检索结果-内蒙古大学图书馆

2012 International Conference on Intelligent Control and Information Processing (ICIP 2012)

作者： Wang Xing-ju Li Jin-zhao Wei Hong-fei Henan Polytechnic Institute Henan Costar Group

To solve the invalidation problem of Dempster-Shafer evidence theory for high conflicting fusion, this paper improves D-S algorithm based on weighted average method. A new similarity function is proposed to represent similarity, and by normalized similarity we obtain support to pretreated evidences, then, fuse preprocessed evidences by Dempster's rule. The more expected result data shows that, compared with other methods, this new algorithm can reduce harmful influence of false evidence effectively, at the same time, have higher convergence rate and reduce decision risk. Finally, the new similarity function is analyzed to prove the rationality of improved algorithm.

关键词： fusion algorithm D-S evidence theory similarity function weighted average

来源：评论

学校读者我要写书评

暂无评论

Integrated fuzzy particle filter based on multi-sensor integrated navigation system 17

Integrated fuzzy particle filter based on multi-sensor integ...

引用

3rd International Conference on Communication and Information Processing (ICCIP)

作者： Cheng Peng-zhan Dang Shu-wen He Fa-jiang Shanghai Univ Engn Sci Sch Mech Engn Shanghai 201620 Peoples R China Shanghai Univ Engn Sci Sch Air Transportat & Flying Shanghai 201620 Peoples R China

ISBN: (纸本)9781450353656

Based on the extended Kalman filter (EKF) algorithm, a new fusion method based particle filtering algorithm (PF) is presented, in which the importance density is generated by means of a fusion algorithm. To derive the importance density of samples, the state of each particle of the individual sensor is predicted separately according to EKF. An application example is given to draw a comparison between this new algorithm(Integrated Fuzzy Particle Filter, IFPF) and the traditional fuzzy particle filter (FPF) algorithm. The experimental results show that the IFPF algorithm is much higher than the FPF algorithm in stability, and especially when the mobile robot is turnning, the accuracy of movement speed increases about 69.2.

关键词： state estimation particle filtering(PF) algorithm fusion algorithm extended Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automatic Annotation for Optimal Image Retrieval

Enhancing Automatic Annotation for Optimal Image Retrieval

引用

作者： Mohamed Masoud Georgia State University

学位级别：博士

Image search and retrieval based on content is very cumbersome task particularly when the image database is large. The accuracy of the retrieval as well as the processing speed are two important measures used for assessing and comparing the effectiveness of various systems. Text retrieval is more mature and advanced than image content retrieval. In this dissertation, the focus is on converting image content into text tags that can be easily searched using standard search engines where the size and speed issues of the database have been already dealt with. Therefore, image tagging becomes an essential tool for image retrieval from large image databases. Automation of image tagging has received considerable attention by many researchers in recent years. The optimal goal of image description is to automatically annotate images with tags that semantically represent the image content. The speed and accuracy of Image retrieval from large databases are few of the important domains that can benefit from automatic tagging. In this work, several state of the art image classification and image tagging techniques are reviewed. We propose a new self-learning multilayered tagging framework that can address the limitations of current approaches and provide mutual accuracy improvement between the recognition layer and the annotation layer. Our results indicate that the proposed framework can improve the overall accuracy of information retrieval in a variety of image databases.

关键词： Image annotation Histograms of Oriented Gradients Improved fisher kernel Deep learning fusion algorithm Rejection principle

来源：评论

学校读者我要写书评

暂无评论

Using Kinect for real-time emotion recognition via facial expressions

引用

Frontiers of Information Technology & Electronic Engineering 2015年第4期16卷 272-282页

作者： Qi-rong MAO Xin-yu PAN Yong-zhao ZHAN Xiang-jun SHEN Department of Computer Science and Communication Engineering Jiangsu University

Emotion recognition via facial expressions （ERFE） has attracted a great deal of interest with recent advances in artificial intelligence and pattern recognition. Most studies are based on 2D images, and their performance is usually computationally expensive. In this paper, we propose a real-time emotion recognition approach based on both 2D and 3D facial expression features captured by Kinect sensors. To capture the deformation of the 3D mesh during facial expression, we combine the features of animation units （AUs） and feature point positions （FPPs） tracked by Kinect. A fusion algorithm based on improved emotional profiles （IEPs） arid maximum confidence is proposed to recognize emotions with these real-time facial expression features. Experiments on both an emotion dataset and a real-time video show the superior performance of our method.

关键词： Kinect Emotion recognition Facial expression Real-time classification fusion algorithm Supportvector machine （SVM）

来源：评论

学校读者我要写书评

暂无评论

Research On Unmanned Multi-Vehicle Cooperative Path Planning algorithm 5

Research On Unmanned Multi-Vehicle Cooperative Path Planning...

引用

5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023

作者： Mo, Liye Leng, Sixuan Lin, Xingzhi Pan, Xiang GuangXi Vocational Normal University Guangxi Nanning China

ISBN: (纸本)9798350357950

Aiming at the technical problems of dynamic adjustment and path planning in the process of unmanned multi-vehicle cooperation, the research of path planning algorithm, optimization algorithm, and path planning algorithm based on optimization algorithm was carried out from three aspects: algorithm principle, algorithm design, and algorithm experiments, and the technical methods such as the A∗ algorithm, DWA algorithm, and fusion algorithm were applied to realize efficient path planning and dynamic adjustment. The simulation model of the path planning algorithm was applied to carry out the unmanned multi-vehicle cooperative path planning algorithm experiments, and the results show that the DWA fusion A∗ algorithm as the technical solution of the unmanned multi-vehicle cooperative path planning algorithm is feasible. © 2023 IEEE.

关键词： A algorithm component fusion algorithm path planning self-driving

来源：评论

学校读者我要写书评

暂无评论

Infrared Weak-Small Target Image fusion Based on Contrast and Wavelet Transform

Infrared Weak-Small Target Image Fusion Based on Contrast an...

引用

作者： Kai Zhang Jun Wan Xiaozhu Wang Xiaoshuang Jiao School of Astronautics Northwestern Polytechnical University Beijing Aeronautical Technology Research Centre Academy of Space Information Systems

The image details and contour information cannot be fully reflected for the current infrared single-band data. It is difficult for the weak-small target to resist background interference after imaging, so that the image produces a lower signal to noise ratio. Therefore, it is necessary to use the texture difference of different band data to improve the signal-to-noise ratio of the image through the complementary fusion method. In this paper, based on weak-small targets in infrared images under different backgrounds, the paper proposes a fusion method based on contrast and wavelet transform. Firstly, the source images are denoised, and multiscale two-dimensional decomposition are performed to obtain low-frequency component and highfrequency component. On this basis, the high-frequency component adopt the method of maximizing absolute value, and the low-frequency component use the method of weighted averaging. Then the image is reconstructed. Finally, the reconstructed image is fused by gray contrast modulation. The fusion results are compared with many fusion algorithms. The experimental results show that the proposed algorithm can improve the intensity of weak-small targets and easily identify weak-small targets in the image. It solves the background interference problem of weak-small targets in the image.

关键词： Infrared dual-band Weak-small targets Contrast and wavelet transform fusion algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on fusion Technology of Multi-frequency Source in Time Frequency Synchronization Device

Research on Fusion Technology of Multi-frequency Source in T...

引用

2018 International Conference on Computational, Modeling, Simulation and Mathematical Statistics(CMSMS 2018)

作者： Zhi-hui WANG Ya-nan WANG Ni ZHEN Zheng-dong REN Xiang-zhou CHEN China Electric Power Research Institute China University of Geosciences(Beijing)

At present, according to the priority principle, the time frequency synchronization device uses one of the multi-frequency sources for time keeping, and the quality of synchronous signal cannot be optimized. To solve this problem, a time keeping algorithm for multi-frequency source fusion backup is proposed, and more accurate frequency signals are used for time keeping by fusing multiple frequency sources. Through the combination of theoretical analysis and experimental testing, the selection method of multi frequency source weights in the fusion algorithm is *** have verified the advantages of the multi-frequency source fusion algorithm when the frequency source is abnormal. The results of the study show that the use of unequal weights can make the stability of the frequency fusion better, and the fusion algorithm can effectively eliminate the abnormal frequency source, so that the frequency stability after fusion converges to the frequency stability of the optimal frequency source.

关键词： Power telecommunication Time frequency synchronization device fusion algorithm

来源：评论

学校读者我要写书评

暂无评论

Summarize of multi-sensor information fusion technology for USV colony

Summarize of multi-sensor information fusion technology for ...

引用

作者： Xufang Zhu Wenliang Huang Zhongjie Chen School of Electronic Engineering Naval University of Engineering

It has gained much attention since the birth of multi-source information fusion technology for its excellent overall system performance. This paper introduces the principle of multi-source information fusion and extends the model structure of target fusion, the fusion methods and practice problems such as target detection fusion, target position fusion, target identification fusion, STA and sensor control are summarized. Finally according to the complex environment, topology, network bandwidth and other practical requirements in the multi-source information fusion of USV colony, it provides support for The relevant research directions are given, it provides support for the follow-up research on information fusion of USV colony.

关键词： fusion detection position fusion identification fusion situation assessment threat assessment sensor control fusion algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive edge detection algorithm for multi-focus application

Adaptive edge detection algorithm for multi-focus applicatio...

引用

International Symposium on Consumer Technologies (ISCT)

作者： Bui, Trong-An Lee, Pei-Jun Natl Chi Nan Univ Elect Engn Dept Nantou Taiwan

ISBN: (纸本)9781538646151

This paper proposes a method of solving the problem of multi-focus through edge detection based on adaptive thresholding. Under conditions such as different light or different regions, the methods of solving the problem of multi focus based on conventional edge detection methods will not work well because they are based on a global value of thresholding. In this paper, we will focus on processing and be applying the adaptive threshold method in determining the regions in the multi-focus problem. We will combine the clustering method as k-mean in an image to combine with the area defined by edge detection through adaptive thresholding to define the best result. The fusion algorithm is applied to handle focused regions defined by the above method. The results and deployment environment we apply to mobile devices.

关键词： Mum-focus Edge detection Adaptive Threshold fusion algorithm Mobile phone Clustering

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-sensor Data fusion Technology

Research on Multi-sensor Data Fusion Technology

引用

作者： Yuqing Tong Jiujun Bai Xuebo Chen School of Electronic and Information Engineering University of Science and Technology Liaoning

Multi-source sensor information fusion mainly collects various types of information from multiple independent decentralized sensors. Due to the different types of information, specific combinations of time and events are required to make the collected information more advanced and useful information. From the level of fusion, it will be merged from the three levels of data set, feature level and decision-making level. For different practical problems, it is necessary to use a certain level of fusion or a certain two levels of fusion according to the situation, so as to obtain the most optimal integration scheme.

关键词： Multi-sensor Sensor integration fusion algorithm

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：