral Information Divergence with Spectral Angle Measure and Spectral Information Divergence with Spectral Correlation Angle are used to measure the similarity between two pixel vectors due to their proven capabilities for capturing high band-to-band variability for a hyperspectral imagery. Their roles are studied in view of a multispectral imagery. The Possibilistic c means classifier is used with semi-supervised training data using different hybrid measures. Due to the availability of a few labeled training samples, mean shift algorithm is employed to refine the training data and to shift the mean for a Possibilistic c means classification algorithm to a higher density region. In addition, the proposed methods relate the bandwidth parameter from mean shift algorithm to the bandwidth or resolution parameter of Possibilistic c means classifier with an iterative procedure to capture the class variances. The methods are applied to an input LANDSAT-8 imagery with 30 m spatial resolution. The classif

关键词： Possibilistic c means Semi-supervised learning mean shift algorithm Spectral similarity measures

来源：评论

学校读者我要写书评

暂无评论

Adaptive Color Optimization algorithm Based on Machine Vision 2

Adaptive Color Optimization Algorithm Based on Machine Visio...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Yang, Ning Jiang, Tianyu Sun, Xin College of Art and Design Changchun Humanities and Sciences College Jilin Changchun China

ISBN: (纸本)9798350372892

With the rapid development of computer technology, there are more and more electronic products such as smart phones, digital cameras, cameras and other kinds of electronic products, and people can easily obtain a variety of images for recording their life and work. However, due to the limitations of photographic technology, there is often a certain gap between the images people obtain and the reality of the scene, such as underexposure, overexposure, low contrast and so on. Therefore, how to adjust the image to improve the visual effect of the image has become a popular topic. The innovation of this paper is to improve the computational efficiency of the algorithm under the premise of ensuring image color clarity, contrast and sharpness, so as to achieve fast and efficient intelligent optimization of image color. The experimental results showed that the algorithm could achieve good color optimization effects in different scenes and image types, and had strong practicality and promotion value. The mean shift algorithm had a processing time of 0.4-0.55ms for image color optimization, which was relatively efficient. © 2024 IEEE.

关键词： adaptive color optimization machine vision mean shift algorithm RGB space

来源：评论

学校读者我要写书评

暂无评论

A Circle Center Location algorithm Based on Sample Density and Adaptive Thresholding

引用

APPLIED SCIENCES-BASEL 2024年第18期14卷 8453页

作者： Min, Yujin Chen, Hao Chen, Zhuohang Zhang, Faquan Wuhan Text Univ Sch Econ Wuhan 430200 Peoples R China Wuhan Text Univ Sch Elect & Elect Engn Wuhan 430200 Peoples R China

How to acquire the exact center of a circular sample is an essential task in object recognition. Present algorithms suffer from the high time consumption and low precision. To tackle these issues, we propose a novel circle center location algorithm based on sample density and adaptive thresholding. After obtaining circular contours through image pre-processing, these contours were segmented using a grid method to obtain the required coordinates. Based on the principle of three points forming a circle, a data set containing a large number of samples with circle center coordinates was constructed. It was highly probable that these circle center samples would fall within the near neighborhood of the actual circle center coordinates. Subsequently, an adaptive bandwidth fast Gaussian kernel was introduced to address the issue of sample point weighting. The mean shift clustering algorithm was employed to compute the optimal solution for the density of candidate circle center sample data. The final optimal center location was obtained by an iteration algorithm. Experimental results demonstrate that in the presence of interference, the average positioning error of this circle center localization algorithm is 0.051 pixels. Its localization accuracy is 64.1% higher than the Hough transform and 86.4% higher than the circle fitting algorithm.

关键词： sampling density circle center location mean shift algorithm kernel function

来源：评论

学校读者我要写书评

暂无评论

A kernel-based method for markerless tumor tracking in kV fluoroscopic images

引用

PHYSICS IN MEDICINE AND BIOLOGY 2014年第17期59卷 4897-4911页

作者： Zhang, Xiaoyong Homma, Noriyasu Ichiji, Kei Abe, Makoto Sugita, Norihiro Takai, Yoshihiro Narita, Yuichiro Yoshizawa, Makoto Tohoku Univ Grad Sch Med Sendai Miyagi 980 Japan Tohoku Univ Grad Sch Engn Sendai Miyagi 980 Japan Hirosaki Univ Grad Sch Med Hirosaki Aomori Japan Tohoku Univ Cybersci Ctr Sendai Miyagi 980 Japan

Markerless tracking of respiration-induced tumor motion in kilo-voltage (kV) fluoroscopic image sequence is still a challenging task in real time image- guided radiation therapy (IGRT). Most of existing markerless tracking methods are based on a template matching technique or its extensions that are frequently sensitive to non-rigid tumor deformation and involve expensive computation. This paper presents a kernel-based method that is capable of tracking tumor motion in kV fluoroscopic image sequence with robust performance and low computational cost. The proposed tracking system consists of the following three steps. To enhance the contrast of kV fluoroscopic image, we firstly utilize a histogram equalization to transform the intensities of original images to a wider dynamical intensity range. A tumor target in the first frame is then represented by using a histogram-based feature vector. Subsequently, the target tracking is then formulated by maximizing a Bhattacharyya coefficient that measures the similarity between the tumor target and its candidates in the subsequent frames. The numerical solution for maximizing the Bhattacharyya coefficient is performed by a mean-shift algorithm. The proposed method was evaluated by using four clinical kV fluoroscopic image sequences. For comparison, we also implement four conventional template matching-based methods and compare their performance with our proposed method in terms of the tracking accuracy and computational cost. Experimental results demonstrated that the proposed method is superior to conventional template matching-based methods.

关键词： radiation therapy markerless tumor tracking computer vision mean shift algorithm

来源：评论

学校读者我要写书评

暂无评论

Tracking of Entities in Multi-sport Field

引用

Procedia Computer Science 2015年 45卷 300-304页

作者： Khyati K. Vyas Kevin Vira Ruhina Karani Computer Engineering Dwarkadas J.Sanghvi College of Engineering Vile Parle (W) Mumbai-400056 India Assistant Professor Computer Engineering Dwarkadas J.Sanghvi College of Engineering Vile Parle (W) Mumbai-400056 India

Object tracking is the key feature of video analysis. In this paper, we present a method to track object in a multi-sport field. mean shift algorithm is a kernel tracking approach which tracks on the basis of color and shape of the target object. Due to constant motion in a playground, it is difficult to track the same body because of changing color and direction. Hence we introduce a novel method, Incremental Discriminative Color Object Tracking to track entities on a sports ground. We have proposed to modify certain elements of the original mean shift algorithm so as to track entities in video streams with changing color, shape and direction. The trajectory formed from this method enables us to calculate the distance covered by an entity in the field.

关键词： mean shift algorithm IDCT Video Analysis Object tracking Sports.

来源：评论

学校读者我要写书评

暂无评论

A medical tracking system for contrast media

A medical tracking system for contrast media

引用

2010 International Conference on Life System Modeling and Simulation & 2010 International Conference on Intelligent Computing for Sustainable Energy and Environment

作者： Chuan Dai, Zhelong Wang and Hongyu Zhao Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian, 116024.CHINA,

Contrast media is a kind of chemical substance used to improve the image quality of Computed Tomography. However, due to its high speed of injection, emergencies (such as capillary hemorrhage) always exist. In view of this problem, a video object tracking system is implemented to monitor the injection site. The color feature is abstracted from image sequences and used for the mean shift tracking algorithm. The experiment results show that the tracking system is real-time, robust and efficient.

关键词： Tracking Visual tracking Color histogram mean shift algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Detection and Tracking

Real-Time Human Detection and Tracking

引用

Annual IEEE India Conference

作者： Swapnil V. Tathe Sandipan P. Narote Sinhgad College of Engineering Pune India

ISBN: (纸本)9781479922765

Real-time human detection and tracking is a vast, challenging and important field of research. It has wide range of applications in human recognition, human computer interaction (HCI), video surveillance etc. The research for biometric authentication of a person has reached far but the real-time tracking of human beings has not gained much importance. Tracking of human being can be used as a prior step in biometric face recognition. Keeping continuous track of person will allow to identify person at any time. The system consist of two parts first human detection and secondly tracking. Human detection step is split into face detection and eye detection. Face is a vital part of human being represent most important information about the individual. Eyes are the important biometric feature used in person identification. Face detection is done using skin color based methods. YC_bC_r color model is used to detect skin regions as it represents intensity and color information separately. For eye region detection projection function and pixel count methods are used. Finally the mean shift algorithm and kalman filter algorithm is used for tracking.

关键词： Face Detection Eye Detection Projection Function Kalman Filter mean shift algorithm

来源：评论

学校读者我要写书评

暂无评论

SUPERCUT: AN ACCURATE AND EFFECTIVE INTERACTIVE IMAGE SEGMENTATION algorithm

SUPERCUT: AN ACCURATE AND EFFECTIVE INTERACTIVE IMAGE SEGMEN...

引用

IEEE International Conference on Image Processing

作者： Qingsong Zhu Ling Shao Zhan Song Yaoqin Xie Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Electronic and Electrical Engineering University of Sheffield Sheffield UK The Chinese University of Hong Kong Hong Kong China

ISBN: (纸本)9781479923427

The task of interactive image segmentation has attracted a significant attention in recent years. The ultimate goal is to extract an object with as few user interactions as possible. In this paper, we present SUPERCUT, a novel interactive algorithm for foreground object extraction and segmentation in images. In the algorithm, the mean shift algorithm with a boundary confidence prior is introduced to efficiently presegment the original image into super-pixels with precise boundary. Secondly, a Bayes decision theory is introduced to model and cluster the super-pixels so as to obtain an initial effective classification of super-pixels. To achieve a more accurate object segmentation result, a boundary refinement using Interactive rectangle box with GMM learning is adopted. Experimental results on a benchmark data set show that the proposed framework is highly effective and can accurately segment a wide variety of natural images with ease.

关键词： Interactive Image segmentation mean shift algorithm Graph cut Interactive box images image segmentation Interactive Object segmentation Decision Theory algorithms original image Boundary boundary layer extraction of object

来源：评论

学校读者我要写书评

暂无评论

ROBUST UNSUPERVISED NONPARAMETRIC CHANGE DETECTION OF SAR IMAGES

ROBUST UNSUPERVISED NONPARAMETRIC CHANGE DETECTION OF SAR IM...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Andrea Garzelli Claudia Zoppetti Bruno Aiazzi Stefano Baronti Luciano Alparone Dept. Information Engineering University of Siena IFAC-CNR Research Area of Florence Dept. Electron. & Telecomm University of Florence

ISBN: (纸本)9781467311601

This paper presents an unsupervised nonparametric method for change detection in multitemporal synthetic aperture radar (SAR) imagery. The proposed method relies on a novel feature capable of capturing the structural changes between the two images and discarding almost completely the statistical changes due to speckle patterns or co-registration inaccuracies. This feature utilizes the scatterplots of the amplitude levels in the two SAR images and applies a fast version of the mean-shift (MS) algorithm to find the modes of the underlying bivariate distribution. The value of the probability density function (PDF) is translated to a value of conditional information and given to all image pixels originating such modes. Experimental results have been carried out with simulated changes and true SAR images acquired by the COSMO-SkyMed satellite constellation. The proposed feature exhibits significantly better discrimination capability than both the classical log-ratio (LR) and is particularly robust if applied to SAR images having different processing and/or. acquisition angles.

关键词： Change detection Information-theoretic features mean shift algorithm Multi-temporal images Non-parametric methods Synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Target Tracking algorithm based on Multi-feature Fusion

An Adaptive Target Tracking Algorithm based on Multi-feature...

引用

International Conference on Biomedical Engineering and Computer Science

作者： Shengzhi Yuan Jian hua Li Jianli Han Department of ordnance science and technology naval aeronautical and astronautical university Department of scientific research naval aeronautical and astronautical university

ISBN: (纸本)9781424453153;9781424453160

although widely used in practice for real time ability, the mean shift algorithm was weak at target model description and was robust for infrared image sequences form motion platform. In order to enhance the adaptability and target description ability of the mean shift algorithm, meanwhile to make up the shortcomings of the nuclear density estimation based on gradation feature, an adaptive Kalman-mean shift algorithm based on multi-feature fusion was proposed. A target description mode based on gradation-edge feature fusion was applied, while a scale updating item of tracking window was used in the mean shift algorithm based on the relation between mutual information and the object scale. Experimental results demonstrate that the adaptability of mean shift algorithm is enhanced by the improved algorithm, which is effectively applied in the tracking problem for the object of scale variance in long time tracking process.

关键词： Multi-feature fusion Target tracking mean shift algorithm Mutual information

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：