检索结果-内蒙古大学图书馆

International Conference on Advanced Communication Control and Computing Technologies*

作者： Santosh, D. Harihara Mohan, P. G. Krishna JNTU Coll Engn Hyderabad Andhra Pradesh India Inst Aeronaut Engn Dept ECE Hyderabad Andhra Pradesh India

ISBN: (纸本)9781479939145

Object tracking is a primary step for image processing applications like object recognition, navigation systems and surveillance systems. The current image and the background image is differentiated by approaching conventionally in image processing. Image subtraction based algorithms are mainly used in extracting features of moving objects and take the information in frames. Here three algorithms namely Extended Kalman Filter, Gaussian Mixture Model (GMM), mean shift algorithm are compared in the context of multiple object tracking. The comparative results show that GMM performs well when there are occlusions. Extended Kalman filter fails because of abnormal behavior in the distribution of random variables when there is nonlinear transformation. It cannot identify multiple objects when there are occlusions. mean shift algorithm is best suitable for single object tracking and is very sensitive to window size which is adaptive. Results show that this algorithm has the limitation to detect multiple objects when there is even slight occlusion.

关键词： Gaussian mixture model Extended Kalman Filter mean shift algorithm multiple object tracking background subtraction foreground detection

来源：评论

学校读者我要写书评

暂无评论

Implementation of the parallel mean shift-based imagesegmentation algorithm on a GPU cluster

引用

International Journal of Digital Earth 2019年第3期12卷 328-353页

作者： Fang Huang Yinjie Chen Li Li Ji Zhou Jian Tao Xicheng Tan Guangsong Fana School of Resources&Environment University of Electronic Science and Technology of ChinaChengduPeople’s Republic of China Institute of Remote Sensing Big Data Big Data Research CenterUniversity of Electronic Science and Technology of ChinaChengduPeople’s Republic of China School of Construction&Management Engineering Xihua UniversityChengduPeople’s Republic of China Texas A&M Engineering Experiment Station and High Performance Research Computing Texas A&M UniversityCollege StationTXUSA International School of Software Wuhan UniversityWuhanPeople’s Republic of China

The mean shift image segmentation algorithm is very computationintensive. To address the need to deal with a large number of remotesensing (RS) image segmentations in real-world applications, this studyhas investigated the parallelization of the mean shift algorithm on asingle graphics processing unit (GPU) and a task-scheduling methodwith message passing interface (MPI)+OpenCL programming model on aGPU cluster platform. This paper presents the test results of the parallelmean shift image segmentation algorithm on Shelob, a GPU clusterplatform at Louisiana State University, with different datasets andparameters. The experimental results show that the proposed parallelalgorithm can achieve good speedups with different configurations andRS data and can provide an effective solution for RS image processingon a GPU cluster.

关键词： mean shift algorithm GPU cluster task scheduling MPI OpenCL

来源：评论

学校读者我要写书评

暂无评论

Fusion of Kalman filter to improve the KFMS algorithm and its application in parallel robots

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE 2025年

作者： Mei, Jiangping Su, Xiaochen Le, Yuxin Ning, Puxuan Wei, Tianlin Tianjin Univ Sch Mech Engn Tianjin 300350 Peoples R China

An improved mean shift target tracking algorithm integrated with the Kalman Filter (KFMS algorithm) is proposed to address the challenge of accurately tracking targets in complex environments using parallel robots. This algorithm combines the local search capability of the mean shift algorithm with the state estimation capability of the Kalman Filter, reducing the impact of complex environments on tracking performance. It achieves accurate global tracking of targets by the camera, effectively improving the stability and accuracy of dynamic target tracking. Experimental results with a local camera show that the target tracking accuracy and success rate of the improved KFMS algorithm are increased by 21.3% and 29.6%, respectively, compared to the mean shift algorithm, further validating the effectiveness of the enhanced algorithm.

关键词： Visual servoing mean shift algorithm Kalman filter high-speed parallel robots

来源：评论

学校读者我要写书评

暂无评论

Construction of rural landscape design system based on support vector machine and mean drift algorithm

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2025年

作者： Li, Hanjiang Li, Jiaojiao Hefei Univ Sch Design Hefei 230601 Peoples R China Hefei Ind Sch Dept Costume & Culture & Art Hefei Peoples R China

With the theory of beautiful China, the construction and planning of rural landscapes are getting more and more attention. However, China's rural landscape design lacks innovation and practicality. Therefore, in order to avoid the homogeneity of rural landscape design, it is necessary to ensure that rural landscape designs are consistent with the sustainable development of the rural area system. The study is based on the vector machine and the mean shift algorithm in remote sensing control for the segmentation and feature extraction of architectural images, using the function weight addition and the introduction of background suppression factor, to develop a model and algorithms that are more suitable for the diversified features of the buildings. The results indicate that the research method has a maximum accuracy of 99% in extracting architectural images, and the image quality evaluation can reach 100%. In the application analysis, it was found that the economic benefit of unused land in the countryside was low, and the green conservation information of ancient villages in the landscape was 57.3%. Therefore, the model designed by the study has good integrity for architectural image feature extraction, good accuracy, high image quality, and good application value for countryside landscape design.

关键词： rural landscapes landscape design background suppression image feature extraction vector machine mean shift algorithm function weight

来源：评论

学校读者我要写书评

暂无评论

Kernel Smoothing, mean shift, and Their Learning Theory with Directional Data

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2021年第1期22卷 1-92页

作者： Zhang, Yikun Chen, Yen-Chi Univ Washington Dept Stat Seattle WA 98195 USA

Directional data consist of observations distributed on a (hyper)sphere, and appear in many applied fields, such as astronomy, ecology, and environmental science. This paper studies both statistical and computational problems of kernel smoothing for directional data. We generalize the classical mean shift algorithm to directional data, which allows us to identify local modes of the directional kernel density estimator (KDE). The statistical convergence rates of the directional KDE and its derivatives are derived, and the problem of mode estimation is examined. We also prove the ascending property of the directional mean shift algorithm and investigate a general problem of gradient ascent on the unit hypersphere. To demonstrate the applicability of the algorithm, we evaluate it as a mode clustering method on both simulated and real-world data sets.

关键词： Directional data mean shift algorithm kernel smoothing mode clustering optimization on a manifold

来源：评论

学校读者我要写书评

暂无评论

Design of a Real-Time Monitoring and Early Warning System for Engineering Safety Hazards Using Image Analysis Technology

引用

TRAITEMENT DU SIGNAL 2024年第5期41卷 2381-2390页

作者： Xing, Haoran Univ New South Wales Art Design & Architecture Sydney 2033 Australia

As the scale of engineering projects continues to grow, safety management on construction sites faces significant challenges. Traditional methods such as manual inspections and periodic checks struggle to achieve real-time and effective monitoring of potential hazards, which can lead to accidents. In recent years, image analysis technology has increasingly been applied to the monitoring of engineering safety hazards due to its automation, Areal-time capabilities, and high efficiency. However, existing image analysis algorithms still encounter issues such as insufficient tracking accuracy and delayed warning responses in complex engineering environments. To address these problems, this study proposes aArealtime hazard tracking and identification method based on an improved mean shift algorithm, combined with a support vector machine (SVM) for critical state early warning of engineering safety hazards. The system improves recognition accuracy and early warning response speed in complex environments through algorithm optimization, offering higher practicality and reliability. This provides a technical safeguard for safety management at construction sites.

关键词： engineering safety hazards image analysis mean shift algorithm support vector machine (SVM) Areal-time monitoring early warning system

来源：评论

学校读者我要写书评

暂无评论

The Improvement of mean- shift algorithm and Kalman Filter of Tracking Moving Targets in the video of Robotic Fish

The Improvement of Mean- Shift Algorithm and Kalman Filter o...

引用

2015 4th International Conference on Mechatronics,Materials,Chemistry and Computer Engineering(ICMMCCE 2015)

作者： Jingying Wu Wei Xiang Institute of Electrical and Information Engineering Southwest University for Nationalities

ISBN: (纸本)9781510817371

Several defects have been found in the former experiments of basic mean shift algorithm, such as the erroneous judgments when target blocked by a large proportion of barrier. Thus, a fast target tracking algorithm based on mean shift combined Kalman filter is proposed for the theoretical defect of basic mean shift. The blocking issue and tracking of fast moving target are discussed in this paper and applied in the independent visual robotic fish tracking. Here are our conceptions: Firstly, the initial position of mean shift is provided with Kalman filter in every frame, then mean shift algorithm is used to track the position of target. Secondly, the calculation of the Kalman residuals is applied to turn on and turn off the Kalman filter under a large proportion of blocking situation, at the same time, the linear prediction of the target position is replaced by Kalman's function test. Finally, we conduct a real-time tracking experiment on the independent visual robotic fish tracking a moving ball, it is proved that the algorithm can achieve the tracking of fast moving target and robust against the barrier as well.

关键词： mean shift algorithm Kalman residuals Kalman filter Target tracking

来源：评论

学校读者我要写书评

暂无评论

Eye-state analysis using an interdependence and adaptive scale mean shift (IASMS) algorithm

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2014年第1期11卷 53-62页

作者： Ibrahim, Masrullizam Mat Soraghan, John J. Petropoulakis, Lykourgos Univ Tekn Malaysia Melaka Fac Elect & Comp Engn Durian Tunggal 76100 Melaka Malaysia Univ Strathclyde Dept Elect & Elect Engn Ctr Excellence Signal & Image Proc CeSIP 204 George St Glasgow G1 1XW Lanark Scotland

Eye state analysis in real-time is a main input source for Fatigue Detection Systems and Human Computer Interaction applications. This paper presents a novel eye state analysis design aimed for human fatigue evaluation systems. The design is based on an interdependence and adaptive scale mean shift (IASMS) algorithm. IASMS uses moment features to track and estimate the iris area in order to quantify the state of the eye. The proposed system is shown to substantially improve non-rigid eye tracking performance, robustness and reliability. For evaluating the design performance an established eye blink database for blink frequency analysis was used. The design performance was further assessed using the newly formed Strathclyde Facial Fatigue (SFF) video footage database(1) of controlled sleep-deprived volunteers. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： mean shift algorithm Eye tracking Eye state analysis Adaptive scale Fatigue assessment

来源：评论

学校读者我要写书评

暂无评论

Multiple Objects Tracking Using Extended Kalman Filter, GMM and mean shift algorithm - A comparative Study

Multiple Objects Tracking Using Extended Kalman Filter, GMM ...

引用

International Conference on Advanced Communication Control and Computing Technologies

作者： D. Harihara Santosh P.G. Krishna Mohan JNTU College of Engineering Hyderabad Andhra Pradesh Department of ECE Institute of Aeronautical EngineeringHyderabad Andhra Pradesh

ISBN: (纸本)9781479939152

关键词： Gaussian mixture model Extended Kalman Filter mean shift algorithm multiple object tracking background subtraction foreground detection

来源：评论

学校读者我要写书评

暂无评论

Application of 3D image processing technology based on image segmentation in packaging design

引用

INTERNATIONAL JOURNAL OF INTERACTIVE DESIGN AND MANUFACTURING - IJIDEM 2023年 1-12页

作者： Jin, Xiaoxiao Shanghai Publishing & Printing Coll Dept Art Design Shanghai 200093 Peoples R China

Recent years, the methods to combine artificial intelligence technology with 3D image processing technology has become a hub for research in packaging design. Traditional 3D images are mostly produced by professional equipment, but this method is small in scope and high in cost, which does not meet the needs of most people. To solve the above problems, this study combines the mean shift algorithm with the confidence propagation algorithm, and obtains the confidence propagation-mean shift algorithm. In addition, the Lucascanard-confidence factor optical flow algorithm is improved by introducing the confidence factor to the Lucascanard-confidence factor optical flow algorithm. The research continues to combine the confidence propagation-mean shift algorithm with the Lucaskarnad-confidence factor optical flow algorithm to extract parallax maps and then synthesize 3D images. The results show that the iteration times and iteration time of the confidence propagation-mean shift algorithm are 9 times and 97.05 s, respectively. The number of parallax templates and the number of regions is 6 and 43 respectively. The confidence propagation-mean shift algorithm has 4 iterations, 36.8 s iteration time, 14 parallax templates and 65 regions in the category of portrait images. The accuracy of foreground depth, background depth and depth are 99.72, 99.87 and 99.80%, respectively, for the Lucas Kanard-confidence factor optical flow algorithm. In summary, the two algorithms proposed in this study have excellent performance, which can extract parallax map well and generate 3D image accurately, owning certain promotion value in the field of product packaging design.

关键词： Packaging design field mean shift algorithm Confidence propagation algorithm Confidence factor Multi-resolution stepwise refinement strategy

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：